diff --git a/mg5amc/madgraph4gpu-2022/mg5amc-madgraph4gpu-2022.spec b/mg5amc/madgraph4gpu-2022/mg5amc-madgraph4gpu-2022.spec
index ac1ab5a77d31f0691a874863206766e7aa77d730..d5825e76cea35a683bab69a6c10d83e737930b8f 100644
--- a/mg5amc/madgraph4gpu-2022/mg5amc-madgraph4gpu-2022.spec
+++ b/mg5amc/madgraph4gpu-2022/mg5amc-madgraph4gpu-2022.spec
@@ -12,5 +12,5 @@ HEPWL_BMKDESCRIPTION="Madgraph5_aMCatNLO madgraph4gpu benchmark (2022)" # NB the
 HEPWL_BMKOS="gitlab-registry.cern.ch/linuxsupport/cc7-base:20220801-1.x86_64"
 HEPWL_BMKUSEGPU=1
 HEPWL_DOCKERIMAGENAME=mg5amc-madgraph4gpu-2022-bmk
-HEPWL_DOCKERIMAGETAG=ci-v0.7 # NB: use ci-vX.Y for tests (can be rebuilt) and vX.Y for production (cannot be rebuilt)
+HEPWL_DOCKERIMAGETAG=v0.7 # NB: use ci-vX.Y for tests (can be rebuilt) and vX.Y for production (cannot be rebuilt)
 HEPWL_CVMFSREPOS=sft.cern.ch
diff --git a/mg5amc/madgraph4gpu-2022/mg5amc-madgraph4gpu-2022/jobs/good_1/cishortlog.txt b/mg5amc/madgraph4gpu-2022/mg5amc-madgraph4gpu-2022/jobs/good_1/cishortlog.txt
index 01df3ba5c5ce58ddf1d350a1dc25c1483d9b35d4..1226b3a019108b512ddc7f62a93588e57931c9f6 100644
--- a/mg5amc/madgraph4gpu-2022/mg5amc-madgraph4gpu-2022/jobs/good_1/cishortlog.txt
+++ b/mg5amc/madgraph4gpu-2022/mg5amc-madgraph4gpu-2022/jobs/good_1/cishortlog.txt
@@ -1,9 +1,9 @@
     "copies": 1,
-{"run_info":{"copies":1,"threads_per_copy":1,"events_per_thread":2,"extra_arguments":"--both -eemumu -ggtt -ggttg -ggttgg -dbl -flt -inl0 -inl1"},"report":{"wl-scores":{"eemumu-sa-cuda-d-inl0":1130.432,"eemumu-sa-cuda-d-inl1":1128.067,"eemumu-sa-cuda-f-inl0":3036.306,"eemumu-sa-cuda-f-inl1":3029.1,"eemumu-sa-cpp-d-inl0-best":5.8463,"eemumu-sa-cpp-d-inl0-none":1.6029,"eemumu-sa-cpp-d-inl1-best":10.2311,"eemumu-sa-cpp-d-inl1-none":4.6502,"eemumu-sa-cpp-f-inl0-best":12.0628,"eemumu-sa-cpp-f-inl0-none":1.6559,"eemumu-sa-cpp-f-inl1-best":25.1426,"eemumu-sa-cpp-f-inl1-none":4.9364,"eemumu-sa-cpp-d-inl0-sse4":3.0622,"eemumu-sa-cpp-d-inl1-sse4":7.9254,"eemumu-sa-cpp-f-inl0-sse4":6.0888,"eemumu-sa-cpp-f-inl1-sse4":14.2969,"eemumu-sa-cpp-d-inl0-avx2":5.3727,"eemumu-sa-cpp-d-inl1-avx2":10.2311,"eemumu-sa-cpp-f-inl0-avx2":11.2383,"eemumu-sa-cpp-f-inl1-avx2":24.6208,"eemumu-sa-cpp-d-inl0-512y":5.8463,"eemumu-sa-cpp-d-inl1-512y":10.2161,"eemumu-sa-cpp-f-inl0-512y":12.0628,"eemumu-sa-cpp-f-inl1-512y":25.1426,"eemumu-sa-cpp-d-inl0-512z":4.743,"eemumu-sa-cpp-d-inl1-512z":8.5471,"eemumu-sa-cpp-f-inl0-512z":9.644,"eemumu-sa-cpp-f-inl1-512z":18.3169,"ggtt-sa-cuda-d-inl0":130.0122,"ggtt-sa-cuda-d-inl1":130.2486,"ggtt-sa-cuda-f-inl0":363.6906,"ggtt-sa-cuda-f-inl1":363.4642,"ggtt-sa-cpp-d-inl0-best":0.6213,"ggtt-sa-cpp-d-inl0-none":0.1912,"ggtt-sa-cpp-d-inl1-best":0.4756,"ggtt-sa-cpp-d-inl1-none":0.2335,"ggtt-sa-cpp-f-inl0-best":1.1129,"ggtt-sa-cpp-f-inl0-none":0.2,"ggtt-sa-cpp-f-inl1-best":0.7099,"ggtt-sa-cpp-f-inl1-none":0.2424,"ggtt-sa-cpp-d-inl0-sse4":0.3204,"ggtt-sa-cpp-d-inl1-sse4":0.2768,"ggtt-sa-cpp-f-inl0-sse4":0.4764,"ggtt-sa-cpp-f-inl1-sse4":0.5602,"ggtt-sa-cpp-d-inl0-avx2":0.5574,"ggtt-sa-cpp-d-inl1-avx2":0.4593,"ggtt-sa-cpp-f-inl0-avx2":1.0353,"ggtt-sa-cpp-f-inl1-avx2":0.7014,"ggtt-sa-cpp-d-inl0-512y":0.6213,"ggtt-sa-cpp-d-inl1-512y":0.4756,"ggtt-sa-cpp-f-inl0-512y":1.1129,"ggtt-sa-cpp-f-inl1-512y":0.7099,"ggtt-sa-cpp-d-inl0-512z":0.3732,"ggtt-sa-cpp-d-inl1-512z":0.3438,"ggtt-sa-cpp-f-inl0-512z":0.7762,"ggtt-sa-cpp-f-inl1-512z":0.5638,"ggttg-sa-cuda-d-inl0":13.4296,"ggttg-sa-cuda-d-inl1":13.4207,"ggttg-sa-cuda-f-inl0":45.8793,"ggttg-sa-cuda-f-inl1":45.5322,"ggttg-sa-cpp-d-inl0-best":0.1,"ggttg-sa-cpp-d-inl0-none":0.0238,"ggttg-sa-cpp-d-inl1-best":0.0889,"ggttg-sa-cpp-d-inl1-none":0.0063,"ggttg-sa-cpp-f-inl0-best":0.1974,"ggttg-sa-cpp-f-inl0-none":0.0244,"ggttg-sa-cpp-f-inl1-best":0.1555,"ggttg-sa-cpp-f-inl1-none":0.0102,"ggttg-sa-cpp-d-inl0-sse4":0.0448,"ggttg-sa-cpp-d-inl1-sse4":0.0417,"ggttg-sa-cpp-f-inl0-sse4":0.082,"ggttg-sa-cpp-f-inl1-sse4":0.087,"ggttg-sa-cpp-d-inl0-avx2":0.0873,"ggttg-sa-cpp-d-inl1-avx2":0.0806,"ggttg-sa-cpp-f-inl0-avx2":0.1742,"ggttg-sa-cpp-f-inl1-avx2":0.1402,"ggttg-sa-cpp-d-inl0-512y":0.1,"ggttg-sa-cpp-d-inl1-512y":0.0889,"ggttg-sa-cpp-f-inl0-512y":0.1974,"ggttg-sa-cpp-f-inl1-512y":0.1555,"ggttg-sa-cpp-d-inl0-512z":0.0722,"ggttg-sa-cpp-d-inl1-512z":0.0648,"ggttg-sa-cpp-f-inl0-512z":0.1502,"ggttg-sa-cpp-f-inl1-512z":0.115,"ggttgg-sa-cuda-d-inl0":0.4201,"ggttgg-sa-cuda-d-inl1":0.3868,"ggttgg-sa-cuda-f-inl0":0.8683,"ggttgg-sa-cuda-f-inl1":0.7768,"ggttgg-sa-cpp-d-inl0-best":0.0075,"ggttgg-sa-cpp-d-inl0-none":0.0017,"ggttgg-sa-cpp-d-inl1-best":0.0069,"ggttgg-sa-cpp-d-inl1-none":0.0004,"ggttgg-sa-cpp-f-inl0-best":0.0149,"ggttgg-sa-cpp-f-inl0-none":0.0018,"ggttgg-sa-cpp-f-inl1-best":0.0134,"ggttgg-sa-cpp-f-inl1-none":0.0005,"ggttgg-sa-cpp-d-inl0-sse4":0.0033,"ggttgg-sa-cpp-d-inl1-sse4":0.0028,"ggttgg-sa-cpp-f-inl0-sse4":0.0069,"ggttgg-sa-cpp-f-inl1-sse4":0.0061,"ggttgg-sa-cpp-d-inl0-avx2":0.0067,"ggttgg-sa-cpp-d-inl1-avx2":0.0054,"ggttgg-sa-cpp-f-inl0-avx2":0.0134,"ggttgg-sa-cpp-f-inl1-avx2":0.0106,"ggttgg-sa-cpp-d-inl0-512y":0.0075,"ggttgg-sa-cpp-d-inl1-512y":0.0069,"ggttgg-sa-cpp-f-inl0-512y":0.0149,"ggttgg-sa-cpp-f-inl1-512y":0.0134,"ggttgg-sa-cpp-d-inl0-512z":0.0065,"ggttgg-sa-cpp-d-inl1-512z":0.0065,"ggttgg-sa-cpp-f-inl0-512z":0.0131,"ggttgg-sa-cpp-f-inl1-512z":0.0126},"wl-stats":{"eemumu-sa-cuda-d-inl0":{"avg":1130.432,"median":1130.432,"min":1130.432,"max":1130.432,"count":1},"eemumu-sa-cuda-d-inl1":{"avg":1128.067,"median":1128.067,"min":1128.067,"max":1128.067,"count":1},"eemumu-sa-cuda-f-inl0":{"avg":3036.306,"median":3036.306,"min":3036.306,"max":3036.306,"count":1},"eemumu-sa-cuda-f-inl1":{"avg":3029.1,"median":3029.1,"min":3029.1,"max":3029.1,"count":1},"eemumu-sa-cpp-d-inl0-best":{"avg":5.8463,"median":5.8463,"min":5.8463,"max":5.8463,"count":1},"eemumu-sa-cpp-d-inl0-none":{"avg":1.6029,"median":1.6029,"min":1.6029,"max":1.6029,"count":1},"eemumu-sa-cpp-d-inl1-best":{"avg":10.2311,"median":10.2311,"min":10.2311,"max":10.2311,"count":1},"eemumu-sa-cpp-d-inl1-none":{"avg":4.6502,"median":4.6502,"min":4.6502,"max":4.6502,"count":1},"eemumu-sa-cpp-f-inl0-best":{"avg":12.0628,"median":12.0628,"min":12.0628,"max":12.0628,"count":1},"eemumu-sa-cpp-f-inl0-none":{"avg":1.6559,"median":1.6559,"min":1.6559,"max":1.6559,"count":1},"eemumu-sa-cpp-f-inl1-best":{"avg":25.1426,"median":25.1426,"min":25.1426,"max":25.1426,"count":1},"eemumu-sa-cpp-f-inl1-none":{"avg":4.9364,"median":4.9364,"min":4.9364,"max":4.9364,"count":1},"eemumu-sa-cpp-d-inl0-sse4":{"avg":3.0622,"median":3.0622,"min":3.0622,"max":3.0622,"count":1},"eemumu-sa-cpp-d-inl1-sse4":{"avg":7.9254,"median":7.9254,"min":7.9254,"max":7.9254,"count":1},"eemumu-sa-cpp-f-inl0-sse4":{"avg":6.0888,"median":6.0888,"min":6.0888,"max":6.0888,"count":1},"eemumu-sa-cpp-f-inl1-sse4":{"avg":14.2969,"median":14.2969,"min":14.2969,"max":14.2969,"count":1},"eemumu-sa-cpp-d-inl0-avx2":{"avg":5.3727,"median":5.3727,"min":5.3727,"max":5.3727,"count":1},"eemumu-sa-cpp-d-inl1-avx2":{"avg":10.2311,"median":10.2311,"min":10.2311,"max":10.2311,"count":1},"eemumu-sa-cpp-f-inl0-avx2":{"avg":11.2383,"median":11.2383,"min":11.2383,"max":11.2383,"count":1},"eemumu-sa-cpp-f-inl1-avx2":{"avg":24.6208,"median":24.6208,"min":24.6208,"max":24.6208,"count":1},"eemumu-sa-cpp-d-inl0-512y":{"avg":5.8463,"median":5.8463,"min":5.8463,"max":5.8463,"count":1},"eemumu-sa-cpp-d-inl1-512y":{"avg":10.2161,"median":10.2161,"min":10.2161,"max":10.2161,"count":1},"eemumu-sa-cpp-f-inl0-512y":{"avg":12.0628,"median":12.0628,"min":12.0628,"max":12.0628,"count":1},"eemumu-sa-cpp-f-inl1-512y":{"avg":25.1426,"median":25.1426,"min":25.1426,"max":25.1426,"count":1},"eemumu-sa-cpp-d-inl0-512z":{"avg":4.743,"median":4.743,"min":4.743,"max":4.743,"count":1},"eemumu-sa-cpp-d-inl1-512z":{"avg":8.5471,"median":8.5471,"min":8.5471,"max":8.5471,"count":1},"eemumu-sa-cpp-f-inl0-512z":{"avg":9.644,"median":9.644,"min":9.644,"max":9.644,"count":1},"eemumu-sa-cpp-f-inl1-512z":{"avg":18.3169,"median":18.3169,"min":18.3169,"max":18.3169,"count":1},"ggtt-sa-cuda-d-inl0":{"avg":130.0122,"median":130.0122,"min":130.0122,"max":130.0122,"count":1},"ggtt-sa-cuda-d-inl1":{"avg":130.2486,"median":130.2486,"min":130.2486,"max":130.2486,"count":1},"ggtt-sa-cuda-f-inl0":{"avg":363.6906,"median":363.6906,"min":363.6906,"max":363.6906,"count":1},"ggtt-sa-cuda-f-inl1":{"avg":363.4642,"median":363.4642,"min":363.4642,"max":363.4642,"count":1},"ggtt-sa-cpp-d-inl0-best":{"avg":0.6213,"median":0.6213,"min":0.6213,"max":0.6213,"count":1},"ggtt-sa-cpp-d-inl0-none":{"avg":0.1912,"median":0.1912,"min":0.1912,"max":0.1912,"count":1},"ggtt-sa-cpp-d-inl1-best":{"avg":0.4756,"median":0.4756,"min":0.4756,"max":0.4756,"count":1},"ggtt-sa-cpp-d-inl1-none":{"avg":0.2335,"median":0.2335,"min":0.2335,"max":0.2335,"count":1},"ggtt-sa-cpp-f-inl0-best":{"avg":1.1129,"median":1.1129,"min":1.1129,"max":1.1129,"count":1},"ggtt-sa-cpp-f-inl0-none":{"avg":0.2,"median":0.2,"min":0.2,"max":0.2,"count":1},"ggtt-sa-cpp-f-inl1-best":{"avg":0.7099,"median":0.7099,"min":0.7099,"max":0.7099,"count":1},"ggtt-sa-cpp-f-inl1-none":{"avg":0.2424,"median":0.2424,"min":0.2424,"max":0.2424,"count":1},"ggtt-sa-cpp-d-inl0-sse4":{"avg":0.3204,"median":0.3204,"min":0.3204,"max":0.3204,"count":1},"ggtt-sa-cpp-d-inl1-sse4":{"avg":0.2768,"median":0.2768,"min":0.2768,"max":0.2768,"count":1},"ggtt-sa-cpp-f-inl0-sse4":{"avg":0.4764,"median":0.4764,"min":0.4764,"max":0.4764,"count":1},"ggtt-sa-cpp-f-inl1-sse4":{"avg":0.5602,"median":0.5602,"min":0.5602,"max":0.5602,"count":1},"ggtt-sa-cpp-d-inl0-avx2":{"avg":0.5574,"median":0.5574,"min":0.5574,"max":0.5574,"count":1},"ggtt-sa-cpp-d-inl1-avx2":{"avg":0.4593,"median":0.4593,"min":0.4593,"max":0.4593,"count":1},"ggtt-sa-cpp-f-inl0-avx2":{"avg":1.0353,"median":1.0353,"min":1.0353,"max":1.0353,"count":1},"ggtt-sa-cpp-f-inl1-avx2":{"avg":0.7014,"median":0.7014,"min":0.7014,"max":0.7014,"count":1},"ggtt-sa-cpp-d-inl0-512y":{"avg":0.6213,"median":0.6213,"min":0.6213,"max":0.6213,"count":1},"ggtt-sa-cpp-d-inl1-512y":{"avg":0.4756,"median":0.4756,"min":0.4756,"max":0.4756,"count":1},"ggtt-sa-cpp-f-inl0-512y":{"avg":1.1129,"median":1.1129,"min":1.1129,"max":1.1129,"count":1},"ggtt-sa-cpp-f-inl1-512y":{"avg":0.7099,"median":0.7099,"min":0.7099,"max":0.7099,"count":1},"ggtt-sa-cpp-d-inl0-512z":{"avg":0.3732,"median":0.3732,"min":0.3732,"max":0.3732,"count":1},"ggtt-sa-cpp-d-inl1-512z":{"avg":0.3438,"median":0.3438,"min":0.3438,"max":0.3438,"count":1},"ggtt-sa-cpp-f-inl0-512z":{"avg":0.7762,"median":0.7762,"min":0.7762,"max":0.7762,"count":1},"ggtt-sa-cpp-f-inl1-512z":{"avg":0.5638,"median":0.5638,"min":0.5638,"max":0.5638,"count":1},"ggttg-sa-cuda-d-inl0":{"avg":13.4296,"median":13.4296,"min":13.4296,"max":13.4296,"count":1},"ggttg-sa-cuda-d-inl1":{"avg":13.4207,"median":13.4207,"min":13.4207,"max":13.4207,"count":1},"ggttg-sa-cuda-f-inl0":{"avg":45.8793,"median":45.8793,"min":45.8793,"max":45.8793,"count":1},"ggttg-sa-cuda-f-inl1":{"avg":45.5322,"median":45.5322,"min":45.5322,"max":45.5322,"count":1},"ggttg-sa-cpp-d-inl0-best":{"avg":0.1,"median":0.1,"min":0.1,"max":0.1,"count":1},"ggttg-sa-cpp-d-inl0-none":{"avg":0.0238,"median":0.0238,"min":0.0238,"max":0.0238,"count":1},"ggttg-sa-cpp-d-inl1-best":{"avg":0.0889,"median":0.0889,"min":0.0889,"max":0.0889,"count":1},"ggttg-sa-cpp-d-inl1-none":{"avg":0.0063,"median":0.0063,"min":0.0063,"max":0.0063,"count":1},"ggttg-sa-cpp-f-inl0-best":{"avg":0.1974,"median":0.1974,"min":0.1974,"max":0.1974,"count":1},"ggttg-sa-cpp-f-inl0-none":{"avg":0.0244,"median":0.0244,"min":0.0244,"max":0.0244,"count":1},"ggttg-sa-cpp-f-inl1-best":{"avg":0.1555,"median":0.1555,"min":0.1555,"max":0.1555,"count":1},"ggttg-sa-cpp-f-inl1-none":{"avg":0.0102,"median":0.0102,"min":0.0102,"max":0.0102,"count":1},"ggttg-sa-cpp-d-inl0-sse4":{"avg":0.0448,"median":0.0448,"min":0.0448,"max":0.0448,"count":1},"ggttg-sa-cpp-d-inl1-sse4":{"avg":0.0417,"median":0.0417,"min":0.0417,"max":0.0417,"count":1},"ggttg-sa-cpp-f-inl0-sse4":{"avg":0.082,"median":0.082,"min":0.082,"max":0.082,"count":1},"ggttg-sa-cpp-f-inl1-sse4":{"avg":0.087,"median":0.087,"min":0.087,"max":0.087,"count":1},"ggttg-sa-cpp-d-inl0-avx2":{"avg":0.0873,"median":0.0873,"min":0.0873,"max":0.0873,"count":1},"ggttg-sa-cpp-d-inl1-avx2":{"avg":0.0806,"median":0.0806,"min":0.0806,"max":0.0806,"count":1},"ggttg-sa-cpp-f-inl0-avx2":{"avg":0.1742,"median":0.1742,"min":0.1742,"max":0.1742,"count":1},"ggttg-sa-cpp-f-inl1-avx2":{"avg":0.1402,"median":0.1402,"min":0.1402,"max":0.1402,"count":1},"ggttg-sa-cpp-d-inl0-512y":{"avg":0.1,"median":0.1,"min":0.1,"max":0.1,"count":1},"ggttg-sa-cpp-d-inl1-512y":{"avg":0.0889,"median":0.0889,"min":0.0889,"max":0.0889,"count":1},"ggttg-sa-cpp-f-inl0-512y":{"avg":0.1974,"median":0.1974,"min":0.1974,"max":0.1974,"count":1},"ggttg-sa-cpp-f-inl1-512y":{"avg":0.1555,"median":0.1555,"min":0.1555,"max":0.1555,"count":1},"ggttg-sa-cpp-d-inl0-512z":{"avg":0.0722,"median":0.0722,"min":0.0722,"max":0.0722,"count":1},"ggttg-sa-cpp-d-inl1-512z":{"avg":0.0648,"median":0.0648,"min":0.0648,"max":0.0648,"count":1},"ggttg-sa-cpp-f-inl0-512z":{"avg":0.1502,"median":0.1502,"min":0.1502,"max":0.1502,"count":1},"ggttg-sa-cpp-f-inl1-512z":{"avg":0.115,"median":0.115,"min":0.115,"max":0.115,"count":1},"ggttgg-sa-cuda-d-inl0":{"avg":0.4201,"median":0.4201,"min":0.4201,"max":0.4201,"count":1},"ggttgg-sa-cuda-d-inl1":{"avg":0.3868,"median":0.3868,"min":0.3868,"max":0.3868,"count":1},"ggttgg-sa-cuda-f-inl0":{"avg":0.8683,"median":0.8683,"min":0.8683,"max":0.8683,"count":1},"ggttgg-sa-cuda-f-inl1":{"avg":0.7768,"median":0.7768,"min":0.7768,"max":0.7768,"count":1},"ggttgg-sa-cpp-d-inl0-best":{"avg":0.0075,"median":0.0075,"min":0.0075,"max":0.0075,"count":1},"ggttgg-sa-cpp-d-inl0-none":{"avg":0.0017,"median":0.0017,"min":0.0017,"max":0.0017,"count":1},"ggttgg-sa-cpp-d-inl1-best":{"avg":0.0069,"median":0.0069,"min":0.0069,"max":0.0069,"count":1},"ggttgg-sa-cpp-d-inl1-none":{"avg":0.0004,"median":0.0004,"min":0.0004,"max":0.0004,"count":1},"ggttgg-sa-cpp-f-inl0-best":{"avg":0.0149,"median":0.0149,"min":0.0149,"max":0.0149,"count":1},"ggttgg-sa-cpp-f-inl0-none":{"avg":0.0018,"median":0.0018,"min":0.0018,"max":0.0018,"count":1},"ggttgg-sa-cpp-f-inl1-best":{"avg":0.0134,"median":0.0134,"min":0.0134,"max":0.0134,"count":1},"ggttgg-sa-cpp-f-inl1-none":{"avg":0.0005,"median":0.0005,"min":0.0005,"max":0.0005,"count":1},"ggttgg-sa-cpp-d-inl0-sse4":{"avg":0.0033,"median":0.0033,"min":0.0033,"max":0.0033,"count":1},"ggttgg-sa-cpp-d-inl1-sse4":{"avg":0.0028,"median":0.0028,"min":0.0028,"max":0.0028,"count":1},"ggttgg-sa-cpp-f-inl0-sse4":{"avg":0.0069,"median":0.0069,"min":0.0069,"max":0.0069,"count":1},"ggttgg-sa-cpp-f-inl1-sse4":{"avg":0.0061,"median":0.0061,"min":0.0061,"max":0.0061,"count":1},"ggttgg-sa-cpp-d-inl0-avx2":{"avg":0.0067,"median":0.0067,"min":0.0067,"max":0.0067,"count":1},"ggttgg-sa-cpp-d-inl1-avx2":{"avg":0.0054,"median":0.0054,"min":0.0054,"max":0.0054,"count":1},"ggttgg-sa-cpp-f-inl0-avx2":{"avg":0.0134,"median":0.0134,"min":0.0134,"max":0.0134,"count":1},"ggttgg-sa-cpp-f-inl1-avx2":{"avg":0.0106,"median":0.0106,"min":0.0106,"max":0.0106,"count":1},"ggttgg-sa-cpp-d-inl0-512y":{"avg":0.0075,"median":0.0075,"min":0.0075,"max":0.0075,"count":1},"ggttgg-sa-cpp-d-inl1-512y":{"avg":0.0069,"median":0.0069,"min":0.0069,"max":0.0069,"count":1},"ggttgg-sa-cpp-f-inl0-512y":{"avg":0.0149,"median":0.0149,"min":0.0149,"max":0.0149,"count":1},"ggttgg-sa-cpp-f-inl1-512y":{"avg":0.0134,"median":0.0134,"min":0.0134,"max":0.0134,"count":1},"ggttgg-sa-cpp-d-inl0-512z":{"avg":0.0065,"median":0.0065,"min":0.0065,"max":0.0065,"count":1},"ggttgg-sa-cpp-d-inl1-512z":{"avg":0.0065,"median":0.0065,"min":0.0065,"max":0.0065,"count":1},"ggttgg-sa-cpp-f-inl0-512z":{"avg":0.0131,"median":0.0131,"min":0.0131,"max":0.0131,"count":1},"ggttgg-sa-cpp-f-inl1-512z":{"avg":0.0126,"median":0.0126,"min":0.0126,"max":0.0126,"count":1}},"log":"ok"},"app":{"version":"ci-v0.6","description":"Madgraph5_aMCatNLO madgraph4gpu benchmark (2022)","cvmfs_checksum":"05f5179a44c0e2051bbb092a63cf0daf","bmkdata_checksum":"4eb8273563af22b829ddbf985ae0b0a9","bmk_checksum":"9b7bedb12e18a214106591542f8b3093","containment":"docker"}}
-{"run_info":{"copies":1,"threads_per_copy":1,"events_per_thread":2,"extra_arguments":"--both -eemumu -ggtt -ggttg -ggttgg -dbl -flt -inl0 -inl1"},"report":{"wl-scores":{"eemumu-sa-cuda-d-inl0":1130.432,"eemumu-sa-cuda-d-inl1":1128.067,"eemumu-sa-cuda-f-inl0":3036.306,"eemumu-sa-cuda-f-inl1":3029.1,"eemumu-sa-cpp-d-inl0-best":5.8463,"eemumu-sa-cpp-d-inl0-none":1.6029,"eemumu-sa-cpp-d-inl1-best":10.2311,"eemumu-sa-cpp-d-inl1-none":4.6502,"eemumu-sa-cpp-f-inl0-best":12.0628,"eemumu-sa-cpp-f-inl0-none":1.6559,"eemumu-sa-cpp-f-inl1-best":25.1426,"eemumu-sa-cpp-f-inl1-none":4.9364,"eemumu-sa-cpp-d-inl0-sse4":3.0622,"eemumu-sa-cpp-d-inl1-sse4":7.9254,"eemumu-sa-cpp-f-inl0-sse4":6.0888,"eemumu-sa-cpp-f-inl1-sse4":14.2969,"eemumu-sa-cpp-d-inl0-avx2":5.3727,"eemumu-sa-cpp-d-inl1-avx2":10.2311,"eemumu-sa-cpp-f-inl0-avx2":11.2383,"eemumu-sa-cpp-f-inl1-avx2":24.6208,"eemumu-sa-cpp-d-inl0-512y":5.8463,"eemumu-sa-cpp-d-inl1-512y":10.2161,"eemumu-sa-cpp-f-inl0-512y":12.0628,"eemumu-sa-cpp-f-inl1-512y":25.1426,"eemumu-sa-cpp-d-inl0-512z":4.743,"eemumu-sa-cpp-d-inl1-512z":8.5471,"eemumu-sa-cpp-f-inl0-512z":9.644,"eemumu-sa-cpp-f-inl1-512z":18.3169,"ggtt-sa-cuda-d-inl0":130.0122,"ggtt-sa-cuda-d-inl1":130.2486,"ggtt-sa-cuda-f-inl0":363.6906,"ggtt-sa-cuda-f-inl1":363.4642,"ggtt-sa-cpp-d-inl0-best":0.6213,"ggtt-sa-cpp-d-inl0-none":0.1912,"ggtt-sa-cpp-d-inl1-best":0.4756,"ggtt-sa-cpp-d-inl1-none":0.2335,"ggtt-sa-cpp-f-inl0-best":1.1129,"ggtt-sa-cpp-f-inl0-none":0.2,"ggtt-sa-cpp-f-inl1-best":0.7099,"ggtt-sa-cpp-f-inl1-none":0.2424,"ggtt-sa-cpp-d-inl0-sse4":0.3204,"ggtt-sa-cpp-d-inl1-sse4":0.2768,"ggtt-sa-cpp-f-inl0-sse4":0.4764,"ggtt-sa-cpp-f-inl1-sse4":0.5602,"ggtt-sa-cpp-d-inl0-avx2":0.5574,"ggtt-sa-cpp-d-inl1-avx2":0.4593,"ggtt-sa-cpp-f-inl0-avx2":1.0353,"ggtt-sa-cpp-f-inl1-avx2":0.7014,"ggtt-sa-cpp-d-inl0-512y":0.6213,"ggtt-sa-cpp-d-inl1-512y":0.4756,"ggtt-sa-cpp-f-inl0-512y":1.1129,"ggtt-sa-cpp-f-inl1-512y":0.7099,"ggtt-sa-cpp-d-inl0-512z":0.3732,"ggtt-sa-cpp-d-inl1-512z":0.3438,"ggtt-sa-cpp-f-inl0-512z":0.7762,"ggtt-sa-cpp-f-inl1-512z":0.5638,"ggttg-sa-cuda-d-inl0":13.4296,"ggttg-sa-cuda-d-inl1":13.4207,"ggttg-sa-cuda-f-inl0":45.8793,"ggttg-sa-cuda-f-inl1":45.5322,"ggttg-sa-cpp-d-inl0-best":0.1,"ggttg-sa-cpp-d-inl0-none":0.0238,"ggttg-sa-cpp-d-inl1-best":0.0889,"ggttg-sa-cpp-d-inl1-none":0.0063,"ggttg-sa-cpp-f-inl0-best":0.1974,"ggttg-sa-cpp-f-inl0-none":0.0244,"ggttg-sa-cpp-f-inl1-best":0.1555,"ggttg-sa-cpp-f-inl1-none":0.0102,"ggttg-sa-cpp-d-inl0-sse4":0.0448,"ggttg-sa-cpp-d-inl1-sse4":0.0417,"ggttg-sa-cpp-f-inl0-sse4":0.082,"ggttg-sa-cpp-f-inl1-sse4":0.087,"ggttg-sa-cpp-d-inl0-avx2":0.0873,"ggttg-sa-cpp-d-inl1-avx2":0.0806,"ggttg-sa-cpp-f-inl0-avx2":0.1742,"ggttg-sa-cpp-f-inl1-avx2":0.1402,"ggttg-sa-cpp-d-inl0-512y":0.1,"ggttg-sa-cpp-d-inl1-512y":0.0889,"ggttg-sa-cpp-f-inl0-512y":0.1974,"ggttg-sa-cpp-f-inl1-512y":0.1555,"ggttg-sa-cpp-d-inl0-512z":0.0722,"ggttg-sa-cpp-d-inl1-512z":0.0648,"ggttg-sa-cpp-f-inl0-512z":0.1502,"ggttg-sa-cpp-f-inl1-512z":0.115,"ggttgg-sa-cuda-d-inl0":0.4201,"ggttgg-sa-cuda-d-inl1":0.3868,"ggttgg-sa-cuda-f-inl0":0.8683,"ggttgg-sa-cuda-f-inl1":0.7768,"ggttgg-sa-cpp-d-inl0-best":0.0075,"ggttgg-sa-cpp-d-inl0-none":0.0017,"ggttgg-sa-cpp-d-inl1-best":0.0069,"ggttgg-sa-cpp-d-inl1-none":0.0004,"ggttgg-sa-cpp-f-inl0-best":0.0149,"ggttgg-sa-cpp-f-inl0-none":0.0018,"ggttgg-sa-cpp-f-inl1-best":0.0134,"ggttgg-sa-cpp-f-inl1-none":0.0005,"ggttgg-sa-cpp-d-inl0-sse4":0.0033,"ggttgg-sa-cpp-d-inl1-sse4":0.0028,"ggttgg-sa-cpp-f-inl0-sse4":0.0069,"ggttgg-sa-cpp-f-inl1-sse4":0.0061,"ggttgg-sa-cpp-d-inl0-avx2":0.0067,"ggttgg-sa-cpp-d-inl1-avx2":0.0054,"ggttgg-sa-cpp-f-inl0-avx2":0.0134,"ggttgg-sa-cpp-f-inl1-avx2":0.0106,"ggttgg-sa-cpp-d-inl0-512y":0.0075,"ggttgg-sa-cpp-d-inl1-512y":0.0069,"ggttgg-sa-cpp-f-inl0-512y":0.0149,"ggttgg-sa-cpp-f-inl1-512y":0.0134,"ggttgg-sa-cpp-d-inl0-512z":0.0065,"ggttgg-sa-cpp-d-inl1-512z":0.0065,"ggttgg-sa-cpp-f-inl0-512z":0.0131,"ggttgg-sa-cpp-f-inl1-512z":0.0126},"wl-stats":{"eemumu-sa-cuda-d-inl0":{"avg":1130.432,"median":1130.432,"min":1130.432,"max":1130.432,"count":1},"eemumu-sa-cuda-d-inl1":{"avg":1128.067,"median":1128.067,"min":1128.067,"max":1128.067,"count":1},"eemumu-sa-cuda-f-inl0":{"avg":3036.306,"median":3036.306,"min":3036.306,"max":3036.306,"count":1},"eemumu-sa-cuda-f-inl1":{"avg":3029.1,"median":3029.1,"min":3029.1,"max":3029.1,"count":1},"eemumu-sa-cpp-d-inl0-best":{"avg":5.8463,"median":5.8463,"min":5.8463,"max":5.8463,"count":1},"eemumu-sa-cpp-d-inl0-none":{"avg":1.6029,"median":1.6029,"min":1.6029,"max":1.6029,"count":1},"eemumu-sa-cpp-d-inl1-best":{"avg":10.2311,"median":10.2311,"min":10.2311,"max":10.2311,"count":1},"eemumu-sa-cpp-d-inl1-none":{"avg":4.6502,"median":4.6502,"min":4.6502,"max":4.6502,"count":1},"eemumu-sa-cpp-f-inl0-best":{"avg":12.0628,"median":12.0628,"min":12.0628,"max":12.0628,"count":1},"eemumu-sa-cpp-f-inl0-none":{"avg":1.6559,"median":1.6559,"min":1.6559,"max":1.6559,"count":1},"eemumu-sa-cpp-f-inl1-best":{"avg":25.1426,"median":25.1426,"min":25.1426,"max":25.1426,"count":1},"eemumu-sa-cpp-f-inl1-none":{"avg":4.9364,"median":4.9364,"min":4.9364,"max":4.9364,"count":1},"eemumu-sa-cpp-d-inl0-sse4":{"avg":3.0622,"median":3.0622,"min":3.0622,"max":3.0622,"count":1},"eemumu-sa-cpp-d-inl1-sse4":{"avg":7.9254,"median":7.9254,"min":7.9254,"max":7.9254,"count":1},"eemumu-sa-cpp-f-inl0-sse4":{"avg":6.0888,"median":6.0888,"min":6.0888,"max":6.0888,"count":1},"eemumu-sa-cpp-f-inl1-sse4":{"avg":14.2969,"median":14.2969,"min":14.2969,"max":14.2969,"count":1},"eemumu-sa-cpp-d-inl0-avx2":{"avg":5.3727,"median":5.3727,"min":5.3727,"max":5.3727,"count":1},"eemumu-sa-cpp-d-inl1-avx2":{"avg":10.2311,"median":10.2311,"min":10.2311,"max":10.2311,"count":1},"eemumu-sa-cpp-f-inl0-avx2":{"avg":11.2383,"median":11.2383,"min":11.2383,"max":11.2383,"count":1},"eemumu-sa-cpp-f-inl1-avx2":{"avg":24.6208,"median":24.6208,"min":24.6208,"max":24.6208,"count":1},"eemumu-sa-cpp-d-inl0-512y":{"avg":5.8463,"median":5.8463,"min":5.8463,"max":5.8463,"count":1},"eemumu-sa-cpp-d-inl1-512y":{"avg":10.2161,"median":10.2161,"min":10.2161,"max":10.2161,"count":1},"eemumu-sa-cpp-f-inl0-512y":{"avg":12.0628,"median":12.0628,"min":12.0628,"max":12.0628,"count":1},"eemumu-sa-cpp-f-inl1-512y":{"avg":25.1426,"median":25.1426,"min":25.1426,"max":25.1426,"count":1},"eemumu-sa-cpp-d-inl0-512z":{"avg":4.743,"median":4.743,"min":4.743,"max":4.743,"count":1},"eemumu-sa-cpp-d-inl1-512z":{"avg":8.5471,"median":8.5471,"min":8.5471,"max":8.5471,"count":1},"eemumu-sa-cpp-f-inl0-512z":{"avg":9.644,"median":9.644,"min":9.644,"max":9.644,"count":1},"eemumu-sa-cpp-f-inl1-512z":{"avg":18.3169,"median":18.3169,"min":18.3169,"max":18.3169,"count":1},"ggtt-sa-cuda-d-inl0":{"avg":130.0122,"median":130.0122,"min":130.0122,"max":130.0122,"count":1},"ggtt-sa-cuda-d-inl1":{"avg":130.2486,"median":130.2486,"min":130.2486,"max":130.2486,"count":1},"ggtt-sa-cuda-f-inl0":{"avg":363.6906,"median":363.6906,"min":363.6906,"max":363.6906,"count":1},"ggtt-sa-cuda-f-inl1":{"avg":363.4642,"median":363.4642,"min":363.4642,"max":363.4642,"count":1},"ggtt-sa-cpp-d-inl0-best":{"avg":0.6213,"median":0.6213,"min":0.6213,"max":0.6213,"count":1},"ggtt-sa-cpp-d-inl0-none":{"avg":0.1912,"median":0.1912,"min":0.1912,"max":0.1912,"count":1},"ggtt-sa-cpp-d-inl1-best":{"avg":0.4756,"median":0.4756,"min":0.4756,"max":0.4756,"count":1},"ggtt-sa-cpp-d-inl1-none":{"avg":0.2335,"median":0.2335,"min":0.2335,"max":0.2335,"count":1},"ggtt-sa-cpp-f-inl0-best":{"avg":1.1129,"median":1.1129,"min":1.1129,"max":1.1129,"count":1},"ggtt-sa-cpp-f-inl0-none":{"avg":0.2,"median":0.2,"min":0.2,"max":0.2,"count":1},"ggtt-sa-cpp-f-inl1-best":{"avg":0.7099,"median":0.7099,"min":0.7099,"max":0.7099,"count":1},"ggtt-sa-cpp-f-inl1-none":{"avg":0.2424,"median":0.2424,"min":0.2424,"max":0.2424,"count":1},"ggtt-sa-cpp-d-inl0-sse4":{"avg":0.3204,"median":0.3204,"min":0.3204,"max":0.3204,"count":1},"ggtt-sa-cpp-d-inl1-sse4":{"avg":0.2768,"median":0.2768,"min":0.2768,"max":0.2768,"count":1},"ggtt-sa-cpp-f-inl0-sse4":{"avg":0.4764,"median":0.4764,"min":0.4764,"max":0.4764,"count":1},"ggtt-sa-cpp-f-inl1-sse4":{"avg":0.5602,"median":0.5602,"min":0.5602,"max":0.5602,"count":1},"ggtt-sa-cpp-d-inl0-avx2":{"avg":0.5574,"median":0.5574,"min":0.5574,"max":0.5574,"count":1},"ggtt-sa-cpp-d-inl1-avx2":{"avg":0.4593,"median":0.4593,"min":0.4593,"max":0.4593,"count":1},"ggtt-sa-cpp-f-inl0-avx2":{"avg":1.0353,"median":1.0353,"min":1.0353,"max":1.0353,"count":1},"ggtt-sa-cpp-f-inl1-avx2":{"avg":0.7014,"median":0.7014,"min":0.7014,"max":0.7014,"count":1},"ggtt-sa-cpp-d-inl0-512y":{"avg":0.6213,"median":0.6213,"min":0.6213,"max":0.6213,"count":1},"ggtt-sa-cpp-d-inl1-512y":{"avg":0.4756,"median":0.4756,"min":0.4756,"max":0.4756,"count":1},"ggtt-sa-cpp-f-inl0-512y":{"avg":1.1129,"median":1.1129,"min":1.1129,"max":1.1129,"count":1},"ggtt-sa-cpp-f-inl1-512y":{"avg":0.7099,"median":0.7099,"min":0.7099,"max":0.7099,"count":1},"ggtt-sa-cpp-d-inl0-512z":{"avg":0.3732,"median":0.3732,"min":0.3732,"max":0.3732,"count":1},"ggtt-sa-cpp-d-inl1-512z":{"avg":0.3438,"median":0.3438,"min":0.3438,"max":0.3438,"count":1},"ggtt-sa-cpp-f-inl0-512z":{"avg":0.7762,"median":0.7762,"min":0.7762,"max":0.7762,"count":1},"ggtt-sa-cpp-f-inl1-512z":{"avg":0.5638,"median":0.5638,"min":0.5638,"max":0.5638,"count":1},"ggttg-sa-cuda-d-inl0":{"avg":13.4296,"median":13.4296,"min":13.4296,"max":13.4296,"count":1},"ggttg-sa-cuda-d-inl1":{"avg":13.4207,"median":13.4207,"min":13.4207,"max":13.4207,"count":1},"ggttg-sa-cuda-f-inl0":{"avg":45.8793,"median":45.8793,"min":45.8793,"max":45.8793,"count":1},"ggttg-sa-cuda-f-inl1":{"avg":45.5322,"median":45.5322,"min":45.5322,"max":45.5322,"count":1},"ggttg-sa-cpp-d-inl0-best":{"avg":0.1,"median":0.1,"min":0.1,"max":0.1,"count":1},"ggttg-sa-cpp-d-inl0-none":{"avg":0.0238,"median":0.0238,"min":0.0238,"max":0.0238,"count":1},"ggttg-sa-cpp-d-inl1-best":{"avg":0.0889,"median":0.0889,"min":0.0889,"max":0.0889,"count":1},"ggttg-sa-cpp-d-inl1-none":{"avg":0.0063,"median":0.0063,"min":0.0063,"max":0.0063,"count":1},"ggttg-sa-cpp-f-inl0-best":{"avg":0.1974,"median":0.1974,"min":0.1974,"max":0.1974,"count":1},"ggttg-sa-cpp-f-inl0-none":{"avg":0.0244,"median":0.0244,"min":0.0244,"max":0.0244,"count":1},"ggttg-sa-cpp-f-inl1-best":{"avg":0.1555,"median":0.1555,"min":0.1555,"max":0.1555,"count":1},"ggttg-sa-cpp-f-inl1-none":{"avg":0.0102,"median":0.0102,"min":0.0102,"max":0.0102,"count":1},"ggttg-sa-cpp-d-inl0-sse4":{"avg":0.0448,"median":0.0448,"min":0.0448,"max":0.0448,"count":1},"ggttg-sa-cpp-d-inl1-sse4":{"avg":0.0417,"median":0.0417,"min":0.0417,"max":0.0417,"count":1},"ggttg-sa-cpp-f-inl0-sse4":{"avg":0.082,"median":0.082,"min":0.082,"max":0.082,"count":1},"ggttg-sa-cpp-f-inl1-sse4":{"avg":0.087,"median":0.087,"min":0.087,"max":0.087,"count":1},"ggttg-sa-cpp-d-inl0-avx2":{"avg":0.0873,"median":0.0873,"min":0.0873,"max":0.0873,"count":1},"ggttg-sa-cpp-d-inl1-avx2":{"avg":0.0806,"median":0.0806,"min":0.0806,"max":0.0806,"count":1},"ggttg-sa-cpp-f-inl0-avx2":{"avg":0.1742,"median":0.1742,"min":0.1742,"max":0.1742,"count":1},"ggttg-sa-cpp-f-inl1-avx2":{"avg":0.1402,"median":0.1402,"min":0.1402,"max":0.1402,"count":1},"ggttg-sa-cpp-d-inl0-512y":{"avg":0.1,"median":0.1,"min":0.1,"max":0.1,"count":1},"ggttg-sa-cpp-d-inl1-512y":{"avg":0.0889,"median":0.0889,"min":0.0889,"max":0.0889,"count":1},"ggttg-sa-cpp-f-inl0-512y":{"avg":0.1974,"median":0.1974,"min":0.1974,"max":0.1974,"count":1},"ggttg-sa-cpp-f-inl1-512y":{"avg":0.1555,"median":0.1555,"min":0.1555,"max":0.1555,"count":1},"ggttg-sa-cpp-d-inl0-512z":{"avg":0.0722,"median":0.0722,"min":0.0722,"max":0.0722,"count":1},"ggttg-sa-cpp-d-inl1-512z":{"avg":0.0648,"median":0.0648,"min":0.0648,"max":0.0648,"count":1},"ggttg-sa-cpp-f-inl0-512z":{"avg":0.1502,"median":0.1502,"min":0.1502,"max":0.1502,"count":1},"ggttg-sa-cpp-f-inl1-512z":{"avg":0.115,"median":0.115,"min":0.115,"max":0.115,"count":1},"ggttgg-sa-cuda-d-inl0":{"avg":0.4201,"median":0.4201,"min":0.4201,"max":0.4201,"count":1},"ggttgg-sa-cuda-d-inl1":{"avg":0.3868,"median":0.3868,"min":0.3868,"max":0.3868,"count":1},"ggttgg-sa-cuda-f-inl0":{"avg":0.8683,"median":0.8683,"min":0.8683,"max":0.8683,"count":1},"ggttgg-sa-cuda-f-inl1":{"avg":0.7768,"median":0.7768,"min":0.7768,"max":0.7768,"count":1},"ggttgg-sa-cpp-d-inl0-best":{"avg":0.0075,"median":0.0075,"min":0.0075,"max":0.0075,"count":1},"ggttgg-sa-cpp-d-inl0-none":{"avg":0.0017,"median":0.0017,"min":0.0017,"max":0.0017,"count":1},"ggttgg-sa-cpp-d-inl1-best":{"avg":0.0069,"median":0.0069,"min":0.0069,"max":0.0069,"count":1},"ggttgg-sa-cpp-d-inl1-none":{"avg":0.0004,"median":0.0004,"min":0.0004,"max":0.0004,"count":1},"ggttgg-sa-cpp-f-inl0-best":{"avg":0.0149,"median":0.0149,"min":0.0149,"max":0.0149,"count":1},"ggttgg-sa-cpp-f-inl0-none":{"avg":0.0018,"median":0.0018,"min":0.0018,"max":0.0018,"count":1},"ggttgg-sa-cpp-f-inl1-best":{"avg":0.0134,"median":0.0134,"min":0.0134,"max":0.0134,"count":1},"ggttgg-sa-cpp-f-inl1-none":{"avg":0.0005,"median":0.0005,"min":0.0005,"max":0.0005,"count":1},"ggttgg-sa-cpp-d-inl0-sse4":{"avg":0.0033,"median":0.0033,"min":0.0033,"max":0.0033,"count":1},"ggttgg-sa-cpp-d-inl1-sse4":{"avg":0.0028,"median":0.0028,"min":0.0028,"max":0.0028,"count":1},"ggttgg-sa-cpp-f-inl0-sse4":{"avg":0.0069,"median":0.0069,"min":0.0069,"max":0.0069,"count":1},"ggttgg-sa-cpp-f-inl1-sse4":{"avg":0.0061,"median":0.0061,"min":0.0061,"max":0.0061,"count":1},"ggttgg-sa-cpp-d-inl0-avx2":{"avg":0.0067,"median":0.0067,"min":0.0067,"max":0.0067,"count":1},"ggttgg-sa-cpp-d-inl1-avx2":{"avg":0.0054,"median":0.0054,"min":0.0054,"max":0.0054,"count":1},"ggttgg-sa-cpp-f-inl0-avx2":{"avg":0.0134,"median":0.0134,"min":0.0134,"max":0.0134,"count":1},"ggttgg-sa-cpp-f-inl1-avx2":{"avg":0.0106,"median":0.0106,"min":0.0106,"max":0.0106,"count":1},"ggttgg-sa-cpp-d-inl0-512y":{"avg":0.0075,"median":0.0075,"min":0.0075,"max":0.0075,"count":1},"ggttgg-sa-cpp-d-inl1-512y":{"avg":0.0069,"median":0.0069,"min":0.0069,"max":0.0069,"count":1},"ggttgg-sa-cpp-f-inl0-512y":{"avg":0.0149,"median":0.0149,"min":0.0149,"max":0.0149,"count":1},"ggttgg-sa-cpp-f-inl1-512y":{"avg":0.0134,"median":0.0134,"min":0.0134,"max":0.0134,"count":1},"ggttgg-sa-cpp-d-inl0-512z":{"avg":0.0065,"median":0.0065,"min":0.0065,"max":0.0065,"count":1},"ggttgg-sa-cpp-d-inl1-512z":{"avg":0.0065,"median":0.0065,"min":0.0065,"max":0.0065,"count":1},"ggttgg-sa-cpp-f-inl0-512z":{"avg":0.0131,"median":0.0131,"min":0.0131,"max":0.0131,"count":1},"ggttgg-sa-cpp-f-inl1-512z":{"avg":0.0126,"median":0.0126,"min":0.0126,"max":0.0126,"count":1}},"log":"ok"},"app":{"version":"ci-v0.6","description":"Madgraph5_aMCatNLO madgraph4gpu benchmark (2022)","cvmfs_checksum":"05f5179a44c0e2051bbb092a63cf0daf","bmkdata_checksum":"4eb8273563af22b829ddbf985ae0b0a9","bmk_checksum":"9b7bedb12e18a214106591542f8b3093","containment":"docker"}}
+{"run_info":{"copies":1,"threads_per_copy":1,"events_per_thread":2,"extra_arguments":"--both -eemumu -ggtt -ggttg -ggttgg -dbl -flt -inl0 -inl1"},"report":{"wl-scores":{"eemumu-sa-cuda-d-inl0":48.79672,"eemumu-sa-cuda-d-inl1":49.58971,"eemumu-sa-cuda-f-inl0":1485.295,"eemumu-sa-cuda-f-inl1":1420.555,"eemumu-sa-cpp-d-inl0-best":5.85542,"eemumu-sa-cpp-d-inl0-none":1.60346,"eemumu-sa-cpp-d-inl1-best":11.02532,"eemumu-sa-cpp-d-inl1-none":4.669919,"eemumu-sa-cpp-f-inl0-best":12.28219,"eemumu-sa-cpp-f-inl0-none":1.662875,"eemumu-sa-cpp-f-inl1-best":27.95492,"eemumu-sa-cpp-f-inl1-none":4.952863,"eemumu-sa-cpp-d-inl0-sse4":3.070359,"eemumu-sa-cpp-d-inl1-sse4":8.24349,"eemumu-sa-cpp-f-inl0-sse4":6.108306,"eemumu-sa-cpp-f-inl1-sse4":14.71368,"eemumu-sa-cpp-d-inl0-avx2":5.434791,"eemumu-sa-cpp-d-inl1-avx2":11.02532,"eemumu-sa-cpp-f-inl0-avx2":11.37094,"eemumu-sa-cpp-f-inl1-avx2":27.61771,"eemumu-sa-cpp-d-inl0-512y":5.85542,"eemumu-sa-cpp-d-inl1-512y":10.94437,"eemumu-sa-cpp-f-inl0-512y":12.28219,"eemumu-sa-cpp-f-inl1-512y":27.95492,"eemumu-sa-cpp-d-inl0-512z":4.919846,"eemumu-sa-cpp-d-inl1-512z":9.140349,"eemumu-sa-cpp-f-inl0-512z":10.05686,"eemumu-sa-cpp-f-inl1-512z":20.54445,"ggtt-sa-cuda-d-inl0":5.745921,"ggtt-sa-cuda-d-inl1":5.897079,"ggtt-sa-cuda-f-inl0":175.4402,"ggtt-sa-cuda-f-inl1":170.835,"ggtt-sa-cpp-d-inl0-best":0.625262,"ggtt-sa-cpp-d-inl0-none":0.191705,"ggtt-sa-cpp-d-inl1-best":0.481277,"ggtt-sa-cpp-d-inl1-none":0.233871,"ggtt-sa-cpp-f-inl0-best":1.115452,"ggtt-sa-cpp-f-inl0-none":0.200632,"ggtt-sa-cpp-f-inl1-best":0.717432,"ggtt-sa-cpp-f-inl1-none":0.243362,"ggtt-sa-cpp-d-inl0-sse4":0.322312,"ggtt-sa-cpp-d-inl1-sse4":0.278407,"ggtt-sa-cpp-f-inl0-sse4":0.478232,"ggtt-sa-cpp-f-inl1-sse4":0.562256,"ggtt-sa-cpp-d-inl0-avx2":0.559118,"ggtt-sa-cpp-d-inl1-avx2":0.461578,"ggtt-sa-cpp-f-inl0-avx2":1.038209,"ggtt-sa-cpp-f-inl1-avx2":0.717164,"ggtt-sa-cpp-d-inl0-512y":0.625262,"ggtt-sa-cpp-d-inl1-512y":0.481277,"ggtt-sa-cpp-f-inl0-512y":1.115452,"ggtt-sa-cpp-f-inl1-512y":0.717432,"ggtt-sa-cpp-d-inl0-512z":0.374524,"ggtt-sa-cpp-d-inl1-512z":0.347206,"ggtt-sa-cpp-f-inl0-512z":0.781307,"ggtt-sa-cpp-f-inl1-512z":0.564741,"ggttg-sa-cuda-d-inl0":0.818309,"ggttg-sa-cuda-d-inl1":0.818317,"ggttg-sa-cuda-f-inl0":18.42414,"ggttg-sa-cuda-f-inl1":18.37018,"ggttg-sa-cpp-d-inl0-best":0.100087,"ggttg-sa-cpp-d-inl0-none":0.023867,"ggttg-sa-cpp-d-inl1-best":0.089018,"ggttg-sa-cpp-d-inl1-none":0.006266,"ggttg-sa-cpp-f-inl0-best":0.197983,"ggttg-sa-cpp-f-inl0-none":0.024443,"ggttg-sa-cpp-f-inl1-best":0.155876,"ggttg-sa-cpp-f-inl1-none":0.010211,"ggttg-sa-cpp-d-inl0-sse4":0.044909,"ggttg-sa-cpp-d-inl1-sse4":0.041899,"ggttg-sa-cpp-f-inl0-sse4":0.082025,"ggttg-sa-cpp-f-inl1-sse4":0.087215,"ggttg-sa-cpp-d-inl0-avx2":0.087359,"ggttg-sa-cpp-d-inl1-avx2":0.08088,"ggttg-sa-cpp-f-inl0-avx2":0.174366,"ggttg-sa-cpp-f-inl1-avx2":0.140372,"ggttg-sa-cpp-d-inl0-512y":0.100087,"ggttg-sa-cpp-d-inl1-512y":0.089018,"ggttg-sa-cpp-f-inl0-512y":0.197983,"ggttg-sa-cpp-f-inl1-512y":0.155876,"ggttg-sa-cpp-d-inl0-512z":0.072352,"ggttg-sa-cpp-d-inl1-512z":0.064912,"ggttg-sa-cpp-f-inl0-512z":0.150358,"ggttg-sa-cpp-f-inl1-512z":0.115493,"ggttgg-sa-cuda-d-inl0":0.055489,"ggttgg-sa-cuda-d-inl1":0.062788,"ggttgg-sa-cuda-f-inl0":0.308794,"ggttgg-sa-cuda-f-inl1":0.263863,"ggttgg-sa-cpp-d-inl0-best":0.007537,"ggttgg-sa-cpp-d-inl0-none":0.001743,"ggttgg-sa-cpp-d-inl1-best":0.006903,"ggttgg-sa-cpp-d-inl1-none":0.000386,"ggttgg-sa-cpp-f-inl0-best":0.014863,"ggttgg-sa-cpp-f-inl0-none":0.001829,"ggttgg-sa-cpp-f-inl1-best":0.013425,"ggttgg-sa-cpp-f-inl1-none":0.000499,"ggttgg-sa-cpp-d-inl0-sse4":0.00335,"ggttgg-sa-cpp-d-inl1-sse4":0.002792,"ggttgg-sa-cpp-f-inl0-sse4":0.006907,"ggttgg-sa-cpp-f-inl1-sse4":0.006093,"ggttgg-sa-cpp-d-inl0-avx2":0.006673,"ggttgg-sa-cpp-d-inl1-avx2":0.00545,"ggttgg-sa-cpp-f-inl0-avx2":0.013348,"ggttgg-sa-cpp-f-inl1-avx2":0.010681,"ggttgg-sa-cpp-d-inl0-512y":0.007537,"ggttgg-sa-cpp-d-inl1-512y":0.006903,"ggttgg-sa-cpp-f-inl0-512y":0.014863,"ggttgg-sa-cpp-f-inl1-512y":0.013425,"ggttgg-sa-cpp-d-inl0-512z":0.006486,"ggttgg-sa-cpp-d-inl1-512z":0.006547,"ggttgg-sa-cpp-f-inl0-512z":0.013055,"ggttgg-sa-cpp-f-inl1-512z":0.012701},"wl-stats":{"eemumu-sa-cuda-d-inl0":{"avg":48.79672,"median":48.79672,"min":48.79672,"max":48.79672,"count":1},"eemumu-sa-cuda-d-inl1":{"avg":49.58971,"median":49.58971,"min":49.58971,"max":49.58971,"count":1},"eemumu-sa-cuda-f-inl0":{"avg":1485.295,"median":1485.295,"min":1485.295,"max":1485.295,"count":1},"eemumu-sa-cuda-f-inl1":{"avg":1420.555,"median":1420.555,"min":1420.555,"max":1420.555,"count":1},"eemumu-sa-cpp-d-inl0-best":{"avg":5.85542,"median":5.85542,"min":5.85542,"max":5.85542,"count":1},"eemumu-sa-cpp-d-inl0-none":{"avg":1.60346,"median":1.60346,"min":1.60346,"max":1.60346,"count":1},"eemumu-sa-cpp-d-inl1-best":{"avg":11.02532,"median":11.02532,"min":11.02532,"max":11.02532,"count":1},"eemumu-sa-cpp-d-inl1-none":{"avg":4.669919,"median":4.669919,"min":4.669919,"max":4.669919,"count":1},"eemumu-sa-cpp-f-inl0-best":{"avg":12.28219,"median":12.28219,"min":12.28219,"max":12.28219,"count":1},"eemumu-sa-cpp-f-inl0-none":{"avg":1.662875,"median":1.662875,"min":1.662875,"max":1.662875,"count":1},"eemumu-sa-cpp-f-inl1-best":{"avg":27.95492,"median":27.95492,"min":27.95492,"max":27.95492,"count":1},"eemumu-sa-cpp-f-inl1-none":{"avg":4.952863,"median":4.952863,"min":4.952863,"max":4.952863,"count":1},"eemumu-sa-cpp-d-inl0-sse4":{"avg":3.070359,"median":3.070359,"min":3.070359,"max":3.070359,"count":1},"eemumu-sa-cpp-d-inl1-sse4":{"avg":8.24349,"median":8.24349,"min":8.24349,"max":8.24349,"count":1},"eemumu-sa-cpp-f-inl0-sse4":{"avg":6.108306,"median":6.108306,"min":6.108306,"max":6.108306,"count":1},"eemumu-sa-cpp-f-inl1-sse4":{"avg":14.71368,"median":14.71368,"min":14.71368,"max":14.71368,"count":1},"eemumu-sa-cpp-d-inl0-avx2":{"avg":5.434791,"median":5.434791,"min":5.434791,"max":5.434791,"count":1},"eemumu-sa-cpp-d-inl1-avx2":{"avg":11.02532,"median":11.02532,"min":11.02532,"max":11.02532,"count":1},"eemumu-sa-cpp-f-inl0-avx2":{"avg":11.37094,"median":11.37094,"min":11.37094,"max":11.37094,"count":1},"eemumu-sa-cpp-f-inl1-avx2":{"avg":27.61771,"median":27.61771,"min":27.61771,"max":27.61771,"count":1},"eemumu-sa-cpp-d-inl0-512y":{"avg":5.85542,"median":5.85542,"min":5.85542,"max":5.85542,"count":1},"eemumu-sa-cpp-d-inl1-512y":{"avg":10.94437,"median":10.94437,"min":10.94437,"max":10.94437,"count":1},"eemumu-sa-cpp-f-inl0-512y":{"avg":12.28219,"median":12.28219,"min":12.28219,"max":12.28219,"count":1},"eemumu-sa-cpp-f-inl1-512y":{"avg":27.95492,"median":27.95492,"min":27.95492,"max":27.95492,"count":1},"eemumu-sa-cpp-d-inl0-512z":{"avg":4.919846,"median":4.919846,"min":4.919846,"max":4.919846,"count":1},"eemumu-sa-cpp-d-inl1-512z":{"avg":9.140349,"median":9.140349,"min":9.140349,"max":9.140349,"count":1},"eemumu-sa-cpp-f-inl0-512z":{"avg":10.05686,"median":10.05686,"min":10.05686,"max":10.05686,"count":1},"eemumu-sa-cpp-f-inl1-512z":{"avg":20.54445,"median":20.54445,"min":20.54445,"max":20.54445,"count":1},"ggtt-sa-cuda-d-inl0":{"avg":5.745921,"median":5.745921,"min":5.745921,"max":5.745921,"count":1},"ggtt-sa-cuda-d-inl1":{"avg":5.897079,"median":5.897079,"min":5.897079,"max":5.897079,"count":1},"ggtt-sa-cuda-f-inl0":{"avg":175.4402,"median":175.4402,"min":175.4402,"max":175.4402,"count":1},"ggtt-sa-cuda-f-inl1":{"avg":170.835,"median":170.835,"min":170.835,"max":170.835,"count":1},"ggtt-sa-cpp-d-inl0-best":{"avg":0.625262,"median":0.625262,"min":0.625262,"max":0.625262,"count":1},"ggtt-sa-cpp-d-inl0-none":{"avg":0.191705,"median":0.191705,"min":0.191705,"max":0.191705,"count":1},"ggtt-sa-cpp-d-inl1-best":{"avg":0.481277,"median":0.481277,"min":0.481277,"max":0.481277,"count":1},"ggtt-sa-cpp-d-inl1-none":{"avg":0.233871,"median":0.233871,"min":0.233871,"max":0.233871,"count":1},"ggtt-sa-cpp-f-inl0-best":{"avg":1.115452,"median":1.115452,"min":1.115452,"max":1.115452,"count":1},"ggtt-sa-cpp-f-inl0-none":{"avg":0.200632,"median":0.200632,"min":0.200632,"max":0.200632,"count":1},"ggtt-sa-cpp-f-inl1-best":{"avg":0.717432,"median":0.717432,"min":0.717432,"max":0.717432,"count":1},"ggtt-sa-cpp-f-inl1-none":{"avg":0.243362,"median":0.243362,"min":0.243362,"max":0.243362,"count":1},"ggtt-sa-cpp-d-inl0-sse4":{"avg":0.322312,"median":0.322312,"min":0.322312,"max":0.322312,"count":1},"ggtt-sa-cpp-d-inl1-sse4":{"avg":0.278407,"median":0.278407,"min":0.278407,"max":0.278407,"count":1},"ggtt-sa-cpp-f-inl0-sse4":{"avg":0.478232,"median":0.478232,"min":0.478232,"max":0.478232,"count":1},"ggtt-sa-cpp-f-inl1-sse4":{"avg":0.562256,"median":0.562256,"min":0.562256,"max":0.562256,"count":1},"ggtt-sa-cpp-d-inl0-avx2":{"avg":0.559118,"median":0.559118,"min":0.559118,"max":0.559118,"count":1},"ggtt-sa-cpp-d-inl1-avx2":{"avg":0.461578,"median":0.461578,"min":0.461578,"max":0.461578,"count":1},"ggtt-sa-cpp-f-inl0-avx2":{"avg":1.038209,"median":1.038209,"min":1.038209,"max":1.038209,"count":1},"ggtt-sa-cpp-f-inl1-avx2":{"avg":0.717164,"median":0.717164,"min":0.717164,"max":0.717164,"count":1},"ggtt-sa-cpp-d-inl0-512y":{"avg":0.625262,"median":0.625262,"min":0.625262,"max":0.625262,"count":1},"ggtt-sa-cpp-d-inl1-512y":{"avg":0.481277,"median":0.481277,"min":0.481277,"max":0.481277,"count":1},"ggtt-sa-cpp-f-inl0-512y":{"avg":1.115452,"median":1.115452,"min":1.115452,"max":1.115452,"count":1},"ggtt-sa-cpp-f-inl1-512y":{"avg":0.717432,"median":0.717432,"min":0.717432,"max":0.717432,"count":1},"ggtt-sa-cpp-d-inl0-512z":{"avg":0.374524,"median":0.374524,"min":0.374524,"max":0.374524,"count":1},"ggtt-sa-cpp-d-inl1-512z":{"avg":0.347206,"median":0.347206,"min":0.347206,"max":0.347206,"count":1},"ggtt-sa-cpp-f-inl0-512z":{"avg":0.781307,"median":0.781307,"min":0.781307,"max":0.781307,"count":1},"ggtt-sa-cpp-f-inl1-512z":{"avg":0.564741,"median":0.564741,"min":0.564741,"max":0.564741,"count":1},"ggttg-sa-cuda-d-inl0":{"avg":0.818309,"median":0.818309,"min":0.818309,"max":0.818309,"count":1},"ggttg-sa-cuda-d-inl1":{"avg":0.818317,"median":0.818317,"min":0.818317,"max":0.818317,"count":1},"ggttg-sa-cuda-f-inl0":{"avg":18.42414,"median":18.42414,"min":18.42414,"max":18.42414,"count":1},"ggttg-sa-cuda-f-inl1":{"avg":18.37018,"median":18.37018,"min":18.37018,"max":18.37018,"count":1},"ggttg-sa-cpp-d-inl0-best":{"avg":0.100087,"median":0.100087,"min":0.100087,"max":0.100087,"count":1},"ggttg-sa-cpp-d-inl0-none":{"avg":0.023867,"median":0.023867,"min":0.023867,"max":0.023867,"count":1},"ggttg-sa-cpp-d-inl1-best":{"avg":0.089018,"median":0.089018,"min":0.089018,"max":0.089018,"count":1},"ggttg-sa-cpp-d-inl1-none":{"avg":0.006266,"median":0.006266,"min":0.006266,"max":0.006266,"count":1},"ggttg-sa-cpp-f-inl0-best":{"avg":0.197983,"median":0.197983,"min":0.197983,"max":0.197983,"count":1},"ggttg-sa-cpp-f-inl0-none":{"avg":0.024443,"median":0.024443,"min":0.024443,"max":0.024443,"count":1},"ggttg-sa-cpp-f-inl1-best":{"avg":0.155876,"median":0.155876,"min":0.155876,"max":0.155876,"count":1},"ggttg-sa-cpp-f-inl1-none":{"avg":0.010211,"median":0.010211,"min":0.010211,"max":0.010211,"count":1},"ggttg-sa-cpp-d-inl0-sse4":{"avg":0.044909,"median":0.044909,"min":0.044909,"max":0.044909,"count":1},"ggttg-sa-cpp-d-inl1-sse4":{"avg":0.041899,"median":0.041899,"min":0.041899,"max":0.041899,"count":1},"ggttg-sa-cpp-f-inl0-sse4":{"avg":0.082025,"median":0.082025,"min":0.082025,"max":0.082025,"count":1},"ggttg-sa-cpp-f-inl1-sse4":{"avg":0.087215,"median":0.087215,"min":0.087215,"max":0.087215,"count":1},"ggttg-sa-cpp-d-inl0-avx2":{"avg":0.087359,"median":0.087359,"min":0.087359,"max":0.087359,"count":1},"ggttg-sa-cpp-d-inl1-avx2":{"avg":0.08088,"median":0.08088,"min":0.08088,"max":0.08088,"count":1},"ggttg-sa-cpp-f-inl0-avx2":{"avg":0.174366,"median":0.174366,"min":0.174366,"max":0.174366,"count":1},"ggttg-sa-cpp-f-inl1-avx2":{"avg":0.140372,"median":0.140372,"min":0.140372,"max":0.140372,"count":1},"ggttg-sa-cpp-d-inl0-512y":{"avg":0.100087,"median":0.100087,"min":0.100087,"max":0.100087,"count":1},"ggttg-sa-cpp-d-inl1-512y":{"avg":0.089018,"median":0.089018,"min":0.089018,"max":0.089018,"count":1},"ggttg-sa-cpp-f-inl0-512y":{"avg":0.197983,"median":0.197983,"min":0.197983,"max":0.197983,"count":1},"ggttg-sa-cpp-f-inl1-512y":{"avg":0.155876,"median":0.155876,"min":0.155876,"max":0.155876,"count":1},"ggttg-sa-cpp-d-inl0-512z":{"avg":0.072352,"median":0.072352,"min":0.072352,"max":0.072352,"count":1},"ggttg-sa-cpp-d-inl1-512z":{"avg":0.064912,"median":0.064912,"min":0.064912,"max":0.064912,"count":1},"ggttg-sa-cpp-f-inl0-512z":{"avg":0.150358,"median":0.150358,"min":0.150358,"max":0.150358,"count":1},"ggttg-sa-cpp-f-inl1-512z":{"avg":0.115493,"median":0.115493,"min":0.115493,"max":0.115493,"count":1},"ggttgg-sa-cuda-d-inl0":{"avg":0.055489,"median":0.055489,"min":0.055489,"max":0.055489,"count":1},"ggttgg-sa-cuda-d-inl1":{"avg":0.062788,"median":0.062788,"min":0.062788,"max":0.062788,"count":1},"ggttgg-sa-cuda-f-inl0":{"avg":0.308794,"median":0.308794,"min":0.308794,"max":0.308794,"count":1},"ggttgg-sa-cuda-f-inl1":{"avg":0.263863,"median":0.263863,"min":0.263863,"max":0.263863,"count":1},"ggttgg-sa-cpp-d-inl0-best":{"avg":0.007537,"median":0.007537,"min":0.007537,"max":0.007537,"count":1},"ggttgg-sa-cpp-d-inl0-none":{"avg":0.001743,"median":0.001743,"min":0.001743,"max":0.001743,"count":1},"ggttgg-sa-cpp-d-inl1-best":{"avg":0.006903,"median":0.006903,"min":0.006903,"max":0.006903,"count":1},"ggttgg-sa-cpp-d-inl1-none":{"avg":0.000386,"median":0.000386,"min":0.000386,"max":0.000386,"count":1},"ggttgg-sa-cpp-f-inl0-best":{"avg":0.014863,"median":0.014863,"min":0.014863,"max":0.014863,"count":1},"ggttgg-sa-cpp-f-inl0-none":{"avg":0.001829,"median":0.001829,"min":0.001829,"max":0.001829,"count":1},"ggttgg-sa-cpp-f-inl1-best":{"avg":0.013425,"median":0.013425,"min":0.013425,"max":0.013425,"count":1},"ggttgg-sa-cpp-f-inl1-none":{"avg":0.000499,"median":0.000499,"min":0.000499,"max":0.000499,"count":1},"ggttgg-sa-cpp-d-inl0-sse4":{"avg":0.00335,"median":0.00335,"min":0.00335,"max":0.00335,"count":1},"ggttgg-sa-cpp-d-inl1-sse4":{"avg":0.002792,"median":0.002792,"min":0.002792,"max":0.002792,"count":1},"ggttgg-sa-cpp-f-inl0-sse4":{"avg":0.006907,"median":0.006907,"min":0.006907,"max":0.006907,"count":1},"ggttgg-sa-cpp-f-inl1-sse4":{"avg":0.006093,"median":0.006093,"min":0.006093,"max":0.006093,"count":1},"ggttgg-sa-cpp-d-inl0-avx2":{"avg":0.006673,"median":0.006673,"min":0.006673,"max":0.006673,"count":1},"ggttgg-sa-cpp-d-inl1-avx2":{"avg":0.00545,"median":0.00545,"min":0.00545,"max":0.00545,"count":1},"ggttgg-sa-cpp-f-inl0-avx2":{"avg":0.013348,"median":0.013348,"min":0.013348,"max":0.013348,"count":1},"ggttgg-sa-cpp-f-inl1-avx2":{"avg":0.010681,"median":0.010681,"min":0.010681,"max":0.010681,"count":1},"ggttgg-sa-cpp-d-inl0-512y":{"avg":0.007537,"median":0.007537,"min":0.007537,"max":0.007537,"count":1},"ggttgg-sa-cpp-d-inl1-512y":{"avg":0.006903,"median":0.006903,"min":0.006903,"max":0.006903,"count":1},"ggttgg-sa-cpp-f-inl0-512y":{"avg":0.014863,"median":0.014863,"min":0.014863,"max":0.014863,"count":1},"ggttgg-sa-cpp-f-inl1-512y":{"avg":0.013425,"median":0.013425,"min":0.013425,"max":0.013425,"count":1},"ggttgg-sa-cpp-d-inl0-512z":{"avg":0.006486,"median":0.006486,"min":0.006486,"max":0.006486,"count":1},"ggttgg-sa-cpp-d-inl1-512z":{"avg":0.006547,"median":0.006547,"min":0.006547,"max":0.006547,"count":1},"ggttgg-sa-cpp-f-inl0-512z":{"avg":0.013055,"median":0.013055,"min":0.013055,"max":0.013055,"count":1},"ggttgg-sa-cpp-f-inl1-512z":{"avg":0.012701,"median":0.012701,"min":0.012701,"max":0.012701,"count":1}},"log":"ok"},"app":{"version":"ci-v0.7","description":"Madgraph5_aMCatNLO madgraph4gpu benchmark (2022)","cvmfs_checksum":"34ff738c57b9b7a8a398e4769cba101d","bmkdata_checksum":"d4c9152ed732e012ca54b6518bf3de93","bmk_checksum":"3c9f62f161ec52296be50b21648606b0","containment":"docker"}}
+{"run_info":{"copies":1,"threads_per_copy":1,"events_per_thread":2,"extra_arguments":"--both -eemumu -ggtt -ggttg -ggttgg -dbl -flt -inl0 -inl1"},"report":{"wl-scores":{"eemumu-sa-cuda-d-inl0":48.79672,"eemumu-sa-cuda-d-inl1":49.58971,"eemumu-sa-cuda-f-inl0":1485.295,"eemumu-sa-cuda-f-inl1":1420.555,"eemumu-sa-cpp-d-inl0-best":5.85542,"eemumu-sa-cpp-d-inl0-none":1.60346,"eemumu-sa-cpp-d-inl1-best":11.02532,"eemumu-sa-cpp-d-inl1-none":4.669919,"eemumu-sa-cpp-f-inl0-best":12.28219,"eemumu-sa-cpp-f-inl0-none":1.662875,"eemumu-sa-cpp-f-inl1-best":27.95492,"eemumu-sa-cpp-f-inl1-none":4.952863,"eemumu-sa-cpp-d-inl0-sse4":3.070359,"eemumu-sa-cpp-d-inl1-sse4":8.24349,"eemumu-sa-cpp-f-inl0-sse4":6.108306,"eemumu-sa-cpp-f-inl1-sse4":14.71368,"eemumu-sa-cpp-d-inl0-avx2":5.434791,"eemumu-sa-cpp-d-inl1-avx2":11.02532,"eemumu-sa-cpp-f-inl0-avx2":11.37094,"eemumu-sa-cpp-f-inl1-avx2":27.61771,"eemumu-sa-cpp-d-inl0-512y":5.85542,"eemumu-sa-cpp-d-inl1-512y":10.94437,"eemumu-sa-cpp-f-inl0-512y":12.28219,"eemumu-sa-cpp-f-inl1-512y":27.95492,"eemumu-sa-cpp-d-inl0-512z":4.919846,"eemumu-sa-cpp-d-inl1-512z":9.140349,"eemumu-sa-cpp-f-inl0-512z":10.05686,"eemumu-sa-cpp-f-inl1-512z":20.54445,"ggtt-sa-cuda-d-inl0":5.745921,"ggtt-sa-cuda-d-inl1":5.897079,"ggtt-sa-cuda-f-inl0":175.4402,"ggtt-sa-cuda-f-inl1":170.835,"ggtt-sa-cpp-d-inl0-best":0.625262,"ggtt-sa-cpp-d-inl0-none":0.191705,"ggtt-sa-cpp-d-inl1-best":0.481277,"ggtt-sa-cpp-d-inl1-none":0.233871,"ggtt-sa-cpp-f-inl0-best":1.115452,"ggtt-sa-cpp-f-inl0-none":0.200632,"ggtt-sa-cpp-f-inl1-best":0.717432,"ggtt-sa-cpp-f-inl1-none":0.243362,"ggtt-sa-cpp-d-inl0-sse4":0.322312,"ggtt-sa-cpp-d-inl1-sse4":0.278407,"ggtt-sa-cpp-f-inl0-sse4":0.478232,"ggtt-sa-cpp-f-inl1-sse4":0.562256,"ggtt-sa-cpp-d-inl0-avx2":0.559118,"ggtt-sa-cpp-d-inl1-avx2":0.461578,"ggtt-sa-cpp-f-inl0-avx2":1.038209,"ggtt-sa-cpp-f-inl1-avx2":0.717164,"ggtt-sa-cpp-d-inl0-512y":0.625262,"ggtt-sa-cpp-d-inl1-512y":0.481277,"ggtt-sa-cpp-f-inl0-512y":1.115452,"ggtt-sa-cpp-f-inl1-512y":0.717432,"ggtt-sa-cpp-d-inl0-512z":0.374524,"ggtt-sa-cpp-d-inl1-512z":0.347206,"ggtt-sa-cpp-f-inl0-512z":0.781307,"ggtt-sa-cpp-f-inl1-512z":0.564741,"ggttg-sa-cuda-d-inl0":0.818309,"ggttg-sa-cuda-d-inl1":0.818317,"ggttg-sa-cuda-f-inl0":18.42414,"ggttg-sa-cuda-f-inl1":18.37018,"ggttg-sa-cpp-d-inl0-best":0.100087,"ggttg-sa-cpp-d-inl0-none":0.023867,"ggttg-sa-cpp-d-inl1-best":0.089018,"ggttg-sa-cpp-d-inl1-none":0.006266,"ggttg-sa-cpp-f-inl0-best":0.197983,"ggttg-sa-cpp-f-inl0-none":0.024443,"ggttg-sa-cpp-f-inl1-best":0.155876,"ggttg-sa-cpp-f-inl1-none":0.010211,"ggttg-sa-cpp-d-inl0-sse4":0.044909,"ggttg-sa-cpp-d-inl1-sse4":0.041899,"ggttg-sa-cpp-f-inl0-sse4":0.082025,"ggttg-sa-cpp-f-inl1-sse4":0.087215,"ggttg-sa-cpp-d-inl0-avx2":0.087359,"ggttg-sa-cpp-d-inl1-avx2":0.08088,"ggttg-sa-cpp-f-inl0-avx2":0.174366,"ggttg-sa-cpp-f-inl1-avx2":0.140372,"ggttg-sa-cpp-d-inl0-512y":0.100087,"ggttg-sa-cpp-d-inl1-512y":0.089018,"ggttg-sa-cpp-f-inl0-512y":0.197983,"ggttg-sa-cpp-f-inl1-512y":0.155876,"ggttg-sa-cpp-d-inl0-512z":0.072352,"ggttg-sa-cpp-d-inl1-512z":0.064912,"ggttg-sa-cpp-f-inl0-512z":0.150358,"ggttg-sa-cpp-f-inl1-512z":0.115493,"ggttgg-sa-cuda-d-inl0":0.055489,"ggttgg-sa-cuda-d-inl1":0.062788,"ggttgg-sa-cuda-f-inl0":0.308794,"ggttgg-sa-cuda-f-inl1":0.263863,"ggttgg-sa-cpp-d-inl0-best":0.007537,"ggttgg-sa-cpp-d-inl0-none":0.001743,"ggttgg-sa-cpp-d-inl1-best":0.006903,"ggttgg-sa-cpp-d-inl1-none":0.000386,"ggttgg-sa-cpp-f-inl0-best":0.014863,"ggttgg-sa-cpp-f-inl0-none":0.001829,"ggttgg-sa-cpp-f-inl1-best":0.013425,"ggttgg-sa-cpp-f-inl1-none":0.000499,"ggttgg-sa-cpp-d-inl0-sse4":0.00335,"ggttgg-sa-cpp-d-inl1-sse4":0.002792,"ggttgg-sa-cpp-f-inl0-sse4":0.006907,"ggttgg-sa-cpp-f-inl1-sse4":0.006093,"ggttgg-sa-cpp-d-inl0-avx2":0.006673,"ggttgg-sa-cpp-d-inl1-avx2":0.00545,"ggttgg-sa-cpp-f-inl0-avx2":0.013348,"ggttgg-sa-cpp-f-inl1-avx2":0.010681,"ggttgg-sa-cpp-d-inl0-512y":0.007537,"ggttgg-sa-cpp-d-inl1-512y":0.006903,"ggttgg-sa-cpp-f-inl0-512y":0.014863,"ggttgg-sa-cpp-f-inl1-512y":0.013425,"ggttgg-sa-cpp-d-inl0-512z":0.006486,"ggttgg-sa-cpp-d-inl1-512z":0.006547,"ggttgg-sa-cpp-f-inl0-512z":0.013055,"ggttgg-sa-cpp-f-inl1-512z":0.012701},"wl-stats":{"eemumu-sa-cuda-d-inl0":{"avg":48.79672,"median":48.79672,"min":48.79672,"max":48.79672,"count":1},"eemumu-sa-cuda-d-inl1":{"avg":49.58971,"median":49.58971,"min":49.58971,"max":49.58971,"count":1},"eemumu-sa-cuda-f-inl0":{"avg":1485.295,"median":1485.295,"min":1485.295,"max":1485.295,"count":1},"eemumu-sa-cuda-f-inl1":{"avg":1420.555,"median":1420.555,"min":1420.555,"max":1420.555,"count":1},"eemumu-sa-cpp-d-inl0-best":{"avg":5.85542,"median":5.85542,"min":5.85542,"max":5.85542,"count":1},"eemumu-sa-cpp-d-inl0-none":{"avg":1.60346,"median":1.60346,"min":1.60346,"max":1.60346,"count":1},"eemumu-sa-cpp-d-inl1-best":{"avg":11.02532,"median":11.02532,"min":11.02532,"max":11.02532,"count":1},"eemumu-sa-cpp-d-inl1-none":{"avg":4.669919,"median":4.669919,"min":4.669919,"max":4.669919,"count":1},"eemumu-sa-cpp-f-inl0-best":{"avg":12.28219,"median":12.28219,"min":12.28219,"max":12.28219,"count":1},"eemumu-sa-cpp-f-inl0-none":{"avg":1.662875,"median":1.662875,"min":1.662875,"max":1.662875,"count":1},"eemumu-sa-cpp-f-inl1-best":{"avg":27.95492,"median":27.95492,"min":27.95492,"max":27.95492,"count":1},"eemumu-sa-cpp-f-inl1-none":{"avg":4.952863,"median":4.952863,"min":4.952863,"max":4.952863,"count":1},"eemumu-sa-cpp-d-inl0-sse4":{"avg":3.070359,"median":3.070359,"min":3.070359,"max":3.070359,"count":1},"eemumu-sa-cpp-d-inl1-sse4":{"avg":8.24349,"median":8.24349,"min":8.24349,"max":8.24349,"count":1},"eemumu-sa-cpp-f-inl0-sse4":{"avg":6.108306,"median":6.108306,"min":6.108306,"max":6.108306,"count":1},"eemumu-sa-cpp-f-inl1-sse4":{"avg":14.71368,"median":14.71368,"min":14.71368,"max":14.71368,"count":1},"eemumu-sa-cpp-d-inl0-avx2":{"avg":5.434791,"median":5.434791,"min":5.434791,"max":5.434791,"count":1},"eemumu-sa-cpp-d-inl1-avx2":{"avg":11.02532,"median":11.02532,"min":11.02532,"max":11.02532,"count":1},"eemumu-sa-cpp-f-inl0-avx2":{"avg":11.37094,"median":11.37094,"min":11.37094,"max":11.37094,"count":1},"eemumu-sa-cpp-f-inl1-avx2":{"avg":27.61771,"median":27.61771,"min":27.61771,"max":27.61771,"count":1},"eemumu-sa-cpp-d-inl0-512y":{"avg":5.85542,"median":5.85542,"min":5.85542,"max":5.85542,"count":1},"eemumu-sa-cpp-d-inl1-512y":{"avg":10.94437,"median":10.94437,"min":10.94437,"max":10.94437,"count":1},"eemumu-sa-cpp-f-inl0-512y":{"avg":12.28219,"median":12.28219,"min":12.28219,"max":12.28219,"count":1},"eemumu-sa-cpp-f-inl1-512y":{"avg":27.95492,"median":27.95492,"min":27.95492,"max":27.95492,"count":1},"eemumu-sa-cpp-d-inl0-512z":{"avg":4.919846,"median":4.919846,"min":4.919846,"max":4.919846,"count":1},"eemumu-sa-cpp-d-inl1-512z":{"avg":9.140349,"median":9.140349,"min":9.140349,"max":9.140349,"count":1},"eemumu-sa-cpp-f-inl0-512z":{"avg":10.05686,"median":10.05686,"min":10.05686,"max":10.05686,"count":1},"eemumu-sa-cpp-f-inl1-512z":{"avg":20.54445,"median":20.54445,"min":20.54445,"max":20.54445,"count":1},"ggtt-sa-cuda-d-inl0":{"avg":5.745921,"median":5.745921,"min":5.745921,"max":5.745921,"count":1},"ggtt-sa-cuda-d-inl1":{"avg":5.897079,"median":5.897079,"min":5.897079,"max":5.897079,"count":1},"ggtt-sa-cuda-f-inl0":{"avg":175.4402,"median":175.4402,"min":175.4402,"max":175.4402,"count":1},"ggtt-sa-cuda-f-inl1":{"avg":170.835,"median":170.835,"min":170.835,"max":170.835,"count":1},"ggtt-sa-cpp-d-inl0-best":{"avg":0.625262,"median":0.625262,"min":0.625262,"max":0.625262,"count":1},"ggtt-sa-cpp-d-inl0-none":{"avg":0.191705,"median":0.191705,"min":0.191705,"max":0.191705,"count":1},"ggtt-sa-cpp-d-inl1-best":{"avg":0.481277,"median":0.481277,"min":0.481277,"max":0.481277,"count":1},"ggtt-sa-cpp-d-inl1-none":{"avg":0.233871,"median":0.233871,"min":0.233871,"max":0.233871,"count":1},"ggtt-sa-cpp-f-inl0-best":{"avg":1.115452,"median":1.115452,"min":1.115452,"max":1.115452,"count":1},"ggtt-sa-cpp-f-inl0-none":{"avg":0.200632,"median":0.200632,"min":0.200632,"max":0.200632,"count":1},"ggtt-sa-cpp-f-inl1-best":{"avg":0.717432,"median":0.717432,"min":0.717432,"max":0.717432,"count":1},"ggtt-sa-cpp-f-inl1-none":{"avg":0.243362,"median":0.243362,"min":0.243362,"max":0.243362,"count":1},"ggtt-sa-cpp-d-inl0-sse4":{"avg":0.322312,"median":0.322312,"min":0.322312,"max":0.322312,"count":1},"ggtt-sa-cpp-d-inl1-sse4":{"avg":0.278407,"median":0.278407,"min":0.278407,"max":0.278407,"count":1},"ggtt-sa-cpp-f-inl0-sse4":{"avg":0.478232,"median":0.478232,"min":0.478232,"max":0.478232,"count":1},"ggtt-sa-cpp-f-inl1-sse4":{"avg":0.562256,"median":0.562256,"min":0.562256,"max":0.562256,"count":1},"ggtt-sa-cpp-d-inl0-avx2":{"avg":0.559118,"median":0.559118,"min":0.559118,"max":0.559118,"count":1},"ggtt-sa-cpp-d-inl1-avx2":{"avg":0.461578,"median":0.461578,"min":0.461578,"max":0.461578,"count":1},"ggtt-sa-cpp-f-inl0-avx2":{"avg":1.038209,"median":1.038209,"min":1.038209,"max":1.038209,"count":1},"ggtt-sa-cpp-f-inl1-avx2":{"avg":0.717164,"median":0.717164,"min":0.717164,"max":0.717164,"count":1},"ggtt-sa-cpp-d-inl0-512y":{"avg":0.625262,"median":0.625262,"min":0.625262,"max":0.625262,"count":1},"ggtt-sa-cpp-d-inl1-512y":{"avg":0.481277,"median":0.481277,"min":0.481277,"max":0.481277,"count":1},"ggtt-sa-cpp-f-inl0-512y":{"avg":1.115452,"median":1.115452,"min":1.115452,"max":1.115452,"count":1},"ggtt-sa-cpp-f-inl1-512y":{"avg":0.717432,"median":0.717432,"min":0.717432,"max":0.717432,"count":1},"ggtt-sa-cpp-d-inl0-512z":{"avg":0.374524,"median":0.374524,"min":0.374524,"max":0.374524,"count":1},"ggtt-sa-cpp-d-inl1-512z":{"avg":0.347206,"median":0.347206,"min":0.347206,"max":0.347206,"count":1},"ggtt-sa-cpp-f-inl0-512z":{"avg":0.781307,"median":0.781307,"min":0.781307,"max":0.781307,"count":1},"ggtt-sa-cpp-f-inl1-512z":{"avg":0.564741,"median":0.564741,"min":0.564741,"max":0.564741,"count":1},"ggttg-sa-cuda-d-inl0":{"avg":0.818309,"median":0.818309,"min":0.818309,"max":0.818309,"count":1},"ggttg-sa-cuda-d-inl1":{"avg":0.818317,"median":0.818317,"min":0.818317,"max":0.818317,"count":1},"ggttg-sa-cuda-f-inl0":{"avg":18.42414,"median":18.42414,"min":18.42414,"max":18.42414,"count":1},"ggttg-sa-cuda-f-inl1":{"avg":18.37018,"median":18.37018,"min":18.37018,"max":18.37018,"count":1},"ggttg-sa-cpp-d-inl0-best":{"avg":0.100087,"median":0.100087,"min":0.100087,"max":0.100087,"count":1},"ggttg-sa-cpp-d-inl0-none":{"avg":0.023867,"median":0.023867,"min":0.023867,"max":0.023867,"count":1},"ggttg-sa-cpp-d-inl1-best":{"avg":0.089018,"median":0.089018,"min":0.089018,"max":0.089018,"count":1},"ggttg-sa-cpp-d-inl1-none":{"avg":0.006266,"median":0.006266,"min":0.006266,"max":0.006266,"count":1},"ggttg-sa-cpp-f-inl0-best":{"avg":0.197983,"median":0.197983,"min":0.197983,"max":0.197983,"count":1},"ggttg-sa-cpp-f-inl0-none":{"avg":0.024443,"median":0.024443,"min":0.024443,"max":0.024443,"count":1},"ggttg-sa-cpp-f-inl1-best":{"avg":0.155876,"median":0.155876,"min":0.155876,"max":0.155876,"count":1},"ggttg-sa-cpp-f-inl1-none":{"avg":0.010211,"median":0.010211,"min":0.010211,"max":0.010211,"count":1},"ggttg-sa-cpp-d-inl0-sse4":{"avg":0.044909,"median":0.044909,"min":0.044909,"max":0.044909,"count":1},"ggttg-sa-cpp-d-inl1-sse4":{"avg":0.041899,"median":0.041899,"min":0.041899,"max":0.041899,"count":1},"ggttg-sa-cpp-f-inl0-sse4":{"avg":0.082025,"median":0.082025,"min":0.082025,"max":0.082025,"count":1},"ggttg-sa-cpp-f-inl1-sse4":{"avg":0.087215,"median":0.087215,"min":0.087215,"max":0.087215,"count":1},"ggttg-sa-cpp-d-inl0-avx2":{"avg":0.087359,"median":0.087359,"min":0.087359,"max":0.087359,"count":1},"ggttg-sa-cpp-d-inl1-avx2":{"avg":0.08088,"median":0.08088,"min":0.08088,"max":0.08088,"count":1},"ggttg-sa-cpp-f-inl0-avx2":{"avg":0.174366,"median":0.174366,"min":0.174366,"max":0.174366,"count":1},"ggttg-sa-cpp-f-inl1-avx2":{"avg":0.140372,"median":0.140372,"min":0.140372,"max":0.140372,"count":1},"ggttg-sa-cpp-d-inl0-512y":{"avg":0.100087,"median":0.100087,"min":0.100087,"max":0.100087,"count":1},"ggttg-sa-cpp-d-inl1-512y":{"avg":0.089018,"median":0.089018,"min":0.089018,"max":0.089018,"count":1},"ggttg-sa-cpp-f-inl0-512y":{"avg":0.197983,"median":0.197983,"min":0.197983,"max":0.197983,"count":1},"ggttg-sa-cpp-f-inl1-512y":{"avg":0.155876,"median":0.155876,"min":0.155876,"max":0.155876,"count":1},"ggttg-sa-cpp-d-inl0-512z":{"avg":0.072352,"median":0.072352,"min":0.072352,"max":0.072352,"count":1},"ggttg-sa-cpp-d-inl1-512z":{"avg":0.064912,"median":0.064912,"min":0.064912,"max":0.064912,"count":1},"ggttg-sa-cpp-f-inl0-512z":{"avg":0.150358,"median":0.150358,"min":0.150358,"max":0.150358,"count":1},"ggttg-sa-cpp-f-inl1-512z":{"avg":0.115493,"median":0.115493,"min":0.115493,"max":0.115493,"count":1},"ggttgg-sa-cuda-d-inl0":{"avg":0.055489,"median":0.055489,"min":0.055489,"max":0.055489,"count":1},"ggttgg-sa-cuda-d-inl1":{"avg":0.062788,"median":0.062788,"min":0.062788,"max":0.062788,"count":1},"ggttgg-sa-cuda-f-inl0":{"avg":0.308794,"median":0.308794,"min":0.308794,"max":0.308794,"count":1},"ggttgg-sa-cuda-f-inl1":{"avg":0.263863,"median":0.263863,"min":0.263863,"max":0.263863,"count":1},"ggttgg-sa-cpp-d-inl0-best":{"avg":0.007537,"median":0.007537,"min":0.007537,"max":0.007537,"count":1},"ggttgg-sa-cpp-d-inl0-none":{"avg":0.001743,"median":0.001743,"min":0.001743,"max":0.001743,"count":1},"ggttgg-sa-cpp-d-inl1-best":{"avg":0.006903,"median":0.006903,"min":0.006903,"max":0.006903,"count":1},"ggttgg-sa-cpp-d-inl1-none":{"avg":0.000386,"median":0.000386,"min":0.000386,"max":0.000386,"count":1},"ggttgg-sa-cpp-f-inl0-best":{"avg":0.014863,"median":0.014863,"min":0.014863,"max":0.014863,"count":1},"ggttgg-sa-cpp-f-inl0-none":{"avg":0.001829,"median":0.001829,"min":0.001829,"max":0.001829,"count":1},"ggttgg-sa-cpp-f-inl1-best":{"avg":0.013425,"median":0.013425,"min":0.013425,"max":0.013425,"count":1},"ggttgg-sa-cpp-f-inl1-none":{"avg":0.000499,"median":0.000499,"min":0.000499,"max":0.000499,"count":1},"ggttgg-sa-cpp-d-inl0-sse4":{"avg":0.00335,"median":0.00335,"min":0.00335,"max":0.00335,"count":1},"ggttgg-sa-cpp-d-inl1-sse4":{"avg":0.002792,"median":0.002792,"min":0.002792,"max":0.002792,"count":1},"ggttgg-sa-cpp-f-inl0-sse4":{"avg":0.006907,"median":0.006907,"min":0.006907,"max":0.006907,"count":1},"ggttgg-sa-cpp-f-inl1-sse4":{"avg":0.006093,"median":0.006093,"min":0.006093,"max":0.006093,"count":1},"ggttgg-sa-cpp-d-inl0-avx2":{"avg":0.006673,"median":0.006673,"min":0.006673,"max":0.006673,"count":1},"ggttgg-sa-cpp-d-inl1-avx2":{"avg":0.00545,"median":0.00545,"min":0.00545,"max":0.00545,"count":1},"ggttgg-sa-cpp-f-inl0-avx2":{"avg":0.013348,"median":0.013348,"min":0.013348,"max":0.013348,"count":1},"ggttgg-sa-cpp-f-inl1-avx2":{"avg":0.010681,"median":0.010681,"min":0.010681,"max":0.010681,"count":1},"ggttgg-sa-cpp-d-inl0-512y":{"avg":0.007537,"median":0.007537,"min":0.007537,"max":0.007537,"count":1},"ggttgg-sa-cpp-d-inl1-512y":{"avg":0.006903,"median":0.006903,"min":0.006903,"max":0.006903,"count":1},"ggttgg-sa-cpp-f-inl0-512y":{"avg":0.014863,"median":0.014863,"min":0.014863,"max":0.014863,"count":1},"ggttgg-sa-cpp-f-inl1-512y":{"avg":0.013425,"median":0.013425,"min":0.013425,"max":0.013425,"count":1},"ggttgg-sa-cpp-d-inl0-512z":{"avg":0.006486,"median":0.006486,"min":0.006486,"max":0.006486,"count":1},"ggttgg-sa-cpp-d-inl1-512z":{"avg":0.006547,"median":0.006547,"min":0.006547,"max":0.006547,"count":1},"ggttgg-sa-cpp-f-inl0-512z":{"avg":0.013055,"median":0.013055,"min":0.013055,"max":0.013055,"count":1},"ggttgg-sa-cpp-f-inl1-512z":{"avg":0.012701,"median":0.012701,"min":0.012701,"max":0.012701,"count":1}},"log":"ok"},"app":{"version":"ci-v0.7","description":"Madgraph5_aMCatNLO madgraph4gpu benchmark (2022)","cvmfs_checksum":"34ff738c57b9b7a8a398e4769cba101d","bmkdata_checksum":"d4c9152ed732e012ca54b6518bf3de93","bmk_checksum":"3c9f62f161ec52296be50b21648606b0","containment":"docker"}}
     "copies": 1,
-{"run_info":{"copies":1,"threads_per_copy":1,"events_per_thread":2,"extra_arguments":"--both -eemumu -ggtt -ggttg -ggttgg -dbl -flt -inl0 -inl1"},"report":{"wl-scores":{"eemumu-sa-cuda-d-inl0":1072.013,"eemumu-sa-cuda-d-inl1":1112.401,"eemumu-sa-cuda-f-inl0":2992.508,"eemumu-sa-cuda-f-inl1":3015.399,"eemumu-sa-cpp-d-inl0-best":5.8296,"eemumu-sa-cpp-d-inl0-none":1.5919,"eemumu-sa-cpp-d-inl1-best":11.1671,"eemumu-sa-cpp-d-inl1-none":4.6585,"eemumu-sa-cpp-f-inl0-best":12.1605,"eemumu-sa-cpp-f-inl0-none":1.6592,"eemumu-sa-cpp-f-inl1-best":27.2887,"eemumu-sa-cpp-f-inl1-none":4.9238,"eemumu-sa-cpp-d-inl0-sse4":3.0524,"eemumu-sa-cpp-d-inl1-sse4":8.4065,"eemumu-sa-cpp-f-inl0-sse4":6.071,"eemumu-sa-cpp-f-inl1-sse4":14.6166,"eemumu-sa-cpp-d-inl0-avx2":5.4038,"eemumu-sa-cpp-d-inl1-avx2":11.1671,"eemumu-sa-cpp-f-inl0-avx2":11.2902,"eemumu-sa-cpp-f-inl1-avx2":27.0139,"eemumu-sa-cpp-d-inl0-512y":5.8296,"eemumu-sa-cpp-d-inl1-512y":11.1648,"eemumu-sa-cpp-f-inl0-512y":12.1605,"eemumu-sa-cpp-f-inl1-512y":27.2887,"eemumu-sa-cpp-d-inl0-512z":4.9231,"eemumu-sa-cpp-d-inl1-512z":9.356,"eemumu-sa-cpp-f-inl0-512z":10.0033,"eemumu-sa-cpp-f-inl1-512z":20.404,"ggtt-sa-cuda-d-inl0":130.0279,"ggtt-sa-cuda-d-inl1":130.1676,"ggtt-sa-cuda-f-inl0":364.1785,"ggtt-sa-cuda-f-inl1":363.7591,"ggtt-sa-cpp-d-inl0-best":0.615,"ggtt-sa-cpp-d-inl0-none":0.1917,"ggtt-sa-cpp-d-inl1-best":0.4822,"ggtt-sa-cpp-d-inl1-none":0.2337,"ggtt-sa-cpp-f-inl0-best":1.111,"ggtt-sa-cpp-f-inl0-none":0.2,"ggtt-sa-cpp-f-inl1-best":0.7165,"ggtt-sa-cpp-f-inl1-none":0.2429,"ggtt-sa-cpp-d-inl0-sse4":0.3206,"ggtt-sa-cpp-d-inl1-sse4":0.2771,"ggtt-sa-cpp-f-inl0-sse4":0.4771,"ggtt-sa-cpp-f-inl1-sse4":0.5594,"ggtt-sa-cpp-d-inl0-avx2":0.5525,"ggtt-sa-cpp-d-inl1-avx2":0.458,"ggtt-sa-cpp-f-inl0-avx2":1.0259,"ggtt-sa-cpp-f-inl1-avx2":0.7163,"ggtt-sa-cpp-d-inl0-512y":0.615,"ggtt-sa-cpp-d-inl1-512y":0.4822,"ggtt-sa-cpp-f-inl0-512y":1.111,"ggtt-sa-cpp-f-inl1-512y":0.7165,"ggtt-sa-cpp-d-inl0-512z":0.3709,"ggtt-sa-cpp-d-inl1-512z":0.3445,"ggtt-sa-cpp-f-inl0-512z":0.7731,"ggtt-sa-cpp-f-inl1-512z":0.5628,"ggttg-sa-cuda-d-inl0":13.3654,"ggttg-sa-cuda-d-inl1":13.3478,"ggttg-sa-cuda-f-inl0":45.8364,"ggttg-sa-cuda-f-inl1":44.8611,"ggttg-sa-cpp-d-inl0-best":0.0999,"ggttg-sa-cpp-d-inl0-none":0.0238,"ggttg-sa-cpp-d-inl1-best":0.0888,"ggttg-sa-cpp-d-inl1-none":0.0063,"ggttg-sa-cpp-f-inl0-best":0.1972,"ggttg-sa-cpp-f-inl0-none":0.0244,"ggttg-sa-cpp-f-inl1-best":0.1556,"ggttg-sa-cpp-f-inl1-none":0.0102,"ggttg-sa-cpp-d-inl0-sse4":0.0448,"ggttg-sa-cpp-d-inl1-sse4":0.0419,"ggttg-sa-cpp-f-inl0-sse4":0.0817,"ggttg-sa-cpp-f-inl1-sse4":0.0871,"ggttg-sa-cpp-d-inl0-avx2":0.0872,"ggttg-sa-cpp-d-inl1-avx2":0.0806,"ggttg-sa-cpp-f-inl0-avx2":0.1747,"ggttg-sa-cpp-f-inl1-avx2":0.1401,"ggttg-sa-cpp-d-inl0-512y":0.0999,"ggttg-sa-cpp-d-inl1-512y":0.0888,"ggttg-sa-cpp-f-inl0-512y":0.1972,"ggttg-sa-cpp-f-inl1-512y":0.1556,"ggttg-sa-cpp-d-inl0-512z":0.0723,"ggttg-sa-cpp-d-inl1-512z":0.0646,"ggttg-sa-cpp-f-inl0-512z":0.1503,"ggttg-sa-cpp-f-inl1-512z":0.1153,"ggttgg-sa-cuda-d-inl0":0.4202,"ggttgg-sa-cuda-d-inl1":0.3865,"ggttgg-sa-cuda-f-inl0":0.8751,"ggttgg-sa-cuda-f-inl1":0.7763,"ggttgg-sa-cpp-d-inl0-best":0.0075,"ggttgg-sa-cpp-d-inl0-none":0.0017,"ggttgg-sa-cpp-d-inl1-best":0.0069,"ggttgg-sa-cpp-d-inl1-none":0.0004,"ggttgg-sa-cpp-f-inl0-best":0.0149,"ggttgg-sa-cpp-f-inl0-none":0.0018,"ggttgg-sa-cpp-f-inl1-best":0.0134,"ggttgg-sa-cpp-f-inl1-none":0.0005,"ggttgg-sa-cpp-d-inl0-sse4":0.0033,"ggttgg-sa-cpp-d-inl1-sse4":0.0028,"ggttgg-sa-cpp-f-inl0-sse4":0.0069,"ggttgg-sa-cpp-f-inl1-sse4":0.0061,"ggttgg-sa-cpp-d-inl0-avx2":0.0067,"ggttgg-sa-cpp-d-inl1-avx2":0.0054,"ggttgg-sa-cpp-f-inl0-avx2":0.0134,"ggttgg-sa-cpp-f-inl1-avx2":0.0106,"ggttgg-sa-cpp-d-inl0-512y":0.0075,"ggttgg-sa-cpp-d-inl1-512y":0.0069,"ggttgg-sa-cpp-f-inl0-512y":0.0149,"ggttgg-sa-cpp-f-inl1-512y":0.0134,"ggttgg-sa-cpp-d-inl0-512z":0.0065,"ggttgg-sa-cpp-d-inl1-512z":0.0065,"ggttgg-sa-cpp-f-inl0-512z":0.013,"ggttgg-sa-cpp-f-inl1-512z":0.0126},"wl-stats":{"eemumu-sa-cuda-d-inl0":{"avg":1072.013,"median":1072.013,"min":1072.013,"max":1072.013,"count":1},"eemumu-sa-cuda-d-inl1":{"avg":1112.401,"median":1112.401,"min":1112.401,"max":1112.401,"count":1},"eemumu-sa-cuda-f-inl0":{"avg":2992.508,"median":2992.508,"min":2992.508,"max":2992.508,"count":1},"eemumu-sa-cuda-f-inl1":{"avg":3015.399,"median":3015.399,"min":3015.399,"max":3015.399,"count":1},"eemumu-sa-cpp-d-inl0-best":{"avg":5.8296,"median":5.8296,"min":5.8296,"max":5.8296,"count":1},"eemumu-sa-cpp-d-inl0-none":{"avg":1.5919,"median":1.5919,"min":1.5919,"max":1.5919,"count":1},"eemumu-sa-cpp-d-inl1-best":{"avg":11.1671,"median":11.1671,"min":11.1671,"max":11.1671,"count":1},"eemumu-sa-cpp-d-inl1-none":{"avg":4.6585,"median":4.6585,"min":4.6585,"max":4.6585,"count":1},"eemumu-sa-cpp-f-inl0-best":{"avg":12.1605,"median":12.1605,"min":12.1605,"max":12.1605,"count":1},"eemumu-sa-cpp-f-inl0-none":{"avg":1.6592,"median":1.6592,"min":1.6592,"max":1.6592,"count":1},"eemumu-sa-cpp-f-inl1-best":{"avg":27.2887,"median":27.2887,"min":27.2887,"max":27.2887,"count":1},"eemumu-sa-cpp-f-inl1-none":{"avg":4.9238,"median":4.9238,"min":4.9238,"max":4.9238,"count":1},"eemumu-sa-cpp-d-inl0-sse4":{"avg":3.0524,"median":3.0524,"min":3.0524,"max":3.0524,"count":1},"eemumu-sa-cpp-d-inl1-sse4":{"avg":8.4065,"median":8.4065,"min":8.4065,"max":8.4065,"count":1},"eemumu-sa-cpp-f-inl0-sse4":{"avg":6.071,"median":6.071,"min":6.071,"max":6.071,"count":1},"eemumu-sa-cpp-f-inl1-sse4":{"avg":14.6166,"median":14.6166,"min":14.6166,"max":14.6166,"count":1},"eemumu-sa-cpp-d-inl0-avx2":{"avg":5.4038,"median":5.4038,"min":5.4038,"max":5.4038,"count":1},"eemumu-sa-cpp-d-inl1-avx2":{"avg":11.1671,"median":11.1671,"min":11.1671,"max":11.1671,"count":1},"eemumu-sa-cpp-f-inl0-avx2":{"avg":11.2902,"median":11.2902,"min":11.2902,"max":11.2902,"count":1},"eemumu-sa-cpp-f-inl1-avx2":{"avg":27.0139,"median":27.0139,"min":27.0139,"max":27.0139,"count":1},"eemumu-sa-cpp-d-inl0-512y":{"avg":5.8296,"median":5.8296,"min":5.8296,"max":5.8296,"count":1},"eemumu-sa-cpp-d-inl1-512y":{"avg":11.1648,"median":11.1648,"min":11.1648,"max":11.1648,"count":1},"eemumu-sa-cpp-f-inl0-512y":{"avg":12.1605,"median":12.1605,"min":12.1605,"max":12.1605,"count":1},"eemumu-sa-cpp-f-inl1-512y":{"avg":27.2887,"median":27.2887,"min":27.2887,"max":27.2887,"count":1},"eemumu-sa-cpp-d-inl0-512z":{"avg":4.9231,"median":4.9231,"min":4.9231,"max":4.9231,"count":1},"eemumu-sa-cpp-d-inl1-512z":{"avg":9.356,"median":9.356,"min":9.356,"max":9.356,"count":1},"eemumu-sa-cpp-f-inl0-512z":{"avg":10.0033,"median":10.0033,"min":10.0033,"max":10.0033,"count":1},"eemumu-sa-cpp-f-inl1-512z":{"avg":20.404,"median":20.404,"min":20.404,"max":20.404,"count":1},"ggtt-sa-cuda-d-inl0":{"avg":130.0279,"median":130.0279,"min":130.0279,"max":130.0279,"count":1},"ggtt-sa-cuda-d-inl1":{"avg":130.1676,"median":130.1676,"min":130.1676,"max":130.1676,"count":1},"ggtt-sa-cuda-f-inl0":{"avg":364.1785,"median":364.1785,"min":364.1785,"max":364.1785,"count":1},"ggtt-sa-cuda-f-inl1":{"avg":363.7591,"median":363.7591,"min":363.7591,"max":363.7591,"count":1},"ggtt-sa-cpp-d-inl0-best":{"avg":0.615,"median":0.615,"min":0.615,"max":0.615,"count":1},"ggtt-sa-cpp-d-inl0-none":{"avg":0.1917,"median":0.1917,"min":0.1917,"max":0.1917,"count":1},"ggtt-sa-cpp-d-inl1-best":{"avg":0.4822,"median":0.4822,"min":0.4822,"max":0.4822,"count":1},"ggtt-sa-cpp-d-inl1-none":{"avg":0.2337,"median":0.2337,"min":0.2337,"max":0.2337,"count":1},"ggtt-sa-cpp-f-inl0-best":{"avg":1.111,"median":1.111,"min":1.111,"max":1.111,"count":1},"ggtt-sa-cpp-f-inl0-none":{"avg":0.2,"median":0.2,"min":0.2,"max":0.2,"count":1},"ggtt-sa-cpp-f-inl1-best":{"avg":0.7165,"median":0.7165,"min":0.7165,"max":0.7165,"count":1},"ggtt-sa-cpp-f-inl1-none":{"avg":0.2429,"median":0.2429,"min":0.2429,"max":0.2429,"count":1},"ggtt-sa-cpp-d-inl0-sse4":{"avg":0.3206,"median":0.3206,"min":0.3206,"max":0.3206,"count":1},"ggtt-sa-cpp-d-inl1-sse4":{"avg":0.2771,"median":0.2771,"min":0.2771,"max":0.2771,"count":1},"ggtt-sa-cpp-f-inl0-sse4":{"avg":0.4771,"median":0.4771,"min":0.4771,"max":0.4771,"count":1},"ggtt-sa-cpp-f-inl1-sse4":{"avg":0.5594,"median":0.5594,"min":0.5594,"max":0.5594,"count":1},"ggtt-sa-cpp-d-inl0-avx2":{"avg":0.5525,"median":0.5525,"min":0.5525,"max":0.5525,"count":1},"ggtt-sa-cpp-d-inl1-avx2":{"avg":0.458,"median":0.458,"min":0.458,"max":0.458,"count":1},"ggtt-sa-cpp-f-inl0-avx2":{"avg":1.0259,"median":1.0259,"min":1.0259,"max":1.0259,"count":1},"ggtt-sa-cpp-f-inl1-avx2":{"avg":0.7163,"median":0.7163,"min":0.7163,"max":0.7163,"count":1},"ggtt-sa-cpp-d-inl0-512y":{"avg":0.615,"median":0.615,"min":0.615,"max":0.615,"count":1},"ggtt-sa-cpp-d-inl1-512y":{"avg":0.4822,"median":0.4822,"min":0.4822,"max":0.4822,"count":1},"ggtt-sa-cpp-f-inl0-512y":{"avg":1.111,"median":1.111,"min":1.111,"max":1.111,"count":1},"ggtt-sa-cpp-f-inl1-512y":{"avg":0.7165,"median":0.7165,"min":0.7165,"max":0.7165,"count":1},"ggtt-sa-cpp-d-inl0-512z":{"avg":0.3709,"median":0.3709,"min":0.3709,"max":0.3709,"count":1},"ggtt-sa-cpp-d-inl1-512z":{"avg":0.3445,"median":0.3445,"min":0.3445,"max":0.3445,"count":1},"ggtt-sa-cpp-f-inl0-512z":{"avg":0.7731,"median":0.7731,"min":0.7731,"max":0.7731,"count":1},"ggtt-sa-cpp-f-inl1-512z":{"avg":0.5628,"median":0.5628,"min":0.5628,"max":0.5628,"count":1},"ggttg-sa-cuda-d-inl0":{"avg":13.3654,"median":13.3654,"min":13.3654,"max":13.3654,"count":1},"ggttg-sa-cuda-d-inl1":{"avg":13.3478,"median":13.3478,"min":13.3478,"max":13.3478,"count":1},"ggttg-sa-cuda-f-inl0":{"avg":45.8364,"median":45.8364,"min":45.8364,"max":45.8364,"count":1},"ggttg-sa-cuda-f-inl1":{"avg":44.8611,"median":44.8611,"min":44.8611,"max":44.8611,"count":1},"ggttg-sa-cpp-d-inl0-best":{"avg":0.0999,"median":0.0999,"min":0.0999,"max":0.0999,"count":1},"ggttg-sa-cpp-d-inl0-none":{"avg":0.0238,"median":0.0238,"min":0.0238,"max":0.0238,"count":1},"ggttg-sa-cpp-d-inl1-best":{"avg":0.0888,"median":0.0888,"min":0.0888,"max":0.0888,"count":1},"ggttg-sa-cpp-d-inl1-none":{"avg":0.0063,"median":0.0063,"min":0.0063,"max":0.0063,"count":1},"ggttg-sa-cpp-f-inl0-best":{"avg":0.1972,"median":0.1972,"min":0.1972,"max":0.1972,"count":1},"ggttg-sa-cpp-f-inl0-none":{"avg":0.0244,"median":0.0244,"min":0.0244,"max":0.0244,"count":1},"ggttg-sa-cpp-f-inl1-best":{"avg":0.1556,"median":0.1556,"min":0.1556,"max":0.1556,"count":1},"ggttg-sa-cpp-f-inl1-none":{"avg":0.0102,"median":0.0102,"min":0.0102,"max":0.0102,"count":1},"ggttg-sa-cpp-d-inl0-sse4":{"avg":0.0448,"median":0.0448,"min":0.0448,"max":0.0448,"count":1},"ggttg-sa-cpp-d-inl1-sse4":{"avg":0.0419,"median":0.0419,"min":0.0419,"max":0.0419,"count":1},"ggttg-sa-cpp-f-inl0-sse4":{"avg":0.0817,"median":0.0817,"min":0.0817,"max":0.0817,"count":1},"ggttg-sa-cpp-f-inl1-sse4":{"avg":0.0871,"median":0.0871,"min":0.0871,"max":0.0871,"count":1},"ggttg-sa-cpp-d-inl0-avx2":{"avg":0.0872,"median":0.0872,"min":0.0872,"max":0.0872,"count":1},"ggttg-sa-cpp-d-inl1-avx2":{"avg":0.0806,"median":0.0806,"min":0.0806,"max":0.0806,"count":1},"ggttg-sa-cpp-f-inl0-avx2":{"avg":0.1747,"median":0.1747,"min":0.1747,"max":0.1747,"count":1},"ggttg-sa-cpp-f-inl1-avx2":{"avg":0.1401,"median":0.1401,"min":0.1401,"max":0.1401,"count":1},"ggttg-sa-cpp-d-inl0-512y":{"avg":0.0999,"median":0.0999,"min":0.0999,"max":0.0999,"count":1},"ggttg-sa-cpp-d-inl1-512y":{"avg":0.0888,"median":0.0888,"min":0.0888,"max":0.0888,"count":1},"ggttg-sa-cpp-f-inl0-512y":{"avg":0.1972,"median":0.1972,"min":0.1972,"max":0.1972,"count":1},"ggttg-sa-cpp-f-inl1-512y":{"avg":0.1556,"median":0.1556,"min":0.1556,"max":0.1556,"count":1},"ggttg-sa-cpp-d-inl0-512z":{"avg":0.0723,"median":0.0723,"min":0.0723,"max":0.0723,"count":1},"ggttg-sa-cpp-d-inl1-512z":{"avg":0.0646,"median":0.0646,"min":0.0646,"max":0.0646,"count":1},"ggttg-sa-cpp-f-inl0-512z":{"avg":0.1503,"median":0.1503,"min":0.1503,"max":0.1503,"count":1},"ggttg-sa-cpp-f-inl1-512z":{"avg":0.1153,"median":0.1153,"min":0.1153,"max":0.1153,"count":1},"ggttgg-sa-cuda-d-inl0":{"avg":0.4202,"median":0.4202,"min":0.4202,"max":0.4202,"count":1},"ggttgg-sa-cuda-d-inl1":{"avg":0.3865,"median":0.3865,"min":0.3865,"max":0.3865,"count":1},"ggttgg-sa-cuda-f-inl0":{"avg":0.8751,"median":0.8751,"min":0.8751,"max":0.8751,"count":1},"ggttgg-sa-cuda-f-inl1":{"avg":0.7763,"median":0.7763,"min":0.7763,"max":0.7763,"count":1},"ggttgg-sa-cpp-d-inl0-best":{"avg":0.0075,"median":0.0075,"min":0.0075,"max":0.0075,"count":1},"ggttgg-sa-cpp-d-inl0-none":{"avg":0.0017,"median":0.0017,"min":0.0017,"max":0.0017,"count":1},"ggttgg-sa-cpp-d-inl1-best":{"avg":0.0069,"median":0.0069,"min":0.0069,"max":0.0069,"count":1},"ggttgg-sa-cpp-d-inl1-none":{"avg":0.0004,"median":0.0004,"min":0.0004,"max":0.0004,"count":1},"ggttgg-sa-cpp-f-inl0-best":{"avg":0.0149,"median":0.0149,"min":0.0149,"max":0.0149,"count":1},"ggttgg-sa-cpp-f-inl0-none":{"avg":0.0018,"median":0.0018,"min":0.0018,"max":0.0018,"count":1},"ggttgg-sa-cpp-f-inl1-best":{"avg":0.0134,"median":0.0134,"min":0.0134,"max":0.0134,"count":1},"ggttgg-sa-cpp-f-inl1-none":{"avg":0.0005,"median":0.0005,"min":0.0005,"max":0.0005,"count":1},"ggttgg-sa-cpp-d-inl0-sse4":{"avg":0.0033,"median":0.0033,"min":0.0033,"max":0.0033,"count":1},"ggttgg-sa-cpp-d-inl1-sse4":{"avg":0.0028,"median":0.0028,"min":0.0028,"max":0.0028,"count":1},"ggttgg-sa-cpp-f-inl0-sse4":{"avg":0.0069,"median":0.0069,"min":0.0069,"max":0.0069,"count":1},"ggttgg-sa-cpp-f-inl1-sse4":{"avg":0.0061,"median":0.0061,"min":0.0061,"max":0.0061,"count":1},"ggttgg-sa-cpp-d-inl0-avx2":{"avg":0.0067,"median":0.0067,"min":0.0067,"max":0.0067,"count":1},"ggttgg-sa-cpp-d-inl1-avx2":{"avg":0.0054,"median":0.0054,"min":0.0054,"max":0.0054,"count":1},"ggttgg-sa-cpp-f-inl0-avx2":{"avg":0.0134,"median":0.0134,"min":0.0134,"max":0.0134,"count":1},"ggttgg-sa-cpp-f-inl1-avx2":{"avg":0.0106,"median":0.0106,"min":0.0106,"max":0.0106,"count":1},"ggttgg-sa-cpp-d-inl0-512y":{"avg":0.0075,"median":0.0075,"min":0.0075,"max":0.0075,"count":1},"ggttgg-sa-cpp-d-inl1-512y":{"avg":0.0069,"median":0.0069,"min":0.0069,"max":0.0069,"count":1},"ggttgg-sa-cpp-f-inl0-512y":{"avg":0.0149,"median":0.0149,"min":0.0149,"max":0.0149,"count":1},"ggttgg-sa-cpp-f-inl1-512y":{"avg":0.0134,"median":0.0134,"min":0.0134,"max":0.0134,"count":1},"ggttgg-sa-cpp-d-inl0-512z":{"avg":0.0065,"median":0.0065,"min":0.0065,"max":0.0065,"count":1},"ggttgg-sa-cpp-d-inl1-512z":{"avg":0.0065,"median":0.0065,"min":0.0065,"max":0.0065,"count":1},"ggttgg-sa-cpp-f-inl0-512z":{"avg":0.013,"median":0.013,"min":0.013,"max":0.013,"count":1},"ggttgg-sa-cpp-f-inl1-512z":{"avg":0.0126,"median":0.0126,"min":0.0126,"max":0.0126,"count":1}},"log":"ok"},"app":{"version":"ci-v0.6","description":"Madgraph5_aMCatNLO madgraph4gpu benchmark (2022)","cvmfs_checksum":"e4f4430425242382df2def56875c4d4b","bmkdata_checksum":"4eb8273563af22b829ddbf985ae0b0a9","bmk_checksum":"7b36bbe13203a2c3938a20b58de6a563","containment":"docker"}}
-{"run_info":{"copies":1,"threads_per_copy":1,"events_per_thread":2,"extra_arguments":"--both -eemumu -ggtt -ggttg -ggttgg -dbl -flt -inl0 -inl1"},"report":{"wl-scores":{"eemumu-sa-cuda-d-inl0":1130.432,"eemumu-sa-cuda-d-inl1":1128.067,"eemumu-sa-cuda-f-inl0":3036.306,"eemumu-sa-cuda-f-inl1":3029.1,"eemumu-sa-cpp-d-inl0-best":5.8463,"eemumu-sa-cpp-d-inl0-none":1.6029,"eemumu-sa-cpp-d-inl1-best":10.2311,"eemumu-sa-cpp-d-inl1-none":4.6502,"eemumu-sa-cpp-f-inl0-best":12.0628,"eemumu-sa-cpp-f-inl0-none":1.6559,"eemumu-sa-cpp-f-inl1-best":25.1426,"eemumu-sa-cpp-f-inl1-none":4.9364,"eemumu-sa-cpp-d-inl0-sse4":3.0622,"eemumu-sa-cpp-d-inl1-sse4":7.9254,"eemumu-sa-cpp-f-inl0-sse4":6.0888,"eemumu-sa-cpp-f-inl1-sse4":14.2969,"eemumu-sa-cpp-d-inl0-avx2":5.3727,"eemumu-sa-cpp-d-inl1-avx2":10.2311,"eemumu-sa-cpp-f-inl0-avx2":11.2383,"eemumu-sa-cpp-f-inl1-avx2":24.6208,"eemumu-sa-cpp-d-inl0-512y":5.8463,"eemumu-sa-cpp-d-inl1-512y":10.2161,"eemumu-sa-cpp-f-inl0-512y":12.0628,"eemumu-sa-cpp-f-inl1-512y":25.1426,"eemumu-sa-cpp-d-inl0-512z":4.743,"eemumu-sa-cpp-d-inl1-512z":8.5471,"eemumu-sa-cpp-f-inl0-512z":9.644,"eemumu-sa-cpp-f-inl1-512z":18.3169,"ggtt-sa-cuda-d-inl0":130.0122,"ggtt-sa-cuda-d-inl1":130.2486,"ggtt-sa-cuda-f-inl0":363.6906,"ggtt-sa-cuda-f-inl1":363.4642,"ggtt-sa-cpp-d-inl0-best":0.6213,"ggtt-sa-cpp-d-inl0-none":0.1912,"ggtt-sa-cpp-d-inl1-best":0.4756,"ggtt-sa-cpp-d-inl1-none":0.2335,"ggtt-sa-cpp-f-inl0-best":1.1129,"ggtt-sa-cpp-f-inl0-none":0.2,"ggtt-sa-cpp-f-inl1-best":0.7099,"ggtt-sa-cpp-f-inl1-none":0.2424,"ggtt-sa-cpp-d-inl0-sse4":0.3204,"ggtt-sa-cpp-d-inl1-sse4":0.2768,"ggtt-sa-cpp-f-inl0-sse4":0.4764,"ggtt-sa-cpp-f-inl1-sse4":0.5602,"ggtt-sa-cpp-d-inl0-avx2":0.5574,"ggtt-sa-cpp-d-inl1-avx2":0.4593,"ggtt-sa-cpp-f-inl0-avx2":1.0353,"ggtt-sa-cpp-f-inl1-avx2":0.7014,"ggtt-sa-cpp-d-inl0-512y":0.6213,"ggtt-sa-cpp-d-inl1-512y":0.4756,"ggtt-sa-cpp-f-inl0-512y":1.1129,"ggtt-sa-cpp-f-inl1-512y":0.7099,"ggtt-sa-cpp-d-inl0-512z":0.3732,"ggtt-sa-cpp-d-inl1-512z":0.3438,"ggtt-sa-cpp-f-inl0-512z":0.7762,"ggtt-sa-cpp-f-inl1-512z":0.5638,"ggttg-sa-cuda-d-inl0":13.4296,"ggttg-sa-cuda-d-inl1":13.4207,"ggttg-sa-cuda-f-inl0":45.8793,"ggttg-sa-cuda-f-inl1":45.5322,"ggttg-sa-cpp-d-inl0-best":0.1,"ggttg-sa-cpp-d-inl0-none":0.0238,"ggttg-sa-cpp-d-inl1-best":0.0889,"ggttg-sa-cpp-d-inl1-none":0.0063,"ggttg-sa-cpp-f-inl0-best":0.1974,"ggttg-sa-cpp-f-inl0-none":0.0244,"ggttg-sa-cpp-f-inl1-best":0.1555,"ggttg-sa-cpp-f-inl1-none":0.0102,"ggttg-sa-cpp-d-inl0-sse4":0.0448,"ggttg-sa-cpp-d-inl1-sse4":0.0417,"ggttg-sa-cpp-f-inl0-sse4":0.082,"ggttg-sa-cpp-f-inl1-sse4":0.087,"ggttg-sa-cpp-d-inl0-avx2":0.0873,"ggttg-sa-cpp-d-inl1-avx2":0.0806,"ggttg-sa-cpp-f-inl0-avx2":0.1742,"ggttg-sa-cpp-f-inl1-avx2":0.1402,"ggttg-sa-cpp-d-inl0-512y":0.1,"ggttg-sa-cpp-d-inl1-512y":0.0889,"ggttg-sa-cpp-f-inl0-512y":0.1974,"ggttg-sa-cpp-f-inl1-512y":0.1555,"ggttg-sa-cpp-d-inl0-512z":0.0722,"ggttg-sa-cpp-d-inl1-512z":0.0648,"ggttg-sa-cpp-f-inl0-512z":0.1502,"ggttg-sa-cpp-f-inl1-512z":0.115,"ggttgg-sa-cuda-d-inl0":0.4201,"ggttgg-sa-cuda-d-inl1":0.3868,"ggttgg-sa-cuda-f-inl0":0.8683,"ggttgg-sa-cuda-f-inl1":0.7768,"ggttgg-sa-cpp-d-inl0-best":0.0075,"ggttgg-sa-cpp-d-inl0-none":0.0017,"ggttgg-sa-cpp-d-inl1-best":0.0069,"ggttgg-sa-cpp-d-inl1-none":0.0004,"ggttgg-sa-cpp-f-inl0-best":0.0149,"ggttgg-sa-cpp-f-inl0-none":0.0018,"ggttgg-sa-cpp-f-inl1-best":0.0134,"ggttgg-sa-cpp-f-inl1-none":0.0005,"ggttgg-sa-cpp-d-inl0-sse4":0.0033,"ggttgg-sa-cpp-d-inl1-sse4":0.0028,"ggttgg-sa-cpp-f-inl0-sse4":0.0069,"ggttgg-sa-cpp-f-inl1-sse4":0.0061,"ggttgg-sa-cpp-d-inl0-avx2":0.0067,"ggttgg-sa-cpp-d-inl1-avx2":0.0054,"ggttgg-sa-cpp-f-inl0-avx2":0.0134,"ggttgg-sa-cpp-f-inl1-avx2":0.0106,"ggttgg-sa-cpp-d-inl0-512y":0.0075,"ggttgg-sa-cpp-d-inl1-512y":0.0069,"ggttgg-sa-cpp-f-inl0-512y":0.0149,"ggttgg-sa-cpp-f-inl1-512y":0.0134,"ggttgg-sa-cpp-d-inl0-512z":0.0065,"ggttgg-sa-cpp-d-inl1-512z":0.0065,"ggttgg-sa-cpp-f-inl0-512z":0.0131,"ggttgg-sa-cpp-f-inl1-512z":0.0126},"wl-stats":{"eemumu-sa-cuda-d-inl0":{"avg":1130.432,"median":1130.432,"min":1130.432,"max":1130.432,"count":1},"eemumu-sa-cuda-d-inl1":{"avg":1128.067,"median":1128.067,"min":1128.067,"max":1128.067,"count":1},"eemumu-sa-cuda-f-inl0":{"avg":3036.306,"median":3036.306,"min":3036.306,"max":3036.306,"count":1},"eemumu-sa-cuda-f-inl1":{"avg":3029.1,"median":3029.1,"min":3029.1,"max":3029.1,"count":1},"eemumu-sa-cpp-d-inl0-best":{"avg":5.8463,"median":5.8463,"min":5.8463,"max":5.8463,"count":1},"eemumu-sa-cpp-d-inl0-none":{"avg":1.6029,"median":1.6029,"min":1.6029,"max":1.6029,"count":1},"eemumu-sa-cpp-d-inl1-best":{"avg":10.2311,"median":10.2311,"min":10.2311,"max":10.2311,"count":1},"eemumu-sa-cpp-d-inl1-none":{"avg":4.6502,"median":4.6502,"min":4.6502,"max":4.6502,"count":1},"eemumu-sa-cpp-f-inl0-best":{"avg":12.0628,"median":12.0628,"min":12.0628,"max":12.0628,"count":1},"eemumu-sa-cpp-f-inl0-none":{"avg":1.6559,"median":1.6559,"min":1.6559,"max":1.6559,"count":1},"eemumu-sa-cpp-f-inl1-best":{"avg":25.1426,"median":25.1426,"min":25.1426,"max":25.1426,"count":1},"eemumu-sa-cpp-f-inl1-none":{"avg":4.9364,"median":4.9364,"min":4.9364,"max":4.9364,"count":1},"eemumu-sa-cpp-d-inl0-sse4":{"avg":3.0622,"median":3.0622,"min":3.0622,"max":3.0622,"count":1},"eemumu-sa-cpp-d-inl1-sse4":{"avg":7.9254,"median":7.9254,"min":7.9254,"max":7.9254,"count":1},"eemumu-sa-cpp-f-inl0-sse4":{"avg":6.0888,"median":6.0888,"min":6.0888,"max":6.0888,"count":1},"eemumu-sa-cpp-f-inl1-sse4":{"avg":14.2969,"median":14.2969,"min":14.2969,"max":14.2969,"count":1},"eemumu-sa-cpp-d-inl0-avx2":{"avg":5.3727,"median":5.3727,"min":5.3727,"max":5.3727,"count":1},"eemumu-sa-cpp-d-inl1-avx2":{"avg":10.2311,"median":10.2311,"min":10.2311,"max":10.2311,"count":1},"eemumu-sa-cpp-f-inl0-avx2":{"avg":11.2383,"median":11.2383,"min":11.2383,"max":11.2383,"count":1},"eemumu-sa-cpp-f-inl1-avx2":{"avg":24.6208,"median":24.6208,"min":24.6208,"max":24.6208,"count":1},"eemumu-sa-cpp-d-inl0-512y":{"avg":5.8463,"median":5.8463,"min":5.8463,"max":5.8463,"count":1},"eemumu-sa-cpp-d-inl1-512y":{"avg":10.2161,"median":10.2161,"min":10.2161,"max":10.2161,"count":1},"eemumu-sa-cpp-f-inl0-512y":{"avg":12.0628,"median":12.0628,"min":12.0628,"max":12.0628,"count":1},"eemumu-sa-cpp-f-inl1-512y":{"avg":25.1426,"median":25.1426,"min":25.1426,"max":25.1426,"count":1},"eemumu-sa-cpp-d-inl0-512z":{"avg":4.743,"median":4.743,"min":4.743,"max":4.743,"count":1},"eemumu-sa-cpp-d-inl1-512z":{"avg":8.5471,"median":8.5471,"min":8.5471,"max":8.5471,"count":1},"eemumu-sa-cpp-f-inl0-512z":{"avg":9.644,"median":9.644,"min":9.644,"max":9.644,"count":1},"eemumu-sa-cpp-f-inl1-512z":{"avg":18.3169,"median":18.3169,"min":18.3169,"max":18.3169,"count":1},"ggtt-sa-cuda-d-inl0":{"avg":130.0122,"median":130.0122,"min":130.0122,"max":130.0122,"count":1},"ggtt-sa-cuda-d-inl1":{"avg":130.2486,"median":130.2486,"min":130.2486,"max":130.2486,"count":1},"ggtt-sa-cuda-f-inl0":{"avg":363.6906,"median":363.6906,"min":363.6906,"max":363.6906,"count":1},"ggtt-sa-cuda-f-inl1":{"avg":363.4642,"median":363.4642,"min":363.4642,"max":363.4642,"count":1},"ggtt-sa-cpp-d-inl0-best":{"avg":0.6213,"median":0.6213,"min":0.6213,"max":0.6213,"count":1},"ggtt-sa-cpp-d-inl0-none":{"avg":0.1912,"median":0.1912,"min":0.1912,"max":0.1912,"count":1},"ggtt-sa-cpp-d-inl1-best":{"avg":0.4756,"median":0.4756,"min":0.4756,"max":0.4756,"count":1},"ggtt-sa-cpp-d-inl1-none":{"avg":0.2335,"median":0.2335,"min":0.2335,"max":0.2335,"count":1},"ggtt-sa-cpp-f-inl0-best":{"avg":1.1129,"median":1.1129,"min":1.1129,"max":1.1129,"count":1},"ggtt-sa-cpp-f-inl0-none":{"avg":0.2,"median":0.2,"min":0.2,"max":0.2,"count":1},"ggtt-sa-cpp-f-inl1-best":{"avg":0.7099,"median":0.7099,"min":0.7099,"max":0.7099,"count":1},"ggtt-sa-cpp-f-inl1-none":{"avg":0.2424,"median":0.2424,"min":0.2424,"max":0.2424,"count":1},"ggtt-sa-cpp-d-inl0-sse4":{"avg":0.3204,"median":0.3204,"min":0.3204,"max":0.3204,"count":1},"ggtt-sa-cpp-d-inl1-sse4":{"avg":0.2768,"median":0.2768,"min":0.2768,"max":0.2768,"count":1},"ggtt-sa-cpp-f-inl0-sse4":{"avg":0.4764,"median":0.4764,"min":0.4764,"max":0.4764,"count":1},"ggtt-sa-cpp-f-inl1-sse4":{"avg":0.5602,"median":0.5602,"min":0.5602,"max":0.5602,"count":1},"ggtt-sa-cpp-d-inl0-avx2":{"avg":0.5574,"median":0.5574,"min":0.5574,"max":0.5574,"count":1},"ggtt-sa-cpp-d-inl1-avx2":{"avg":0.4593,"median":0.4593,"min":0.4593,"max":0.4593,"count":1},"ggtt-sa-cpp-f-inl0-avx2":{"avg":1.0353,"median":1.0353,"min":1.0353,"max":1.0353,"count":1},"ggtt-sa-cpp-f-inl1-avx2":{"avg":0.7014,"median":0.7014,"min":0.7014,"max":0.7014,"count":1},"ggtt-sa-cpp-d-inl0-512y":{"avg":0.6213,"median":0.6213,"min":0.6213,"max":0.6213,"count":1},"ggtt-sa-cpp-d-inl1-512y":{"avg":0.4756,"median":0.4756,"min":0.4756,"max":0.4756,"count":1},"ggtt-sa-cpp-f-inl0-512y":{"avg":1.1129,"median":1.1129,"min":1.1129,"max":1.1129,"count":1},"ggtt-sa-cpp-f-inl1-512y":{"avg":0.7099,"median":0.7099,"min":0.7099,"max":0.7099,"count":1},"ggtt-sa-cpp-d-inl0-512z":{"avg":0.3732,"median":0.3732,"min":0.3732,"max":0.3732,"count":1},"ggtt-sa-cpp-d-inl1-512z":{"avg":0.3438,"median":0.3438,"min":0.3438,"max":0.3438,"count":1},"ggtt-sa-cpp-f-inl0-512z":{"avg":0.7762,"median":0.7762,"min":0.7762,"max":0.7762,"count":1},"ggtt-sa-cpp-f-inl1-512z":{"avg":0.5638,"median":0.5638,"min":0.5638,"max":0.5638,"count":1},"ggttg-sa-cuda-d-inl0":{"avg":13.4296,"median":13.4296,"min":13.4296,"max":13.4296,"count":1},"ggttg-sa-cuda-d-inl1":{"avg":13.4207,"median":13.4207,"min":13.4207,"max":13.4207,"count":1},"ggttg-sa-cuda-f-inl0":{"avg":45.8793,"median":45.8793,"min":45.8793,"max":45.8793,"count":1},"ggttg-sa-cuda-f-inl1":{"avg":45.5322,"median":45.5322,"min":45.5322,"max":45.5322,"count":1},"ggttg-sa-cpp-d-inl0-best":{"avg":0.1,"median":0.1,"min":0.1,"max":0.1,"count":1},"ggttg-sa-cpp-d-inl0-none":{"avg":0.0238,"median":0.0238,"min":0.0238,"max":0.0238,"count":1},"ggttg-sa-cpp-d-inl1-best":{"avg":0.0889,"median":0.0889,"min":0.0889,"max":0.0889,"count":1},"ggttg-sa-cpp-d-inl1-none":{"avg":0.0063,"median":0.0063,"min":0.0063,"max":0.0063,"count":1},"ggttg-sa-cpp-f-inl0-best":{"avg":0.1974,"median":0.1974,"min":0.1974,"max":0.1974,"count":1},"ggttg-sa-cpp-f-inl0-none":{"avg":0.0244,"median":0.0244,"min":0.0244,"max":0.0244,"count":1},"ggttg-sa-cpp-f-inl1-best":{"avg":0.1555,"median":0.1555,"min":0.1555,"max":0.1555,"count":1},"ggttg-sa-cpp-f-inl1-none":{"avg":0.0102,"median":0.0102,"min":0.0102,"max":0.0102,"count":1},"ggttg-sa-cpp-d-inl0-sse4":{"avg":0.0448,"median":0.0448,"min":0.0448,"max":0.0448,"count":1},"ggttg-sa-cpp-d-inl1-sse4":{"avg":0.0417,"median":0.0417,"min":0.0417,"max":0.0417,"count":1},"ggttg-sa-cpp-f-inl0-sse4":{"avg":0.082,"median":0.082,"min":0.082,"max":0.082,"count":1},"ggttg-sa-cpp-f-inl1-sse4":{"avg":0.087,"median":0.087,"min":0.087,"max":0.087,"count":1},"ggttg-sa-cpp-d-inl0-avx2":{"avg":0.0873,"median":0.0873,"min":0.0873,"max":0.0873,"count":1},"ggttg-sa-cpp-d-inl1-avx2":{"avg":0.0806,"median":0.0806,"min":0.0806,"max":0.0806,"count":1},"ggttg-sa-cpp-f-inl0-avx2":{"avg":0.1742,"median":0.1742,"min":0.1742,"max":0.1742,"count":1},"ggttg-sa-cpp-f-inl1-avx2":{"avg":0.1402,"median":0.1402,"min":0.1402,"max":0.1402,"count":1},"ggttg-sa-cpp-d-inl0-512y":{"avg":0.1,"median":0.1,"min":0.1,"max":0.1,"count":1},"ggttg-sa-cpp-d-inl1-512y":{"avg":0.0889,"median":0.0889,"min":0.0889,"max":0.0889,"count":1},"ggttg-sa-cpp-f-inl0-512y":{"avg":0.1974,"median":0.1974,"min":0.1974,"max":0.1974,"count":1},"ggttg-sa-cpp-f-inl1-512y":{"avg":0.1555,"median":0.1555,"min":0.1555,"max":0.1555,"count":1},"ggttg-sa-cpp-d-inl0-512z":{"avg":0.0722,"median":0.0722,"min":0.0722,"max":0.0722,"count":1},"ggttg-sa-cpp-d-inl1-512z":{"avg":0.0648,"median":0.0648,"min":0.0648,"max":0.0648,"count":1},"ggttg-sa-cpp-f-inl0-512z":{"avg":0.1502,"median":0.1502,"min":0.1502,"max":0.1502,"count":1},"ggttg-sa-cpp-f-inl1-512z":{"avg":0.115,"median":0.115,"min":0.115,"max":0.115,"count":1},"ggttgg-sa-cuda-d-inl0":{"avg":0.4201,"median":0.4201,"min":0.4201,"max":0.4201,"count":1},"ggttgg-sa-cuda-d-inl1":{"avg":0.3868,"median":0.3868,"min":0.3868,"max":0.3868,"count":1},"ggttgg-sa-cuda-f-inl0":{"avg":0.8683,"median":0.8683,"min":0.8683,"max":0.8683,"count":1},"ggttgg-sa-cuda-f-inl1":{"avg":0.7768,"median":0.7768,"min":0.7768,"max":0.7768,"count":1},"ggttgg-sa-cpp-d-inl0-best":{"avg":0.0075,"median":0.0075,"min":0.0075,"max":0.0075,"count":1},"ggttgg-sa-cpp-d-inl0-none":{"avg":0.0017,"median":0.0017,"min":0.0017,"max":0.0017,"count":1},"ggttgg-sa-cpp-d-inl1-best":{"avg":0.0069,"median":0.0069,"min":0.0069,"max":0.0069,"count":1},"ggttgg-sa-cpp-d-inl1-none":{"avg":0.0004,"median":0.0004,"min":0.0004,"max":0.0004,"count":1},"ggttgg-sa-cpp-f-inl0-best":{"avg":0.0149,"median":0.0149,"min":0.0149,"max":0.0149,"count":1},"ggttgg-sa-cpp-f-inl0-none":{"avg":0.0018,"median":0.0018,"min":0.0018,"max":0.0018,"count":1},"ggttgg-sa-cpp-f-inl1-best":{"avg":0.0134,"median":0.0134,"min":0.0134,"max":0.0134,"count":1},"ggttgg-sa-cpp-f-inl1-none":{"avg":0.0005,"median":0.0005,"min":0.0005,"max":0.0005,"count":1},"ggttgg-sa-cpp-d-inl0-sse4":{"avg":0.0033,"median":0.0033,"min":0.0033,"max":0.0033,"count":1},"ggttgg-sa-cpp-d-inl1-sse4":{"avg":0.0028,"median":0.0028,"min":0.0028,"max":0.0028,"count":1},"ggttgg-sa-cpp-f-inl0-sse4":{"avg":0.0069,"median":0.0069,"min":0.0069,"max":0.0069,"count":1},"ggttgg-sa-cpp-f-inl1-sse4":{"avg":0.0061,"median":0.0061,"min":0.0061,"max":0.0061,"count":1},"ggttgg-sa-cpp-d-inl0-avx2":{"avg":0.0067,"median":0.0067,"min":0.0067,"max":0.0067,"count":1},"ggttgg-sa-cpp-d-inl1-avx2":{"avg":0.0054,"median":0.0054,"min":0.0054,"max":0.0054,"count":1},"ggttgg-sa-cpp-f-inl0-avx2":{"avg":0.0134,"median":0.0134,"min":0.0134,"max":0.0134,"count":1},"ggttgg-sa-cpp-f-inl1-avx2":{"avg":0.0106,"median":0.0106,"min":0.0106,"max":0.0106,"count":1},"ggttgg-sa-cpp-d-inl0-512y":{"avg":0.0075,"median":0.0075,"min":0.0075,"max":0.0075,"count":1},"ggttgg-sa-cpp-d-inl1-512y":{"avg":0.0069,"median":0.0069,"min":0.0069,"max":0.0069,"count":1},"ggttgg-sa-cpp-f-inl0-512y":{"avg":0.0149,"median":0.0149,"min":0.0149,"max":0.0149,"count":1},"ggttgg-sa-cpp-f-inl1-512y":{"avg":0.0134,"median":0.0134,"min":0.0134,"max":0.0134,"count":1},"ggttgg-sa-cpp-d-inl0-512z":{"avg":0.0065,"median":0.0065,"min":0.0065,"max":0.0065,"count":1},"ggttgg-sa-cpp-d-inl1-512z":{"avg":0.0065,"median":0.0065,"min":0.0065,"max":0.0065,"count":1},"ggttgg-sa-cpp-f-inl0-512z":{"avg":0.0131,"median":0.0131,"min":0.0131,"max":0.0131,"count":1},"ggttgg-sa-cpp-f-inl1-512z":{"avg":0.0126,"median":0.0126,"min":0.0126,"max":0.0126,"count":1}},"log":"ok"},"app":{"version":"ci-v0.6","description":"Madgraph5_aMCatNLO madgraph4gpu benchmark (2022)","cvmfs_checksum":"05f5179a44c0e2051bbb092a63cf0daf","bmkdata_checksum":"4eb8273563af22b829ddbf985ae0b0a9","bmk_checksum":"9b7bedb12e18a214106591542f8b3093","containment":"docker"}}
+{"run_info":{"copies":1,"threads_per_copy":1,"events_per_thread":2,"extra_arguments":"--both -eemumu -ggtt -ggttg -ggttgg -dbl -flt -inl0 -inl1"},"report":{"wl-scores":{"eemumu-sa-cuda-d-inl0":48.03328,"eemumu-sa-cuda-d-inl1":49.23856,"eemumu-sa-cuda-f-inl0":1416.867,"eemumu-sa-cuda-f-inl1":1489.242,"eemumu-sa-cpp-d-inl0-best":5.828236,"eemumu-sa-cpp-d-inl0-none":1.59746,"eemumu-sa-cpp-d-inl1-best":11.32252,"eemumu-sa-cpp-d-inl1-none":4.672886,"eemumu-sa-cpp-f-inl0-best":12.2777,"eemumu-sa-cpp-f-inl0-none":1.661227,"eemumu-sa-cpp-f-inl1-best":28.87536,"eemumu-sa-cpp-f-inl1-none":4.931595,"eemumu-sa-cpp-d-inl0-sse4":3.065833,"eemumu-sa-cpp-d-inl1-sse4":8.437464,"eemumu-sa-cpp-f-inl0-sse4":6.084133,"eemumu-sa-cpp-f-inl1-sse4":14.78239,"eemumu-sa-cpp-d-inl0-avx2":5.405444,"eemumu-sa-cpp-d-inl1-avx2":11.29233,"eemumu-sa-cpp-f-inl0-avx2":11.36632,"eemumu-sa-cpp-f-inl1-avx2":27.9435,"eemumu-sa-cpp-d-inl0-512y":5.828236,"eemumu-sa-cpp-d-inl1-512y":11.32252,"eemumu-sa-cpp-f-inl0-512y":12.2777,"eemumu-sa-cpp-f-inl1-512y":28.87536,"eemumu-sa-cpp-d-inl0-512z":5.001285,"eemumu-sa-cpp-d-inl1-512z":9.429986,"eemumu-sa-cpp-f-inl0-512z":10.08082,"eemumu-sa-cpp-f-inl1-512z":21.22853,"ggtt-sa-cuda-d-inl0":5.562397,"ggtt-sa-cuda-d-inl1":5.897293,"ggtt-sa-cuda-f-inl0":175.6326,"ggtt-sa-cuda-f-inl1":170.4551,"ggtt-sa-cpp-d-inl0-best":0.625109,"ggtt-sa-cpp-d-inl0-none":0.192193,"ggtt-sa-cpp-d-inl1-best":0.485836,"ggtt-sa-cpp-d-inl1-none":0.234364,"ggtt-sa-cpp-f-inl0-best":1.11991,"ggtt-sa-cpp-f-inl0-none":0.200577,"ggtt-sa-cpp-f-inl1-best":0.726677,"ggtt-sa-cpp-f-inl1-none":0.242927,"ggtt-sa-cpp-d-inl0-sse4":0.32228,"ggtt-sa-cpp-d-inl1-sse4":0.278231,"ggtt-sa-cpp-f-inl0-sse4":0.48159,"ggtt-sa-cpp-f-inl1-sse4":0.56442,"ggtt-sa-cpp-d-inl0-avx2":0.554401,"ggtt-sa-cpp-d-inl1-avx2":0.463128,"ggtt-sa-cpp-f-inl0-avx2":1.035971,"ggtt-sa-cpp-f-inl1-avx2":0.722414,"ggtt-sa-cpp-d-inl0-512y":0.625109,"ggtt-sa-cpp-d-inl1-512y":0.485836,"ggtt-sa-cpp-f-inl0-512y":1.11991,"ggtt-sa-cpp-f-inl1-512y":0.726677,"ggtt-sa-cpp-d-inl0-512z":0.375805,"ggtt-sa-cpp-d-inl1-512z":0.349716,"ggtt-sa-cpp-f-inl0-512z":0.786393,"ggtt-sa-cpp-f-inl1-512z":0.567973,"ggttg-sa-cuda-d-inl0":0.818309,"ggttg-sa-cuda-d-inl1":0.818318,"ggttg-sa-cuda-f-inl0":18.19535,"ggttg-sa-cuda-f-inl1":16.64767,"ggttg-sa-cpp-d-inl0-best":0.099982,"ggttg-sa-cpp-d-inl0-none":0.023869,"ggttg-sa-cpp-d-inl1-best":0.089047,"ggttg-sa-cpp-d-inl1-none":0.006272,"ggttg-sa-cpp-f-inl0-best":0.197359,"ggttg-sa-cpp-f-inl0-none":0.024436,"ggttg-sa-cpp-f-inl1-best":0.155737,"ggttg-sa-cpp-f-inl1-none":0.01021,"ggttg-sa-cpp-d-inl0-sse4":0.044899,"ggttg-sa-cpp-d-inl1-sse4":0.041949,"ggttg-sa-cpp-f-inl0-sse4":0.082058,"ggttg-sa-cpp-f-inl1-sse4":0.087212,"ggttg-sa-cpp-d-inl0-avx2":0.087551,"ggttg-sa-cpp-d-inl1-avx2":0.080926,"ggttg-sa-cpp-f-inl0-avx2":0.175113,"ggttg-sa-cpp-f-inl1-avx2":0.140325,"ggttg-sa-cpp-d-inl0-512y":0.099982,"ggttg-sa-cpp-d-inl1-512y":0.089047,"ggttg-sa-cpp-f-inl0-512y":0.197359,"ggttg-sa-cpp-f-inl1-512y":0.155737,"ggttg-sa-cpp-d-inl0-512z":0.072299,"ggttg-sa-cpp-d-inl1-512z":0.064907,"ggttg-sa-cpp-f-inl0-512z":0.150435,"ggttg-sa-cpp-f-inl1-512z":0.115494,"ggttgg-sa-cuda-d-inl0":0.055457,"ggttgg-sa-cuda-d-inl1":0.06155,"ggttgg-sa-cuda-f-inl0":0.307607,"ggttgg-sa-cuda-f-inl1":0.265562,"ggttgg-sa-cpp-d-inl0-best":0.007551,"ggttgg-sa-cpp-d-inl0-none":0.001745,"ggttgg-sa-cpp-d-inl1-best":0.006898,"ggttgg-sa-cpp-d-inl1-none":0.000386,"ggttgg-sa-cpp-f-inl0-best":0.015008,"ggttgg-sa-cpp-f-inl0-none":0.001827,"ggttgg-sa-cpp-f-inl1-best":0.013485,"ggttgg-sa-cpp-f-inl1-none":0.000499,"ggttgg-sa-cpp-d-inl0-sse4":0.003351,"ggttgg-sa-cpp-d-inl1-sse4":0.002775,"ggttgg-sa-cpp-f-inl0-sse4":0.006906,"ggttgg-sa-cpp-f-inl1-sse4":0.006083,"ggttgg-sa-cpp-d-inl0-avx2":0.006676,"ggttgg-sa-cpp-d-inl1-avx2":0.005454,"ggttgg-sa-cpp-f-inl0-avx2":0.013386,"ggttgg-sa-cpp-f-inl1-avx2":0.010666,"ggttgg-sa-cpp-d-inl0-512y":0.007551,"ggttgg-sa-cpp-d-inl1-512y":0.006898,"ggttgg-sa-cpp-f-inl0-512y":0.015008,"ggttgg-sa-cpp-f-inl1-512y":0.013485,"ggttgg-sa-cpp-d-inl0-512z":0.006376,"ggttgg-sa-cpp-d-inl1-512z":0.006534,"ggttgg-sa-cpp-f-inl0-512z":0.013083,"ggttgg-sa-cpp-f-inl1-512z":0.012661},"wl-stats":{"eemumu-sa-cuda-d-inl0":{"avg":48.03328,"median":48.03328,"min":48.03328,"max":48.03328,"count":1},"eemumu-sa-cuda-d-inl1":{"avg":49.23856,"median":49.23856,"min":49.23856,"max":49.23856,"count":1},"eemumu-sa-cuda-f-inl0":{"avg":1416.867,"median":1416.867,"min":1416.867,"max":1416.867,"count":1},"eemumu-sa-cuda-f-inl1":{"avg":1489.242,"median":1489.242,"min":1489.242,"max":1489.242,"count":1},"eemumu-sa-cpp-d-inl0-best":{"avg":5.828236,"median":5.828236,"min":5.828236,"max":5.828236,"count":1},"eemumu-sa-cpp-d-inl0-none":{"avg":1.59746,"median":1.59746,"min":1.59746,"max":1.59746,"count":1},"eemumu-sa-cpp-d-inl1-best":{"avg":11.32252,"median":11.32252,"min":11.32252,"max":11.32252,"count":1},"eemumu-sa-cpp-d-inl1-none":{"avg":4.672886,"median":4.672886,"min":4.672886,"max":4.672886,"count":1},"eemumu-sa-cpp-f-inl0-best":{"avg":12.2777,"median":12.2777,"min":12.2777,"max":12.2777,"count":1},"eemumu-sa-cpp-f-inl0-none":{"avg":1.661227,"median":1.661227,"min":1.661227,"max":1.661227,"count":1},"eemumu-sa-cpp-f-inl1-best":{"avg":28.87536,"median":28.87536,"min":28.87536,"max":28.87536,"count":1},"eemumu-sa-cpp-f-inl1-none":{"avg":4.931595,"median":4.931595,"min":4.931595,"max":4.931595,"count":1},"eemumu-sa-cpp-d-inl0-sse4":{"avg":3.065833,"median":3.065833,"min":3.065833,"max":3.065833,"count":1},"eemumu-sa-cpp-d-inl1-sse4":{"avg":8.437464,"median":8.437464,"min":8.437464,"max":8.437464,"count":1},"eemumu-sa-cpp-f-inl0-sse4":{"avg":6.084133,"median":6.084133,"min":6.084133,"max":6.084133,"count":1},"eemumu-sa-cpp-f-inl1-sse4":{"avg":14.78239,"median":14.78239,"min":14.78239,"max":14.78239,"count":1},"eemumu-sa-cpp-d-inl0-avx2":{"avg":5.405444,"median":5.405444,"min":5.405444,"max":5.405444,"count":1},"eemumu-sa-cpp-d-inl1-avx2":{"avg":11.29233,"median":11.29233,"min":11.29233,"max":11.29233,"count":1},"eemumu-sa-cpp-f-inl0-avx2":{"avg":11.36632,"median":11.36632,"min":11.36632,"max":11.36632,"count":1},"eemumu-sa-cpp-f-inl1-avx2":{"avg":27.9435,"median":27.9435,"min":27.9435,"max":27.9435,"count":1},"eemumu-sa-cpp-d-inl0-512y":{"avg":5.828236,"median":5.828236,"min":5.828236,"max":5.828236,"count":1},"eemumu-sa-cpp-d-inl1-512y":{"avg":11.32252,"median":11.32252,"min":11.32252,"max":11.32252,"count":1},"eemumu-sa-cpp-f-inl0-512y":{"avg":12.2777,"median":12.2777,"min":12.2777,"max":12.2777,"count":1},"eemumu-sa-cpp-f-inl1-512y":{"avg":28.87536,"median":28.87536,"min":28.87536,"max":28.87536,"count":1},"eemumu-sa-cpp-d-inl0-512z":{"avg":5.001285,"median":5.001285,"min":5.001285,"max":5.001285,"count":1},"eemumu-sa-cpp-d-inl1-512z":{"avg":9.429986,"median":9.429986,"min":9.429986,"max":9.429986,"count":1},"eemumu-sa-cpp-f-inl0-512z":{"avg":10.08082,"median":10.08082,"min":10.08082,"max":10.08082,"count":1},"eemumu-sa-cpp-f-inl1-512z":{"avg":21.22853,"median":21.22853,"min":21.22853,"max":21.22853,"count":1},"ggtt-sa-cuda-d-inl0":{"avg":5.562397,"median":5.562397,"min":5.562397,"max":5.562397,"count":1},"ggtt-sa-cuda-d-inl1":{"avg":5.897293,"median":5.897293,"min":5.897293,"max":5.897293,"count":1},"ggtt-sa-cuda-f-inl0":{"avg":175.6326,"median":175.6326,"min":175.6326,"max":175.6326,"count":1},"ggtt-sa-cuda-f-inl1":{"avg":170.4551,"median":170.4551,"min":170.4551,"max":170.4551,"count":1},"ggtt-sa-cpp-d-inl0-best":{"avg":0.625109,"median":0.625109,"min":0.625109,"max":0.625109,"count":1},"ggtt-sa-cpp-d-inl0-none":{"avg":0.192193,"median":0.192193,"min":0.192193,"max":0.192193,"count":1},"ggtt-sa-cpp-d-inl1-best":{"avg":0.485836,"median":0.485836,"min":0.485836,"max":0.485836,"count":1},"ggtt-sa-cpp-d-inl1-none":{"avg":0.234364,"median":0.234364,"min":0.234364,"max":0.234364,"count":1},"ggtt-sa-cpp-f-inl0-best":{"avg":1.11991,"median":1.11991,"min":1.11991,"max":1.11991,"count":1},"ggtt-sa-cpp-f-inl0-none":{"avg":0.200577,"median":0.200577,"min":0.200577,"max":0.200577,"count":1},"ggtt-sa-cpp-f-inl1-best":{"avg":0.726677,"median":0.726677,"min":0.726677,"max":0.726677,"count":1},"ggtt-sa-cpp-f-inl1-none":{"avg":0.242927,"median":0.242927,"min":0.242927,"max":0.242927,"count":1},"ggtt-sa-cpp-d-inl0-sse4":{"avg":0.32228,"median":0.32228,"min":0.32228,"max":0.32228,"count":1},"ggtt-sa-cpp-d-inl1-sse4":{"avg":0.278231,"median":0.278231,"min":0.278231,"max":0.278231,"count":1},"ggtt-sa-cpp-f-inl0-sse4":{"avg":0.48159,"median":0.48159,"min":0.48159,"max":0.48159,"count":1},"ggtt-sa-cpp-f-inl1-sse4":{"avg":0.56442,"median":0.56442,"min":0.56442,"max":0.56442,"count":1},"ggtt-sa-cpp-d-inl0-avx2":{"avg":0.554401,"median":0.554401,"min":0.554401,"max":0.554401,"count":1},"ggtt-sa-cpp-d-inl1-avx2":{"avg":0.463128,"median":0.463128,"min":0.463128,"max":0.463128,"count":1},"ggtt-sa-cpp-f-inl0-avx2":{"avg":1.035971,"median":1.035971,"min":1.035971,"max":1.035971,"count":1},"ggtt-sa-cpp-f-inl1-avx2":{"avg":0.722414,"median":0.722414,"min":0.722414,"max":0.722414,"count":1},"ggtt-sa-cpp-d-inl0-512y":{"avg":0.625109,"median":0.625109,"min":0.625109,"max":0.625109,"count":1},"ggtt-sa-cpp-d-inl1-512y":{"avg":0.485836,"median":0.485836,"min":0.485836,"max":0.485836,"count":1},"ggtt-sa-cpp-f-inl0-512y":{"avg":1.11991,"median":1.11991,"min":1.11991,"max":1.11991,"count":1},"ggtt-sa-cpp-f-inl1-512y":{"avg":0.726677,"median":0.726677,"min":0.726677,"max":0.726677,"count":1},"ggtt-sa-cpp-d-inl0-512z":{"avg":0.375805,"median":0.375805,"min":0.375805,"max":0.375805,"count":1},"ggtt-sa-cpp-d-inl1-512z":{"avg":0.349716,"median":0.349716,"min":0.349716,"max":0.349716,"count":1},"ggtt-sa-cpp-f-inl0-512z":{"avg":0.786393,"median":0.786393,"min":0.786393,"max":0.786393,"count":1},"ggtt-sa-cpp-f-inl1-512z":{"avg":0.567973,"median":0.567973,"min":0.567973,"max":0.567973,"count":1},"ggttg-sa-cuda-d-inl0":{"avg":0.818309,"median":0.818309,"min":0.818309,"max":0.818309,"count":1},"ggttg-sa-cuda-d-inl1":{"avg":0.818318,"median":0.818318,"min":0.818318,"max":0.818318,"count":1},"ggttg-sa-cuda-f-inl0":{"avg":18.19535,"median":18.19535,"min":18.19535,"max":18.19535,"count":1},"ggttg-sa-cuda-f-inl1":{"avg":16.64767,"median":16.64767,"min":16.64767,"max":16.64767,"count":1},"ggttg-sa-cpp-d-inl0-best":{"avg":0.099982,"median":0.099982,"min":0.099982,"max":0.099982,"count":1},"ggttg-sa-cpp-d-inl0-none":{"avg":0.023869,"median":0.023869,"min":0.023869,"max":0.023869,"count":1},"ggttg-sa-cpp-d-inl1-best":{"avg":0.089047,"median":0.089047,"min":0.089047,"max":0.089047,"count":1},"ggttg-sa-cpp-d-inl1-none":{"avg":0.006272,"median":0.006272,"min":0.006272,"max":0.006272,"count":1},"ggttg-sa-cpp-f-inl0-best":{"avg":0.197359,"median":0.197359,"min":0.197359,"max":0.197359,"count":1},"ggttg-sa-cpp-f-inl0-none":{"avg":0.024436,"median":0.024436,"min":0.024436,"max":0.024436,"count":1},"ggttg-sa-cpp-f-inl1-best":{"avg":0.155737,"median":0.155737,"min":0.155737,"max":0.155737,"count":1},"ggttg-sa-cpp-f-inl1-none":{"avg":0.01021,"median":0.01021,"min":0.01021,"max":0.01021,"count":1},"ggttg-sa-cpp-d-inl0-sse4":{"avg":0.044899,"median":0.044899,"min":0.044899,"max":0.044899,"count":1},"ggttg-sa-cpp-d-inl1-sse4":{"avg":0.041949,"median":0.041949,"min":0.041949,"max":0.041949,"count":1},"ggttg-sa-cpp-f-inl0-sse4":{"avg":0.082058,"median":0.082058,"min":0.082058,"max":0.082058,"count":1},"ggttg-sa-cpp-f-inl1-sse4":{"avg":0.087212,"median":0.087212,"min":0.087212,"max":0.087212,"count":1},"ggttg-sa-cpp-d-inl0-avx2":{"avg":0.087551,"median":0.087551,"min":0.087551,"max":0.087551,"count":1},"ggttg-sa-cpp-d-inl1-avx2":{"avg":0.080926,"median":0.080926,"min":0.080926,"max":0.080926,"count":1},"ggttg-sa-cpp-f-inl0-avx2":{"avg":0.175113,"median":0.175113,"min":0.175113,"max":0.175113,"count":1},"ggttg-sa-cpp-f-inl1-avx2":{"avg":0.140325,"median":0.140325,"min":0.140325,"max":0.140325,"count":1},"ggttg-sa-cpp-d-inl0-512y":{"avg":0.099982,"median":0.099982,"min":0.099982,"max":0.099982,"count":1},"ggttg-sa-cpp-d-inl1-512y":{"avg":0.089047,"median":0.089047,"min":0.089047,"max":0.089047,"count":1},"ggttg-sa-cpp-f-inl0-512y":{"avg":0.197359,"median":0.197359,"min":0.197359,"max":0.197359,"count":1},"ggttg-sa-cpp-f-inl1-512y":{"avg":0.155737,"median":0.155737,"min":0.155737,"max":0.155737,"count":1},"ggttg-sa-cpp-d-inl0-512z":{"avg":0.072299,"median":0.072299,"min":0.072299,"max":0.072299,"count":1},"ggttg-sa-cpp-d-inl1-512z":{"avg":0.064907,"median":0.064907,"min":0.064907,"max":0.064907,"count":1},"ggttg-sa-cpp-f-inl0-512z":{"avg":0.150435,"median":0.150435,"min":0.150435,"max":0.150435,"count":1},"ggttg-sa-cpp-f-inl1-512z":{"avg":0.115494,"median":0.115494,"min":0.115494,"max":0.115494,"count":1},"ggttgg-sa-cuda-d-inl0":{"avg":0.055457,"median":0.055457,"min":0.055457,"max":0.055457,"count":1},"ggttgg-sa-cuda-d-inl1":{"avg":0.06155,"median":0.06155,"min":0.06155,"max":0.06155,"count":1},"ggttgg-sa-cuda-f-inl0":{"avg":0.307607,"median":0.307607,"min":0.307607,"max":0.307607,"count":1},"ggttgg-sa-cuda-f-inl1":{"avg":0.265562,"median":0.265562,"min":0.265562,"max":0.265562,"count":1},"ggttgg-sa-cpp-d-inl0-best":{"avg":0.007551,"median":0.007551,"min":0.007551,"max":0.007551,"count":1},"ggttgg-sa-cpp-d-inl0-none":{"avg":0.001745,"median":0.001745,"min":0.001745,"max":0.001745,"count":1},"ggttgg-sa-cpp-d-inl1-best":{"avg":0.006898,"median":0.006898,"min":0.006898,"max":0.006898,"count":1},"ggttgg-sa-cpp-d-inl1-none":{"avg":0.000386,"median":0.000386,"min":0.000386,"max":0.000386,"count":1},"ggttgg-sa-cpp-f-inl0-best":{"avg":0.015008,"median":0.015008,"min":0.015008,"max":0.015008,"count":1},"ggttgg-sa-cpp-f-inl0-none":{"avg":0.001827,"median":0.001827,"min":0.001827,"max":0.001827,"count":1},"ggttgg-sa-cpp-f-inl1-best":{"avg":0.013485,"median":0.013485,"min":0.013485,"max":0.013485,"count":1},"ggttgg-sa-cpp-f-inl1-none":{"avg":0.000499,"median":0.000499,"min":0.000499,"max":0.000499,"count":1},"ggttgg-sa-cpp-d-inl0-sse4":{"avg":0.003351,"median":0.003351,"min":0.003351,"max":0.003351,"count":1},"ggttgg-sa-cpp-d-inl1-sse4":{"avg":0.002775,"median":0.002775,"min":0.002775,"max":0.002775,"count":1},"ggttgg-sa-cpp-f-inl0-sse4":{"avg":0.006906,"median":0.006906,"min":0.006906,"max":0.006906,"count":1},"ggttgg-sa-cpp-f-inl1-sse4":{"avg":0.006083,"median":0.006083,"min":0.006083,"max":0.006083,"count":1},"ggttgg-sa-cpp-d-inl0-avx2":{"avg":0.006676,"median":0.006676,"min":0.006676,"max":0.006676,"count":1},"ggttgg-sa-cpp-d-inl1-avx2":{"avg":0.005454,"median":0.005454,"min":0.005454,"max":0.005454,"count":1},"ggttgg-sa-cpp-f-inl0-avx2":{"avg":0.013386,"median":0.013386,"min":0.013386,"max":0.013386,"count":1},"ggttgg-sa-cpp-f-inl1-avx2":{"avg":0.010666,"median":0.010666,"min":0.010666,"max":0.010666,"count":1},"ggttgg-sa-cpp-d-inl0-512y":{"avg":0.007551,"median":0.007551,"min":0.007551,"max":0.007551,"count":1},"ggttgg-sa-cpp-d-inl1-512y":{"avg":0.006898,"median":0.006898,"min":0.006898,"max":0.006898,"count":1},"ggttgg-sa-cpp-f-inl0-512y":{"avg":0.015008,"median":0.015008,"min":0.015008,"max":0.015008,"count":1},"ggttgg-sa-cpp-f-inl1-512y":{"avg":0.013485,"median":0.013485,"min":0.013485,"max":0.013485,"count":1},"ggttgg-sa-cpp-d-inl0-512z":{"avg":0.006376,"median":0.006376,"min":0.006376,"max":0.006376,"count":1},"ggttgg-sa-cpp-d-inl1-512z":{"avg":0.006534,"median":0.006534,"min":0.006534,"max":0.006534,"count":1},"ggttgg-sa-cpp-f-inl0-512z":{"avg":0.013083,"median":0.013083,"min":0.013083,"max":0.013083,"count":1},"ggttgg-sa-cpp-f-inl1-512z":{"avg":0.012661,"median":0.012661,"min":0.012661,"max":0.012661,"count":1}},"log":"ok"},"app":{"version":"ci-v0.7","description":"Madgraph5_aMCatNLO madgraph4gpu benchmark (2022)","cvmfs_checksum":"70fb8b581609b9e1f7dde9c41d8cd73f","bmkdata_checksum":"d4c9152ed732e012ca54b6518bf3de93","bmk_checksum":"1b9db5695b5654135a84207bfe143df2","containment":"docker"}}
+{"run_info":{"copies":1,"threads_per_copy":1,"events_per_thread":2,"extra_arguments":"--both -eemumu -ggtt -ggttg -ggttgg -dbl -flt -inl0 -inl1"},"report":{"wl-scores":{"eemumu-sa-cuda-d-inl0":48.79672,"eemumu-sa-cuda-d-inl1":49.58971,"eemumu-sa-cuda-f-inl0":1485.295,"eemumu-sa-cuda-f-inl1":1420.555,"eemumu-sa-cpp-d-inl0-best":5.85542,"eemumu-sa-cpp-d-inl0-none":1.60346,"eemumu-sa-cpp-d-inl1-best":11.02532,"eemumu-sa-cpp-d-inl1-none":4.669919,"eemumu-sa-cpp-f-inl0-best":12.28219,"eemumu-sa-cpp-f-inl0-none":1.662875,"eemumu-sa-cpp-f-inl1-best":27.95492,"eemumu-sa-cpp-f-inl1-none":4.952863,"eemumu-sa-cpp-d-inl0-sse4":3.070359,"eemumu-sa-cpp-d-inl1-sse4":8.24349,"eemumu-sa-cpp-f-inl0-sse4":6.108306,"eemumu-sa-cpp-f-inl1-sse4":14.71368,"eemumu-sa-cpp-d-inl0-avx2":5.434791,"eemumu-sa-cpp-d-inl1-avx2":11.02532,"eemumu-sa-cpp-f-inl0-avx2":11.37094,"eemumu-sa-cpp-f-inl1-avx2":27.61771,"eemumu-sa-cpp-d-inl0-512y":5.85542,"eemumu-sa-cpp-d-inl1-512y":10.94437,"eemumu-sa-cpp-f-inl0-512y":12.28219,"eemumu-sa-cpp-f-inl1-512y":27.95492,"eemumu-sa-cpp-d-inl0-512z":4.919846,"eemumu-sa-cpp-d-inl1-512z":9.140349,"eemumu-sa-cpp-f-inl0-512z":10.05686,"eemumu-sa-cpp-f-inl1-512z":20.54445,"ggtt-sa-cuda-d-inl0":5.745921,"ggtt-sa-cuda-d-inl1":5.897079,"ggtt-sa-cuda-f-inl0":175.4402,"ggtt-sa-cuda-f-inl1":170.835,"ggtt-sa-cpp-d-inl0-best":0.625262,"ggtt-sa-cpp-d-inl0-none":0.191705,"ggtt-sa-cpp-d-inl1-best":0.481277,"ggtt-sa-cpp-d-inl1-none":0.233871,"ggtt-sa-cpp-f-inl0-best":1.115452,"ggtt-sa-cpp-f-inl0-none":0.200632,"ggtt-sa-cpp-f-inl1-best":0.717432,"ggtt-sa-cpp-f-inl1-none":0.243362,"ggtt-sa-cpp-d-inl0-sse4":0.322312,"ggtt-sa-cpp-d-inl1-sse4":0.278407,"ggtt-sa-cpp-f-inl0-sse4":0.478232,"ggtt-sa-cpp-f-inl1-sse4":0.562256,"ggtt-sa-cpp-d-inl0-avx2":0.559118,"ggtt-sa-cpp-d-inl1-avx2":0.461578,"ggtt-sa-cpp-f-inl0-avx2":1.038209,"ggtt-sa-cpp-f-inl1-avx2":0.717164,"ggtt-sa-cpp-d-inl0-512y":0.625262,"ggtt-sa-cpp-d-inl1-512y":0.481277,"ggtt-sa-cpp-f-inl0-512y":1.115452,"ggtt-sa-cpp-f-inl1-512y":0.717432,"ggtt-sa-cpp-d-inl0-512z":0.374524,"ggtt-sa-cpp-d-inl1-512z":0.347206,"ggtt-sa-cpp-f-inl0-512z":0.781307,"ggtt-sa-cpp-f-inl1-512z":0.564741,"ggttg-sa-cuda-d-inl0":0.818309,"ggttg-sa-cuda-d-inl1":0.818317,"ggttg-sa-cuda-f-inl0":18.42414,"ggttg-sa-cuda-f-inl1":18.37018,"ggttg-sa-cpp-d-inl0-best":0.100087,"ggttg-sa-cpp-d-inl0-none":0.023867,"ggttg-sa-cpp-d-inl1-best":0.089018,"ggttg-sa-cpp-d-inl1-none":0.006266,"ggttg-sa-cpp-f-inl0-best":0.197983,"ggttg-sa-cpp-f-inl0-none":0.024443,"ggttg-sa-cpp-f-inl1-best":0.155876,"ggttg-sa-cpp-f-inl1-none":0.010211,"ggttg-sa-cpp-d-inl0-sse4":0.044909,"ggttg-sa-cpp-d-inl1-sse4":0.041899,"ggttg-sa-cpp-f-inl0-sse4":0.082025,"ggttg-sa-cpp-f-inl1-sse4":0.087215,"ggttg-sa-cpp-d-inl0-avx2":0.087359,"ggttg-sa-cpp-d-inl1-avx2":0.08088,"ggttg-sa-cpp-f-inl0-avx2":0.174366,"ggttg-sa-cpp-f-inl1-avx2":0.140372,"ggttg-sa-cpp-d-inl0-512y":0.100087,"ggttg-sa-cpp-d-inl1-512y":0.089018,"ggttg-sa-cpp-f-inl0-512y":0.197983,"ggttg-sa-cpp-f-inl1-512y":0.155876,"ggttg-sa-cpp-d-inl0-512z":0.072352,"ggttg-sa-cpp-d-inl1-512z":0.064912,"ggttg-sa-cpp-f-inl0-512z":0.150358,"ggttg-sa-cpp-f-inl1-512z":0.115493,"ggttgg-sa-cuda-d-inl0":0.055489,"ggttgg-sa-cuda-d-inl1":0.062788,"ggttgg-sa-cuda-f-inl0":0.308794,"ggttgg-sa-cuda-f-inl1":0.263863,"ggttgg-sa-cpp-d-inl0-best":0.007537,"ggttgg-sa-cpp-d-inl0-none":0.001743,"ggttgg-sa-cpp-d-inl1-best":0.006903,"ggttgg-sa-cpp-d-inl1-none":0.000386,"ggttgg-sa-cpp-f-inl0-best":0.014863,"ggttgg-sa-cpp-f-inl0-none":0.001829,"ggttgg-sa-cpp-f-inl1-best":0.013425,"ggttgg-sa-cpp-f-inl1-none":0.000499,"ggttgg-sa-cpp-d-inl0-sse4":0.00335,"ggttgg-sa-cpp-d-inl1-sse4":0.002792,"ggttgg-sa-cpp-f-inl0-sse4":0.006907,"ggttgg-sa-cpp-f-inl1-sse4":0.006093,"ggttgg-sa-cpp-d-inl0-avx2":0.006673,"ggttgg-sa-cpp-d-inl1-avx2":0.00545,"ggttgg-sa-cpp-f-inl0-avx2":0.013348,"ggttgg-sa-cpp-f-inl1-avx2":0.010681,"ggttgg-sa-cpp-d-inl0-512y":0.007537,"ggttgg-sa-cpp-d-inl1-512y":0.006903,"ggttgg-sa-cpp-f-inl0-512y":0.014863,"ggttgg-sa-cpp-f-inl1-512y":0.013425,"ggttgg-sa-cpp-d-inl0-512z":0.006486,"ggttgg-sa-cpp-d-inl1-512z":0.006547,"ggttgg-sa-cpp-f-inl0-512z":0.013055,"ggttgg-sa-cpp-f-inl1-512z":0.012701},"wl-stats":{"eemumu-sa-cuda-d-inl0":{"avg":48.79672,"median":48.79672,"min":48.79672,"max":48.79672,"count":1},"eemumu-sa-cuda-d-inl1":{"avg":49.58971,"median":49.58971,"min":49.58971,"max":49.58971,"count":1},"eemumu-sa-cuda-f-inl0":{"avg":1485.295,"median":1485.295,"min":1485.295,"max":1485.295,"count":1},"eemumu-sa-cuda-f-inl1":{"avg":1420.555,"median":1420.555,"min":1420.555,"max":1420.555,"count":1},"eemumu-sa-cpp-d-inl0-best":{"avg":5.85542,"median":5.85542,"min":5.85542,"max":5.85542,"count":1},"eemumu-sa-cpp-d-inl0-none":{"avg":1.60346,"median":1.60346,"min":1.60346,"max":1.60346,"count":1},"eemumu-sa-cpp-d-inl1-best":{"avg":11.02532,"median":11.02532,"min":11.02532,"max":11.02532,"count":1},"eemumu-sa-cpp-d-inl1-none":{"avg":4.669919,"median":4.669919,"min":4.669919,"max":4.669919,"count":1},"eemumu-sa-cpp-f-inl0-best":{"avg":12.28219,"median":12.28219,"min":12.28219,"max":12.28219,"count":1},"eemumu-sa-cpp-f-inl0-none":{"avg":1.662875,"median":1.662875,"min":1.662875,"max":1.662875,"count":1},"eemumu-sa-cpp-f-inl1-best":{"avg":27.95492,"median":27.95492,"min":27.95492,"max":27.95492,"count":1},"eemumu-sa-cpp-f-inl1-none":{"avg":4.952863,"median":4.952863,"min":4.952863,"max":4.952863,"count":1},"eemumu-sa-cpp-d-inl0-sse4":{"avg":3.070359,"median":3.070359,"min":3.070359,"max":3.070359,"count":1},"eemumu-sa-cpp-d-inl1-sse4":{"avg":8.24349,"median":8.24349,"min":8.24349,"max":8.24349,"count":1},"eemumu-sa-cpp-f-inl0-sse4":{"avg":6.108306,"median":6.108306,"min":6.108306,"max":6.108306,"count":1},"eemumu-sa-cpp-f-inl1-sse4":{"avg":14.71368,"median":14.71368,"min":14.71368,"max":14.71368,"count":1},"eemumu-sa-cpp-d-inl0-avx2":{"avg":5.434791,"median":5.434791,"min":5.434791,"max":5.434791,"count":1},"eemumu-sa-cpp-d-inl1-avx2":{"avg":11.02532,"median":11.02532,"min":11.02532,"max":11.02532,"count":1},"eemumu-sa-cpp-f-inl0-avx2":{"avg":11.37094,"median":11.37094,"min":11.37094,"max":11.37094,"count":1},"eemumu-sa-cpp-f-inl1-avx2":{"avg":27.61771,"median":27.61771,"min":27.61771,"max":27.61771,"count":1},"eemumu-sa-cpp-d-inl0-512y":{"avg":5.85542,"median":5.85542,"min":5.85542,"max":5.85542,"count":1},"eemumu-sa-cpp-d-inl1-512y":{"avg":10.94437,"median":10.94437,"min":10.94437,"max":10.94437,"count":1},"eemumu-sa-cpp-f-inl0-512y":{"avg":12.28219,"median":12.28219,"min":12.28219,"max":12.28219,"count":1},"eemumu-sa-cpp-f-inl1-512y":{"avg":27.95492,"median":27.95492,"min":27.95492,"max":27.95492,"count":1},"eemumu-sa-cpp-d-inl0-512z":{"avg":4.919846,"median":4.919846,"min":4.919846,"max":4.919846,"count":1},"eemumu-sa-cpp-d-inl1-512z":{"avg":9.140349,"median":9.140349,"min":9.140349,"max":9.140349,"count":1},"eemumu-sa-cpp-f-inl0-512z":{"avg":10.05686,"median":10.05686,"min":10.05686,"max":10.05686,"count":1},"eemumu-sa-cpp-f-inl1-512z":{"avg":20.54445,"median":20.54445,"min":20.54445,"max":20.54445,"count":1},"ggtt-sa-cuda-d-inl0":{"avg":5.745921,"median":5.745921,"min":5.745921,"max":5.745921,"count":1},"ggtt-sa-cuda-d-inl1":{"avg":5.897079,"median":5.897079,"min":5.897079,"max":5.897079,"count":1},"ggtt-sa-cuda-f-inl0":{"avg":175.4402,"median":175.4402,"min":175.4402,"max":175.4402,"count":1},"ggtt-sa-cuda-f-inl1":{"avg":170.835,"median":170.835,"min":170.835,"max":170.835,"count":1},"ggtt-sa-cpp-d-inl0-best":{"avg":0.625262,"median":0.625262,"min":0.625262,"max":0.625262,"count":1},"ggtt-sa-cpp-d-inl0-none":{"avg":0.191705,"median":0.191705,"min":0.191705,"max":0.191705,"count":1},"ggtt-sa-cpp-d-inl1-best":{"avg":0.481277,"median":0.481277,"min":0.481277,"max":0.481277,"count":1},"ggtt-sa-cpp-d-inl1-none":{"avg":0.233871,"median":0.233871,"min":0.233871,"max":0.233871,"count":1},"ggtt-sa-cpp-f-inl0-best":{"avg":1.115452,"median":1.115452,"min":1.115452,"max":1.115452,"count":1},"ggtt-sa-cpp-f-inl0-none":{"avg":0.200632,"median":0.200632,"min":0.200632,"max":0.200632,"count":1},"ggtt-sa-cpp-f-inl1-best":{"avg":0.717432,"median":0.717432,"min":0.717432,"max":0.717432,"count":1},"ggtt-sa-cpp-f-inl1-none":{"avg":0.243362,"median":0.243362,"min":0.243362,"max":0.243362,"count":1},"ggtt-sa-cpp-d-inl0-sse4":{"avg":0.322312,"median":0.322312,"min":0.322312,"max":0.322312,"count":1},"ggtt-sa-cpp-d-inl1-sse4":{"avg":0.278407,"median":0.278407,"min":0.278407,"max":0.278407,"count":1},"ggtt-sa-cpp-f-inl0-sse4":{"avg":0.478232,"median":0.478232,"min":0.478232,"max":0.478232,"count":1},"ggtt-sa-cpp-f-inl1-sse4":{"avg":0.562256,"median":0.562256,"min":0.562256,"max":0.562256,"count":1},"ggtt-sa-cpp-d-inl0-avx2":{"avg":0.559118,"median":0.559118,"min":0.559118,"max":0.559118,"count":1},"ggtt-sa-cpp-d-inl1-avx2":{"avg":0.461578,"median":0.461578,"min":0.461578,"max":0.461578,"count":1},"ggtt-sa-cpp-f-inl0-avx2":{"avg":1.038209,"median":1.038209,"min":1.038209,"max":1.038209,"count":1},"ggtt-sa-cpp-f-inl1-avx2":{"avg":0.717164,"median":0.717164,"min":0.717164,"max":0.717164,"count":1},"ggtt-sa-cpp-d-inl0-512y":{"avg":0.625262,"median":0.625262,"min":0.625262,"max":0.625262,"count":1},"ggtt-sa-cpp-d-inl1-512y":{"avg":0.481277,"median":0.481277,"min":0.481277,"max":0.481277,"count":1},"ggtt-sa-cpp-f-inl0-512y":{"avg":1.115452,"median":1.115452,"min":1.115452,"max":1.115452,"count":1},"ggtt-sa-cpp-f-inl1-512y":{"avg":0.717432,"median":0.717432,"min":0.717432,"max":0.717432,"count":1},"ggtt-sa-cpp-d-inl0-512z":{"avg":0.374524,"median":0.374524,"min":0.374524,"max":0.374524,"count":1},"ggtt-sa-cpp-d-inl1-512z":{"avg":0.347206,"median":0.347206,"min":0.347206,"max":0.347206,"count":1},"ggtt-sa-cpp-f-inl0-512z":{"avg":0.781307,"median":0.781307,"min":0.781307,"max":0.781307,"count":1},"ggtt-sa-cpp-f-inl1-512z":{"avg":0.564741,"median":0.564741,"min":0.564741,"max":0.564741,"count":1},"ggttg-sa-cuda-d-inl0":{"avg":0.818309,"median":0.818309,"min":0.818309,"max":0.818309,"count":1},"ggttg-sa-cuda-d-inl1":{"avg":0.818317,"median":0.818317,"min":0.818317,"max":0.818317,"count":1},"ggttg-sa-cuda-f-inl0":{"avg":18.42414,"median":18.42414,"min":18.42414,"max":18.42414,"count":1},"ggttg-sa-cuda-f-inl1":{"avg":18.37018,"median":18.37018,"min":18.37018,"max":18.37018,"count":1},"ggttg-sa-cpp-d-inl0-best":{"avg":0.100087,"median":0.100087,"min":0.100087,"max":0.100087,"count":1},"ggttg-sa-cpp-d-inl0-none":{"avg":0.023867,"median":0.023867,"min":0.023867,"max":0.023867,"count":1},"ggttg-sa-cpp-d-inl1-best":{"avg":0.089018,"median":0.089018,"min":0.089018,"max":0.089018,"count":1},"ggttg-sa-cpp-d-inl1-none":{"avg":0.006266,"median":0.006266,"min":0.006266,"max":0.006266,"count":1},"ggttg-sa-cpp-f-inl0-best":{"avg":0.197983,"median":0.197983,"min":0.197983,"max":0.197983,"count":1},"ggttg-sa-cpp-f-inl0-none":{"avg":0.024443,"median":0.024443,"min":0.024443,"max":0.024443,"count":1},"ggttg-sa-cpp-f-inl1-best":{"avg":0.155876,"median":0.155876,"min":0.155876,"max":0.155876,"count":1},"ggttg-sa-cpp-f-inl1-none":{"avg":0.010211,"median":0.010211,"min":0.010211,"max":0.010211,"count":1},"ggttg-sa-cpp-d-inl0-sse4":{"avg":0.044909,"median":0.044909,"min":0.044909,"max":0.044909,"count":1},"ggttg-sa-cpp-d-inl1-sse4":{"avg":0.041899,"median":0.041899,"min":0.041899,"max":0.041899,"count":1},"ggttg-sa-cpp-f-inl0-sse4":{"avg":0.082025,"median":0.082025,"min":0.082025,"max":0.082025,"count":1},"ggttg-sa-cpp-f-inl1-sse4":{"avg":0.087215,"median":0.087215,"min":0.087215,"max":0.087215,"count":1},"ggttg-sa-cpp-d-inl0-avx2":{"avg":0.087359,"median":0.087359,"min":0.087359,"max":0.087359,"count":1},"ggttg-sa-cpp-d-inl1-avx2":{"avg":0.08088,"median":0.08088,"min":0.08088,"max":0.08088,"count":1},"ggttg-sa-cpp-f-inl0-avx2":{"avg":0.174366,"median":0.174366,"min":0.174366,"max":0.174366,"count":1},"ggttg-sa-cpp-f-inl1-avx2":{"avg":0.140372,"median":0.140372,"min":0.140372,"max":0.140372,"count":1},"ggttg-sa-cpp-d-inl0-512y":{"avg":0.100087,"median":0.100087,"min":0.100087,"max":0.100087,"count":1},"ggttg-sa-cpp-d-inl1-512y":{"avg":0.089018,"median":0.089018,"min":0.089018,"max":0.089018,"count":1},"ggttg-sa-cpp-f-inl0-512y":{"avg":0.197983,"median":0.197983,"min":0.197983,"max":0.197983,"count":1},"ggttg-sa-cpp-f-inl1-512y":{"avg":0.155876,"median":0.155876,"min":0.155876,"max":0.155876,"count":1},"ggttg-sa-cpp-d-inl0-512z":{"avg":0.072352,"median":0.072352,"min":0.072352,"max":0.072352,"count":1},"ggttg-sa-cpp-d-inl1-512z":{"avg":0.064912,"median":0.064912,"min":0.064912,"max":0.064912,"count":1},"ggttg-sa-cpp-f-inl0-512z":{"avg":0.150358,"median":0.150358,"min":0.150358,"max":0.150358,"count":1},"ggttg-sa-cpp-f-inl1-512z":{"avg":0.115493,"median":0.115493,"min":0.115493,"max":0.115493,"count":1},"ggttgg-sa-cuda-d-inl0":{"avg":0.055489,"median":0.055489,"min":0.055489,"max":0.055489,"count":1},"ggttgg-sa-cuda-d-inl1":{"avg":0.062788,"median":0.062788,"min":0.062788,"max":0.062788,"count":1},"ggttgg-sa-cuda-f-inl0":{"avg":0.308794,"median":0.308794,"min":0.308794,"max":0.308794,"count":1},"ggttgg-sa-cuda-f-inl1":{"avg":0.263863,"median":0.263863,"min":0.263863,"max":0.263863,"count":1},"ggttgg-sa-cpp-d-inl0-best":{"avg":0.007537,"median":0.007537,"min":0.007537,"max":0.007537,"count":1},"ggttgg-sa-cpp-d-inl0-none":{"avg":0.001743,"median":0.001743,"min":0.001743,"max":0.001743,"count":1},"ggttgg-sa-cpp-d-inl1-best":{"avg":0.006903,"median":0.006903,"min":0.006903,"max":0.006903,"count":1},"ggttgg-sa-cpp-d-inl1-none":{"avg":0.000386,"median":0.000386,"min":0.000386,"max":0.000386,"count":1},"ggttgg-sa-cpp-f-inl0-best":{"avg":0.014863,"median":0.014863,"min":0.014863,"max":0.014863,"count":1},"ggttgg-sa-cpp-f-inl0-none":{"avg":0.001829,"median":0.001829,"min":0.001829,"max":0.001829,"count":1},"ggttgg-sa-cpp-f-inl1-best":{"avg":0.013425,"median":0.013425,"min":0.013425,"max":0.013425,"count":1},"ggttgg-sa-cpp-f-inl1-none":{"avg":0.000499,"median":0.000499,"min":0.000499,"max":0.000499,"count":1},"ggttgg-sa-cpp-d-inl0-sse4":{"avg":0.00335,"median":0.00335,"min":0.00335,"max":0.00335,"count":1},"ggttgg-sa-cpp-d-inl1-sse4":{"avg":0.002792,"median":0.002792,"min":0.002792,"max":0.002792,"count":1},"ggttgg-sa-cpp-f-inl0-sse4":{"avg":0.006907,"median":0.006907,"min":0.006907,"max":0.006907,"count":1},"ggttgg-sa-cpp-f-inl1-sse4":{"avg":0.006093,"median":0.006093,"min":0.006093,"max":0.006093,"count":1},"ggttgg-sa-cpp-d-inl0-avx2":{"avg":0.006673,"median":0.006673,"min":0.006673,"max":0.006673,"count":1},"ggttgg-sa-cpp-d-inl1-avx2":{"avg":0.00545,"median":0.00545,"min":0.00545,"max":0.00545,"count":1},"ggttgg-sa-cpp-f-inl0-avx2":{"avg":0.013348,"median":0.013348,"min":0.013348,"max":0.013348,"count":1},"ggttgg-sa-cpp-f-inl1-avx2":{"avg":0.010681,"median":0.010681,"min":0.010681,"max":0.010681,"count":1},"ggttgg-sa-cpp-d-inl0-512y":{"avg":0.007537,"median":0.007537,"min":0.007537,"max":0.007537,"count":1},"ggttgg-sa-cpp-d-inl1-512y":{"avg":0.006903,"median":0.006903,"min":0.006903,"max":0.006903,"count":1},"ggttgg-sa-cpp-f-inl0-512y":{"avg":0.014863,"median":0.014863,"min":0.014863,"max":0.014863,"count":1},"ggttgg-sa-cpp-f-inl1-512y":{"avg":0.013425,"median":0.013425,"min":0.013425,"max":0.013425,"count":1},"ggttgg-sa-cpp-d-inl0-512z":{"avg":0.006486,"median":0.006486,"min":0.006486,"max":0.006486,"count":1},"ggttgg-sa-cpp-d-inl1-512z":{"avg":0.006547,"median":0.006547,"min":0.006547,"max":0.006547,"count":1},"ggttgg-sa-cpp-f-inl0-512z":{"avg":0.013055,"median":0.013055,"min":0.013055,"max":0.013055,"count":1},"ggttgg-sa-cpp-f-inl1-512z":{"avg":0.012701,"median":0.012701,"min":0.012701,"max":0.012701,"count":1}},"log":"ok"},"app":{"version":"ci-v0.7","description":"Madgraph5_aMCatNLO madgraph4gpu benchmark (2022)","cvmfs_checksum":"34ff738c57b9b7a8a398e4769cba101d","bmkdata_checksum":"d4c9152ed732e012ca54b6518bf3de93","bmk_checksum":"3c9f62f161ec52296be50b21648606b0","containment":"docker"}}
     "copies": 1,
-{"run_info":{"copies":1,"threads_per_copy":1,"events_per_thread":2,"extra_arguments":"--both -eemumu -ggtt -ggttg -ggttgg -dbl -flt -inl0 -inl1"},"report":{"wl-scores":{"eemumu-sa-cuda-d-inl0":1091.498,"eemumu-sa-cuda-d-inl1":1122.856,"eemumu-sa-cuda-f-inl0":3117.898,"eemumu-sa-cuda-f-inl1":3135.858,"eemumu-sa-cpp-d-inl0-best":5.8358,"eemumu-sa-cpp-d-inl0-none":1.6042,"eemumu-sa-cpp-d-inl1-best":10.3635,"eemumu-sa-cpp-d-inl1-none":4.652,"eemumu-sa-cpp-f-inl0-best":12.0673,"eemumu-sa-cpp-f-inl0-none":1.6561,"eemumu-sa-cpp-f-inl1-best":25.4627,"eemumu-sa-cpp-f-inl1-none":4.9386,"eemumu-sa-cpp-d-inl0-sse4":3.0609,"eemumu-sa-cpp-d-inl1-sse4":7.9346,"eemumu-sa-cpp-f-inl0-sse4":6.0965,"eemumu-sa-cpp-f-inl1-sse4":14.4209,"eemumu-sa-cpp-d-inl0-avx2":5.3773,"eemumu-sa-cpp-d-inl1-avx2":10.3635,"eemumu-sa-cpp-f-inl0-avx2":11.2146,"eemumu-sa-cpp-f-inl1-avx2":25.155,"eemumu-sa-cpp-d-inl0-512y":5.8358,"eemumu-sa-cpp-d-inl1-512y":10.3365,"eemumu-sa-cpp-f-inl0-512y":12.0673,"eemumu-sa-cpp-f-inl1-512y":25.4627,"eemumu-sa-cpp-d-inl0-512z":4.7149,"eemumu-sa-cpp-d-inl1-512z":8.6689,"eemumu-sa-cpp-f-inl0-512z":9.7054,"eemumu-sa-cpp-f-inl1-512z":18.9992,"ggtt-sa-cuda-d-inl0":130.7186,"ggtt-sa-cuda-d-inl1":130.2199,"ggtt-sa-cuda-f-inl0":365.0114,"ggtt-sa-cuda-f-inl1":361.8056,"ggtt-sa-cpp-d-inl0-best":0.6225,"ggtt-sa-cpp-d-inl0-none":0.1909,"ggtt-sa-cpp-d-inl1-best":0.4712,"ggtt-sa-cpp-d-inl1-none":0.2329,"ggtt-sa-cpp-f-inl0-best":1.1131,"ggtt-sa-cpp-f-inl0-none":0.1999,"ggtt-sa-cpp-f-inl1-best":0.7113,"ggtt-sa-cpp-f-inl1-none":0.2424,"ggtt-sa-cpp-d-inl0-sse4":0.3206,"ggtt-sa-cpp-d-inl1-sse4":0.2764,"ggtt-sa-cpp-f-inl0-sse4":0.4737,"ggtt-sa-cpp-f-inl1-sse4":0.5593,"ggtt-sa-cpp-d-inl0-avx2":0.5589,"ggtt-sa-cpp-d-inl1-avx2":0.4569,"ggtt-sa-cpp-f-inl0-avx2":1.0321,"ggtt-sa-cpp-f-inl1-avx2":0.7101,"ggtt-sa-cpp-d-inl0-512y":0.6225,"ggtt-sa-cpp-d-inl1-512y":0.4712,"ggtt-sa-cpp-f-inl0-512y":1.1131,"ggtt-sa-cpp-f-inl1-512y":0.7113,"ggtt-sa-cpp-d-inl0-512z":0.3731,"ggtt-sa-cpp-d-inl1-512z":0.3441,"ggtt-sa-cpp-f-inl0-512z":0.7779,"ggtt-sa-cpp-f-inl1-512z":0.5654,"ggttg-sa-cuda-d-inl0":13.4947,"ggttg-sa-cuda-d-inl1":13.5324,"ggttg-sa-cuda-f-inl0":45.6693,"ggttg-sa-cuda-f-inl1":45.5015,"ggttg-sa-cpp-d-inl0-best":0.0999,"ggttg-sa-cpp-d-inl0-none":0.0238,"ggttg-sa-cpp-d-inl1-best":0.0888,"ggttg-sa-cpp-d-inl1-none":0.0063,"ggttg-sa-cpp-f-inl0-best":0.1967,"ggttg-sa-cpp-f-inl0-none":0.0244,"ggttg-sa-cpp-f-inl1-best":0.1556,"ggttg-sa-cpp-f-inl1-none":0.0102,"ggttg-sa-cpp-d-inl0-sse4":0.0446,"ggttg-sa-cpp-d-inl1-sse4":0.0418,"ggttg-sa-cpp-f-inl0-sse4":0.0819,"ggttg-sa-cpp-f-inl1-sse4":0.087,"ggttg-sa-cpp-d-inl0-avx2":0.0872,"ggttg-sa-cpp-d-inl1-avx2":0.0807,"ggttg-sa-cpp-f-inl0-avx2":0.1745,"ggttg-sa-cpp-f-inl1-avx2":0.14,"ggttg-sa-cpp-d-inl0-512y":0.0999,"ggttg-sa-cpp-d-inl1-512y":0.0888,"ggttg-sa-cpp-f-inl0-512y":0.1967,"ggttg-sa-cpp-f-inl1-512y":0.1556,"ggttg-sa-cpp-d-inl0-512z":0.0722,"ggttg-sa-cpp-d-inl1-512z":0.0643,"ggttg-sa-cpp-f-inl0-512z":0.15,"ggttg-sa-cpp-f-inl1-512z":0.1141,"ggttgg-sa-cuda-d-inl0":0.4201,"ggttgg-sa-cuda-d-inl1":0.3867,"ggttgg-sa-cuda-f-inl0":0.8683,"ggttgg-sa-cuda-f-inl1":0.7818,"ggttgg-sa-cpp-d-inl0-best":0.0075,"ggttgg-sa-cpp-d-inl0-none":0.0017,"ggttgg-sa-cpp-d-inl1-best":0.0069,"ggttgg-sa-cpp-d-inl1-none":0.0004,"ggttgg-sa-cpp-f-inl0-best":0.015,"ggttgg-sa-cpp-f-inl0-none":0.0018,"ggttgg-sa-cpp-f-inl1-best":0.0134,"ggttgg-sa-cpp-f-inl1-none":0.0005,"ggttgg-sa-cpp-d-inl0-sse4":0.0033,"ggttgg-sa-cpp-d-inl1-sse4":0.0028,"ggttgg-sa-cpp-f-inl0-sse4":0.0069,"ggttgg-sa-cpp-f-inl1-sse4":0.0061,"ggttgg-sa-cpp-d-inl0-avx2":0.0067,"ggttgg-sa-cpp-d-inl1-avx2":0.0054,"ggttgg-sa-cpp-f-inl0-avx2":0.0134,"ggttgg-sa-cpp-f-inl1-avx2":0.0106,"ggttgg-sa-cpp-d-inl0-512y":0.0075,"ggttgg-sa-cpp-d-inl1-512y":0.0069,"ggttgg-sa-cpp-f-inl0-512y":0.015,"ggttgg-sa-cpp-f-inl1-512y":0.0134,"ggttgg-sa-cpp-d-inl0-512z":0.0065,"ggttgg-sa-cpp-d-inl1-512z":0.0065,"ggttgg-sa-cpp-f-inl0-512z":0.013,"ggttgg-sa-cpp-f-inl1-512z":0.0126},"wl-stats":{"eemumu-sa-cuda-d-inl0":{"avg":1091.498,"median":1091.498,"min":1091.498,"max":1091.498,"count":1},"eemumu-sa-cuda-d-inl1":{"avg":1122.856,"median":1122.856,"min":1122.856,"max":1122.856,"count":1},"eemumu-sa-cuda-f-inl0":{"avg":3117.898,"median":3117.898,"min":3117.898,"max":3117.898,"count":1},"eemumu-sa-cuda-f-inl1":{"avg":3135.858,"median":3135.858,"min":3135.858,"max":3135.858,"count":1},"eemumu-sa-cpp-d-inl0-best":{"avg":5.8358,"median":5.8358,"min":5.8358,"max":5.8358,"count":1},"eemumu-sa-cpp-d-inl0-none":{"avg":1.6042,"median":1.6042,"min":1.6042,"max":1.6042,"count":1},"eemumu-sa-cpp-d-inl1-best":{"avg":10.3635,"median":10.3635,"min":10.3635,"max":10.3635,"count":1},"eemumu-sa-cpp-d-inl1-none":{"avg":4.652,"median":4.652,"min":4.652,"max":4.652,"count":1},"eemumu-sa-cpp-f-inl0-best":{"avg":12.0673,"median":12.0673,"min":12.0673,"max":12.0673,"count":1},"eemumu-sa-cpp-f-inl0-none":{"avg":1.6561,"median":1.6561,"min":1.6561,"max":1.6561,"count":1},"eemumu-sa-cpp-f-inl1-best":{"avg":25.4627,"median":25.4627,"min":25.4627,"max":25.4627,"count":1},"eemumu-sa-cpp-f-inl1-none":{"avg":4.9386,"median":4.9386,"min":4.9386,"max":4.9386,"count":1},"eemumu-sa-cpp-d-inl0-sse4":{"avg":3.0609,"median":3.0609,"min":3.0609,"max":3.0609,"count":1},"eemumu-sa-cpp-d-inl1-sse4":{"avg":7.9346,"median":7.9346,"min":7.9346,"max":7.9346,"count":1},"eemumu-sa-cpp-f-inl0-sse4":{"avg":6.0965,"median":6.0965,"min":6.0965,"max":6.0965,"count":1},"eemumu-sa-cpp-f-inl1-sse4":{"avg":14.4209,"median":14.4209,"min":14.4209,"max":14.4209,"count":1},"eemumu-sa-cpp-d-inl0-avx2":{"avg":5.3773,"median":5.3773,"min":5.3773,"max":5.3773,"count":1},"eemumu-sa-cpp-d-inl1-avx2":{"avg":10.3635,"median":10.3635,"min":10.3635,"max":10.3635,"count":1},"eemumu-sa-cpp-f-inl0-avx2":{"avg":11.2146,"median":11.2146,"min":11.2146,"max":11.2146,"count":1},"eemumu-sa-cpp-f-inl1-avx2":{"avg":25.155,"median":25.155,"min":25.155,"max":25.155,"count":1},"eemumu-sa-cpp-d-inl0-512y":{"avg":5.8358,"median":5.8358,"min":5.8358,"max":5.8358,"count":1},"eemumu-sa-cpp-d-inl1-512y":{"avg":10.3365,"median":10.3365,"min":10.3365,"max":10.3365,"count":1},"eemumu-sa-cpp-f-inl0-512y":{"avg":12.0673,"median":12.0673,"min":12.0673,"max":12.0673,"count":1},"eemumu-sa-cpp-f-inl1-512y":{"avg":25.4627,"median":25.4627,"min":25.4627,"max":25.4627,"count":1},"eemumu-sa-cpp-d-inl0-512z":{"avg":4.7149,"median":4.7149,"min":4.7149,"max":4.7149,"count":1},"eemumu-sa-cpp-d-inl1-512z":{"avg":8.6689,"median":8.6689,"min":8.6689,"max":8.6689,"count":1},"eemumu-sa-cpp-f-inl0-512z":{"avg":9.7054,"median":9.7054,"min":9.7054,"max":9.7054,"count":1},"eemumu-sa-cpp-f-inl1-512z":{"avg":18.9992,"median":18.9992,"min":18.9992,"max":18.9992,"count":1},"ggtt-sa-cuda-d-inl0":{"avg":130.7186,"median":130.7186,"min":130.7186,"max":130.7186,"count":1},"ggtt-sa-cuda-d-inl1":{"avg":130.2199,"median":130.2199,"min":130.2199,"max":130.2199,"count":1},"ggtt-sa-cuda-f-inl0":{"avg":365.0114,"median":365.0114,"min":365.0114,"max":365.0114,"count":1},"ggtt-sa-cuda-f-inl1":{"avg":361.8056,"median":361.8056,"min":361.8056,"max":361.8056,"count":1},"ggtt-sa-cpp-d-inl0-best":{"avg":0.6225,"median":0.6225,"min":0.6225,"max":0.6225,"count":1},"ggtt-sa-cpp-d-inl0-none":{"avg":0.1909,"median":0.1909,"min":0.1909,"max":0.1909,"count":1},"ggtt-sa-cpp-d-inl1-best":{"avg":0.4712,"median":0.4712,"min":0.4712,"max":0.4712,"count":1},"ggtt-sa-cpp-d-inl1-none":{"avg":0.2329,"median":0.2329,"min":0.2329,"max":0.2329,"count":1},"ggtt-sa-cpp-f-inl0-best":{"avg":1.1131,"median":1.1131,"min":1.1131,"max":1.1131,"count":1},"ggtt-sa-cpp-f-inl0-none":{"avg":0.1999,"median":0.1999,"min":0.1999,"max":0.1999,"count":1},"ggtt-sa-cpp-f-inl1-best":{"avg":0.7113,"median":0.7113,"min":0.7113,"max":0.7113,"count":1},"ggtt-sa-cpp-f-inl1-none":{"avg":0.2424,"median":0.2424,"min":0.2424,"max":0.2424,"count":1},"ggtt-sa-cpp-d-inl0-sse4":{"avg":0.3206,"median":0.3206,"min":0.3206,"max":0.3206,"count":1},"ggtt-sa-cpp-d-inl1-sse4":{"avg":0.2764,"median":0.2764,"min":0.2764,"max":0.2764,"count":1},"ggtt-sa-cpp-f-inl0-sse4":{"avg":0.4737,"median":0.4737,"min":0.4737,"max":0.4737,"count":1},"ggtt-sa-cpp-f-inl1-sse4":{"avg":0.5593,"median":0.5593,"min":0.5593,"max":0.5593,"count":1},"ggtt-sa-cpp-d-inl0-avx2":{"avg":0.5589,"median":0.5589,"min":0.5589,"max":0.5589,"count":1},"ggtt-sa-cpp-d-inl1-avx2":{"avg":0.4569,"median":0.4569,"min":0.4569,"max":0.4569,"count":1},"ggtt-sa-cpp-f-inl0-avx2":{"avg":1.0321,"median":1.0321,"min":1.0321,"max":1.0321,"count":1},"ggtt-sa-cpp-f-inl1-avx2":{"avg":0.7101,"median":0.7101,"min":0.7101,"max":0.7101,"count":1},"ggtt-sa-cpp-d-inl0-512y":{"avg":0.6225,"median":0.6225,"min":0.6225,"max":0.6225,"count":1},"ggtt-sa-cpp-d-inl1-512y":{"avg":0.4712,"median":0.4712,"min":0.4712,"max":0.4712,"count":1},"ggtt-sa-cpp-f-inl0-512y":{"avg":1.1131,"median":1.1131,"min":1.1131,"max":1.1131,"count":1},"ggtt-sa-cpp-f-inl1-512y":{"avg":0.7113,"median":0.7113,"min":0.7113,"max":0.7113,"count":1},"ggtt-sa-cpp-d-inl0-512z":{"avg":0.3731,"median":0.3731,"min":0.3731,"max":0.3731,"count":1},"ggtt-sa-cpp-d-inl1-512z":{"avg":0.3441,"median":0.3441,"min":0.3441,"max":0.3441,"count":1},"ggtt-sa-cpp-f-inl0-512z":{"avg":0.7779,"median":0.7779,"min":0.7779,"max":0.7779,"count":1},"ggtt-sa-cpp-f-inl1-512z":{"avg":0.5654,"median":0.5654,"min":0.5654,"max":0.5654,"count":1},"ggttg-sa-cuda-d-inl0":{"avg":13.4947,"median":13.4947,"min":13.4947,"max":13.4947,"count":1},"ggttg-sa-cuda-d-inl1":{"avg":13.5324,"median":13.5324,"min":13.5324,"max":13.5324,"count":1},"ggttg-sa-cuda-f-inl0":{"avg":45.6693,"median":45.6693,"min":45.6693,"max":45.6693,"count":1},"ggttg-sa-cuda-f-inl1":{"avg":45.5015,"median":45.5015,"min":45.5015,"max":45.5015,"count":1},"ggttg-sa-cpp-d-inl0-best":{"avg":0.0999,"median":0.0999,"min":0.0999,"max":0.0999,"count":1},"ggttg-sa-cpp-d-inl0-none":{"avg":0.0238,"median":0.0238,"min":0.0238,"max":0.0238,"count":1},"ggttg-sa-cpp-d-inl1-best":{"avg":0.0888,"median":0.0888,"min":0.0888,"max":0.0888,"count":1},"ggttg-sa-cpp-d-inl1-none":{"avg":0.0063,"median":0.0063,"min":0.0063,"max":0.0063,"count":1},"ggttg-sa-cpp-f-inl0-best":{"avg":0.1967,"median":0.1967,"min":0.1967,"max":0.1967,"count":1},"ggttg-sa-cpp-f-inl0-none":{"avg":0.0244,"median":0.0244,"min":0.0244,"max":0.0244,"count":1},"ggttg-sa-cpp-f-inl1-best":{"avg":0.1556,"median":0.1556,"min":0.1556,"max":0.1556,"count":1},"ggttg-sa-cpp-f-inl1-none":{"avg":0.0102,"median":0.0102,"min":0.0102,"max":0.0102,"count":1},"ggttg-sa-cpp-d-inl0-sse4":{"avg":0.0446,"median":0.0446,"min":0.0446,"max":0.0446,"count":1},"ggttg-sa-cpp-d-inl1-sse4":{"avg":0.0418,"median":0.0418,"min":0.0418,"max":0.0418,"count":1},"ggttg-sa-cpp-f-inl0-sse4":{"avg":0.0819,"median":0.0819,"min":0.0819,"max":0.0819,"count":1},"ggttg-sa-cpp-f-inl1-sse4":{"avg":0.087,"median":0.087,"min":0.087,"max":0.087,"count":1},"ggttg-sa-cpp-d-inl0-avx2":{"avg":0.0872,"median":0.0872,"min":0.0872,"max":0.0872,"count":1},"ggttg-sa-cpp-d-inl1-avx2":{"avg":0.0807,"median":0.0807,"min":0.0807,"max":0.0807,"count":1},"ggttg-sa-cpp-f-inl0-avx2":{"avg":0.1745,"median":0.1745,"min":0.1745,"max":0.1745,"count":1},"ggttg-sa-cpp-f-inl1-avx2":{"avg":0.14,"median":0.14,"min":0.14,"max":0.14,"count":1},"ggttg-sa-cpp-d-inl0-512y":{"avg":0.0999,"median":0.0999,"min":0.0999,"max":0.0999,"count":1},"ggttg-sa-cpp-d-inl1-512y":{"avg":0.0888,"median":0.0888,"min":0.0888,"max":0.0888,"count":1},"ggttg-sa-cpp-f-inl0-512y":{"avg":0.1967,"median":0.1967,"min":0.1967,"max":0.1967,"count":1},"ggttg-sa-cpp-f-inl1-512y":{"avg":0.1556,"median":0.1556,"min":0.1556,"max":0.1556,"count":1},"ggttg-sa-cpp-d-inl0-512z":{"avg":0.0722,"median":0.0722,"min":0.0722,"max":0.0722,"count":1},"ggttg-sa-cpp-d-inl1-512z":{"avg":0.0643,"median":0.0643,"min":0.0643,"max":0.0643,"count":1},"ggttg-sa-cpp-f-inl0-512z":{"avg":0.15,"median":0.15,"min":0.15,"max":0.15,"count":1},"ggttg-sa-cpp-f-inl1-512z":{"avg":0.1141,"median":0.1141,"min":0.1141,"max":0.1141,"count":1},"ggttgg-sa-cuda-d-inl0":{"avg":0.4201,"median":0.4201,"min":0.4201,"max":0.4201,"count":1},"ggttgg-sa-cuda-d-inl1":{"avg":0.3867,"median":0.3867,"min":0.3867,"max":0.3867,"count":1},"ggttgg-sa-cuda-f-inl0":{"avg":0.8683,"median":0.8683,"min":0.8683,"max":0.8683,"count":1},"ggttgg-sa-cuda-f-inl1":{"avg":0.7818,"median":0.7818,"min":0.7818,"max":0.7818,"count":1},"ggttgg-sa-cpp-d-inl0-best":{"avg":0.0075,"median":0.0075,"min":0.0075,"max":0.0075,"count":1},"ggttgg-sa-cpp-d-inl0-none":{"avg":0.0017,"median":0.0017,"min":0.0017,"max":0.0017,"count":1},"ggttgg-sa-cpp-d-inl1-best":{"avg":0.0069,"median":0.0069,"min":0.0069,"max":0.0069,"count":1},"ggttgg-sa-cpp-d-inl1-none":{"avg":0.0004,"median":0.0004,"min":0.0004,"max":0.0004,"count":1},"ggttgg-sa-cpp-f-inl0-best":{"avg":0.015,"median":0.015,"min":0.015,"max":0.015,"count":1},"ggttgg-sa-cpp-f-inl0-none":{"avg":0.0018,"median":0.0018,"min":0.0018,"max":0.0018,"count":1},"ggttgg-sa-cpp-f-inl1-best":{"avg":0.0134,"median":0.0134,"min":0.0134,"max":0.0134,"count":1},"ggttgg-sa-cpp-f-inl1-none":{"avg":0.0005,"median":0.0005,"min":0.0005,"max":0.0005,"count":1},"ggttgg-sa-cpp-d-inl0-sse4":{"avg":0.0033,"median":0.0033,"min":0.0033,"max":0.0033,"count":1},"ggttgg-sa-cpp-d-inl1-sse4":{"avg":0.0028,"median":0.0028,"min":0.0028,"max":0.0028,"count":1},"ggttgg-sa-cpp-f-inl0-sse4":{"avg":0.0069,"median":0.0069,"min":0.0069,"max":0.0069,"count":1},"ggttgg-sa-cpp-f-inl1-sse4":{"avg":0.0061,"median":0.0061,"min":0.0061,"max":0.0061,"count":1},"ggttgg-sa-cpp-d-inl0-avx2":{"avg":0.0067,"median":0.0067,"min":0.0067,"max":0.0067,"count":1},"ggttgg-sa-cpp-d-inl1-avx2":{"avg":0.0054,"median":0.0054,"min":0.0054,"max":0.0054,"count":1},"ggttgg-sa-cpp-f-inl0-avx2":{"avg":0.0134,"median":0.0134,"min":0.0134,"max":0.0134,"count":1},"ggttgg-sa-cpp-f-inl1-avx2":{"avg":0.0106,"median":0.0106,"min":0.0106,"max":0.0106,"count":1},"ggttgg-sa-cpp-d-inl0-512y":{"avg":0.0075,"median":0.0075,"min":0.0075,"max":0.0075,"count":1},"ggttgg-sa-cpp-d-inl1-512y":{"avg":0.0069,"median":0.0069,"min":0.0069,"max":0.0069,"count":1},"ggttgg-sa-cpp-f-inl0-512y":{"avg":0.015,"median":0.015,"min":0.015,"max":0.015,"count":1},"ggttgg-sa-cpp-f-inl1-512y":{"avg":0.0134,"median":0.0134,"min":0.0134,"max":0.0134,"count":1},"ggttgg-sa-cpp-d-inl0-512z":{"avg":0.0065,"median":0.0065,"min":0.0065,"max":0.0065,"count":1},"ggttgg-sa-cpp-d-inl1-512z":{"avg":0.0065,"median":0.0065,"min":0.0065,"max":0.0065,"count":1},"ggttgg-sa-cpp-f-inl0-512z":{"avg":0.013,"median":0.013,"min":0.013,"max":0.013,"count":1},"ggttgg-sa-cpp-f-inl1-512z":{"avg":0.0126,"median":0.0126,"min":0.0126,"max":0.0126,"count":1}},"log":"ok"},"app":{"version":"ci-v0.6","description":"Madgraph5_aMCatNLO madgraph4gpu benchmark (2022)","cvmfs_checksum":"e4f4430425242382df2def56875c4d4b","bmkdata_checksum":"4eb8273563af22b829ddbf985ae0b0a9","bmk_checksum":"7b36bbe13203a2c3938a20b58de6a563","containment":"singularity"}}
-{"run_info":{"copies":1,"threads_per_copy":1,"events_per_thread":2,"extra_arguments":"--both -eemumu -ggtt -ggttg -ggttgg -dbl -flt -inl0 -inl1"},"report":{"wl-scores":{"eemumu-sa-cuda-d-inl0":1130.432,"eemumu-sa-cuda-d-inl1":1128.067,"eemumu-sa-cuda-f-inl0":3036.306,"eemumu-sa-cuda-f-inl1":3029.1,"eemumu-sa-cpp-d-inl0-best":5.8463,"eemumu-sa-cpp-d-inl0-none":1.6029,"eemumu-sa-cpp-d-inl1-best":10.2311,"eemumu-sa-cpp-d-inl1-none":4.6502,"eemumu-sa-cpp-f-inl0-best":12.0628,"eemumu-sa-cpp-f-inl0-none":1.6559,"eemumu-sa-cpp-f-inl1-best":25.1426,"eemumu-sa-cpp-f-inl1-none":4.9364,"eemumu-sa-cpp-d-inl0-sse4":3.0622,"eemumu-sa-cpp-d-inl1-sse4":7.9254,"eemumu-sa-cpp-f-inl0-sse4":6.0888,"eemumu-sa-cpp-f-inl1-sse4":14.2969,"eemumu-sa-cpp-d-inl0-avx2":5.3727,"eemumu-sa-cpp-d-inl1-avx2":10.2311,"eemumu-sa-cpp-f-inl0-avx2":11.2383,"eemumu-sa-cpp-f-inl1-avx2":24.6208,"eemumu-sa-cpp-d-inl0-512y":5.8463,"eemumu-sa-cpp-d-inl1-512y":10.2161,"eemumu-sa-cpp-f-inl0-512y":12.0628,"eemumu-sa-cpp-f-inl1-512y":25.1426,"eemumu-sa-cpp-d-inl0-512z":4.743,"eemumu-sa-cpp-d-inl1-512z":8.5471,"eemumu-sa-cpp-f-inl0-512z":9.644,"eemumu-sa-cpp-f-inl1-512z":18.3169,"ggtt-sa-cuda-d-inl0":130.0122,"ggtt-sa-cuda-d-inl1":130.2486,"ggtt-sa-cuda-f-inl0":363.6906,"ggtt-sa-cuda-f-inl1":363.4642,"ggtt-sa-cpp-d-inl0-best":0.6213,"ggtt-sa-cpp-d-inl0-none":0.1912,"ggtt-sa-cpp-d-inl1-best":0.4756,"ggtt-sa-cpp-d-inl1-none":0.2335,"ggtt-sa-cpp-f-inl0-best":1.1129,"ggtt-sa-cpp-f-inl0-none":0.2,"ggtt-sa-cpp-f-inl1-best":0.7099,"ggtt-sa-cpp-f-inl1-none":0.2424,"ggtt-sa-cpp-d-inl0-sse4":0.3204,"ggtt-sa-cpp-d-inl1-sse4":0.2768,"ggtt-sa-cpp-f-inl0-sse4":0.4764,"ggtt-sa-cpp-f-inl1-sse4":0.5602,"ggtt-sa-cpp-d-inl0-avx2":0.5574,"ggtt-sa-cpp-d-inl1-avx2":0.4593,"ggtt-sa-cpp-f-inl0-avx2":1.0353,"ggtt-sa-cpp-f-inl1-avx2":0.7014,"ggtt-sa-cpp-d-inl0-512y":0.6213,"ggtt-sa-cpp-d-inl1-512y":0.4756,"ggtt-sa-cpp-f-inl0-512y":1.1129,"ggtt-sa-cpp-f-inl1-512y":0.7099,"ggtt-sa-cpp-d-inl0-512z":0.3732,"ggtt-sa-cpp-d-inl1-512z":0.3438,"ggtt-sa-cpp-f-inl0-512z":0.7762,"ggtt-sa-cpp-f-inl1-512z":0.5638,"ggttg-sa-cuda-d-inl0":13.4296,"ggttg-sa-cuda-d-inl1":13.4207,"ggttg-sa-cuda-f-inl0":45.8793,"ggttg-sa-cuda-f-inl1":45.5322,"ggttg-sa-cpp-d-inl0-best":0.1,"ggttg-sa-cpp-d-inl0-none":0.0238,"ggttg-sa-cpp-d-inl1-best":0.0889,"ggttg-sa-cpp-d-inl1-none":0.0063,"ggttg-sa-cpp-f-inl0-best":0.1974,"ggttg-sa-cpp-f-inl0-none":0.0244,"ggttg-sa-cpp-f-inl1-best":0.1555,"ggttg-sa-cpp-f-inl1-none":0.0102,"ggttg-sa-cpp-d-inl0-sse4":0.0448,"ggttg-sa-cpp-d-inl1-sse4":0.0417,"ggttg-sa-cpp-f-inl0-sse4":0.082,"ggttg-sa-cpp-f-inl1-sse4":0.087,"ggttg-sa-cpp-d-inl0-avx2":0.0873,"ggttg-sa-cpp-d-inl1-avx2":0.0806,"ggttg-sa-cpp-f-inl0-avx2":0.1742,"ggttg-sa-cpp-f-inl1-avx2":0.1402,"ggttg-sa-cpp-d-inl0-512y":0.1,"ggttg-sa-cpp-d-inl1-512y":0.0889,"ggttg-sa-cpp-f-inl0-512y":0.1974,"ggttg-sa-cpp-f-inl1-512y":0.1555,"ggttg-sa-cpp-d-inl0-512z":0.0722,"ggttg-sa-cpp-d-inl1-512z":0.0648,"ggttg-sa-cpp-f-inl0-512z":0.1502,"ggttg-sa-cpp-f-inl1-512z":0.115,"ggttgg-sa-cuda-d-inl0":0.4201,"ggttgg-sa-cuda-d-inl1":0.3868,"ggttgg-sa-cuda-f-inl0":0.8683,"ggttgg-sa-cuda-f-inl1":0.7768,"ggttgg-sa-cpp-d-inl0-best":0.0075,"ggttgg-sa-cpp-d-inl0-none":0.0017,"ggttgg-sa-cpp-d-inl1-best":0.0069,"ggttgg-sa-cpp-d-inl1-none":0.0004,"ggttgg-sa-cpp-f-inl0-best":0.0149,"ggttgg-sa-cpp-f-inl0-none":0.0018,"ggttgg-sa-cpp-f-inl1-best":0.0134,"ggttgg-sa-cpp-f-inl1-none":0.0005,"ggttgg-sa-cpp-d-inl0-sse4":0.0033,"ggttgg-sa-cpp-d-inl1-sse4":0.0028,"ggttgg-sa-cpp-f-inl0-sse4":0.0069,"ggttgg-sa-cpp-f-inl1-sse4":0.0061,"ggttgg-sa-cpp-d-inl0-avx2":0.0067,"ggttgg-sa-cpp-d-inl1-avx2":0.0054,"ggttgg-sa-cpp-f-inl0-avx2":0.0134,"ggttgg-sa-cpp-f-inl1-avx2":0.0106,"ggttgg-sa-cpp-d-inl0-512y":0.0075,"ggttgg-sa-cpp-d-inl1-512y":0.0069,"ggttgg-sa-cpp-f-inl0-512y":0.0149,"ggttgg-sa-cpp-f-inl1-512y":0.0134,"ggttgg-sa-cpp-d-inl0-512z":0.0065,"ggttgg-sa-cpp-d-inl1-512z":0.0065,"ggttgg-sa-cpp-f-inl0-512z":0.0131,"ggttgg-sa-cpp-f-inl1-512z":0.0126},"wl-stats":{"eemumu-sa-cuda-d-inl0":{"avg":1130.432,"median":1130.432,"min":1130.432,"max":1130.432,"count":1},"eemumu-sa-cuda-d-inl1":{"avg":1128.067,"median":1128.067,"min":1128.067,"max":1128.067,"count":1},"eemumu-sa-cuda-f-inl0":{"avg":3036.306,"median":3036.306,"min":3036.306,"max":3036.306,"count":1},"eemumu-sa-cuda-f-inl1":{"avg":3029.1,"median":3029.1,"min":3029.1,"max":3029.1,"count":1},"eemumu-sa-cpp-d-inl0-best":{"avg":5.8463,"median":5.8463,"min":5.8463,"max":5.8463,"count":1},"eemumu-sa-cpp-d-inl0-none":{"avg":1.6029,"median":1.6029,"min":1.6029,"max":1.6029,"count":1},"eemumu-sa-cpp-d-inl1-best":{"avg":10.2311,"median":10.2311,"min":10.2311,"max":10.2311,"count":1},"eemumu-sa-cpp-d-inl1-none":{"avg":4.6502,"median":4.6502,"min":4.6502,"max":4.6502,"count":1},"eemumu-sa-cpp-f-inl0-best":{"avg":12.0628,"median":12.0628,"min":12.0628,"max":12.0628,"count":1},"eemumu-sa-cpp-f-inl0-none":{"avg":1.6559,"median":1.6559,"min":1.6559,"max":1.6559,"count":1},"eemumu-sa-cpp-f-inl1-best":{"avg":25.1426,"median":25.1426,"min":25.1426,"max":25.1426,"count":1},"eemumu-sa-cpp-f-inl1-none":{"avg":4.9364,"median":4.9364,"min":4.9364,"max":4.9364,"count":1},"eemumu-sa-cpp-d-inl0-sse4":{"avg":3.0622,"median":3.0622,"min":3.0622,"max":3.0622,"count":1},"eemumu-sa-cpp-d-inl1-sse4":{"avg":7.9254,"median":7.9254,"min":7.9254,"max":7.9254,"count":1},"eemumu-sa-cpp-f-inl0-sse4":{"avg":6.0888,"median":6.0888,"min":6.0888,"max":6.0888,"count":1},"eemumu-sa-cpp-f-inl1-sse4":{"avg":14.2969,"median":14.2969,"min":14.2969,"max":14.2969,"count":1},"eemumu-sa-cpp-d-inl0-avx2":{"avg":5.3727,"median":5.3727,"min":5.3727,"max":5.3727,"count":1},"eemumu-sa-cpp-d-inl1-avx2":{"avg":10.2311,"median":10.2311,"min":10.2311,"max":10.2311,"count":1},"eemumu-sa-cpp-f-inl0-avx2":{"avg":11.2383,"median":11.2383,"min":11.2383,"max":11.2383,"count":1},"eemumu-sa-cpp-f-inl1-avx2":{"avg":24.6208,"median":24.6208,"min":24.6208,"max":24.6208,"count":1},"eemumu-sa-cpp-d-inl0-512y":{"avg":5.8463,"median":5.8463,"min":5.8463,"max":5.8463,"count":1},"eemumu-sa-cpp-d-inl1-512y":{"avg":10.2161,"median":10.2161,"min":10.2161,"max":10.2161,"count":1},"eemumu-sa-cpp-f-inl0-512y":{"avg":12.0628,"median":12.0628,"min":12.0628,"max":12.0628,"count":1},"eemumu-sa-cpp-f-inl1-512y":{"avg":25.1426,"median":25.1426,"min":25.1426,"max":25.1426,"count":1},"eemumu-sa-cpp-d-inl0-512z":{"avg":4.743,"median":4.743,"min":4.743,"max":4.743,"count":1},"eemumu-sa-cpp-d-inl1-512z":{"avg":8.5471,"median":8.5471,"min":8.5471,"max":8.5471,"count":1},"eemumu-sa-cpp-f-inl0-512z":{"avg":9.644,"median":9.644,"min":9.644,"max":9.644,"count":1},"eemumu-sa-cpp-f-inl1-512z":{"avg":18.3169,"median":18.3169,"min":18.3169,"max":18.3169,"count":1},"ggtt-sa-cuda-d-inl0":{"avg":130.0122,"median":130.0122,"min":130.0122,"max":130.0122,"count":1},"ggtt-sa-cuda-d-inl1":{"avg":130.2486,"median":130.2486,"min":130.2486,"max":130.2486,"count":1},"ggtt-sa-cuda-f-inl0":{"avg":363.6906,"median":363.6906,"min":363.6906,"max":363.6906,"count":1},"ggtt-sa-cuda-f-inl1":{"avg":363.4642,"median":363.4642,"min":363.4642,"max":363.4642,"count":1},"ggtt-sa-cpp-d-inl0-best":{"avg":0.6213,"median":0.6213,"min":0.6213,"max":0.6213,"count":1},"ggtt-sa-cpp-d-inl0-none":{"avg":0.1912,"median":0.1912,"min":0.1912,"max":0.1912,"count":1},"ggtt-sa-cpp-d-inl1-best":{"avg":0.4756,"median":0.4756,"min":0.4756,"max":0.4756,"count":1},"ggtt-sa-cpp-d-inl1-none":{"avg":0.2335,"median":0.2335,"min":0.2335,"max":0.2335,"count":1},"ggtt-sa-cpp-f-inl0-best":{"avg":1.1129,"median":1.1129,"min":1.1129,"max":1.1129,"count":1},"ggtt-sa-cpp-f-inl0-none":{"avg":0.2,"median":0.2,"min":0.2,"max":0.2,"count":1},"ggtt-sa-cpp-f-inl1-best":{"avg":0.7099,"median":0.7099,"min":0.7099,"max":0.7099,"count":1},"ggtt-sa-cpp-f-inl1-none":{"avg":0.2424,"median":0.2424,"min":0.2424,"max":0.2424,"count":1},"ggtt-sa-cpp-d-inl0-sse4":{"avg":0.3204,"median":0.3204,"min":0.3204,"max":0.3204,"count":1},"ggtt-sa-cpp-d-inl1-sse4":{"avg":0.2768,"median":0.2768,"min":0.2768,"max":0.2768,"count":1},"ggtt-sa-cpp-f-inl0-sse4":{"avg":0.4764,"median":0.4764,"min":0.4764,"max":0.4764,"count":1},"ggtt-sa-cpp-f-inl1-sse4":{"avg":0.5602,"median":0.5602,"min":0.5602,"max":0.5602,"count":1},"ggtt-sa-cpp-d-inl0-avx2":{"avg":0.5574,"median":0.5574,"min":0.5574,"max":0.5574,"count":1},"ggtt-sa-cpp-d-inl1-avx2":{"avg":0.4593,"median":0.4593,"min":0.4593,"max":0.4593,"count":1},"ggtt-sa-cpp-f-inl0-avx2":{"avg":1.0353,"median":1.0353,"min":1.0353,"max":1.0353,"count":1},"ggtt-sa-cpp-f-inl1-avx2":{"avg":0.7014,"median":0.7014,"min":0.7014,"max":0.7014,"count":1},"ggtt-sa-cpp-d-inl0-512y":{"avg":0.6213,"median":0.6213,"min":0.6213,"max":0.6213,"count":1},"ggtt-sa-cpp-d-inl1-512y":{"avg":0.4756,"median":0.4756,"min":0.4756,"max":0.4756,"count":1},"ggtt-sa-cpp-f-inl0-512y":{"avg":1.1129,"median":1.1129,"min":1.1129,"max":1.1129,"count":1},"ggtt-sa-cpp-f-inl1-512y":{"avg":0.7099,"median":0.7099,"min":0.7099,"max":0.7099,"count":1},"ggtt-sa-cpp-d-inl0-512z":{"avg":0.3732,"median":0.3732,"min":0.3732,"max":0.3732,"count":1},"ggtt-sa-cpp-d-inl1-512z":{"avg":0.3438,"median":0.3438,"min":0.3438,"max":0.3438,"count":1},"ggtt-sa-cpp-f-inl0-512z":{"avg":0.7762,"median":0.7762,"min":0.7762,"max":0.7762,"count":1},"ggtt-sa-cpp-f-inl1-512z":{"avg":0.5638,"median":0.5638,"min":0.5638,"max":0.5638,"count":1},"ggttg-sa-cuda-d-inl0":{"avg":13.4296,"median":13.4296,"min":13.4296,"max":13.4296,"count":1},"ggttg-sa-cuda-d-inl1":{"avg":13.4207,"median":13.4207,"min":13.4207,"max":13.4207,"count":1},"ggttg-sa-cuda-f-inl0":{"avg":45.8793,"median":45.8793,"min":45.8793,"max":45.8793,"count":1},"ggttg-sa-cuda-f-inl1":{"avg":45.5322,"median":45.5322,"min":45.5322,"max":45.5322,"count":1},"ggttg-sa-cpp-d-inl0-best":{"avg":0.1,"median":0.1,"min":0.1,"max":0.1,"count":1},"ggttg-sa-cpp-d-inl0-none":{"avg":0.0238,"median":0.0238,"min":0.0238,"max":0.0238,"count":1},"ggttg-sa-cpp-d-inl1-best":{"avg":0.0889,"median":0.0889,"min":0.0889,"max":0.0889,"count":1},"ggttg-sa-cpp-d-inl1-none":{"avg":0.0063,"median":0.0063,"min":0.0063,"max":0.0063,"count":1},"ggttg-sa-cpp-f-inl0-best":{"avg":0.1974,"median":0.1974,"min":0.1974,"max":0.1974,"count":1},"ggttg-sa-cpp-f-inl0-none":{"avg":0.0244,"median":0.0244,"min":0.0244,"max":0.0244,"count":1},"ggttg-sa-cpp-f-inl1-best":{"avg":0.1555,"median":0.1555,"min":0.1555,"max":0.1555,"count":1},"ggttg-sa-cpp-f-inl1-none":{"avg":0.0102,"median":0.0102,"min":0.0102,"max":0.0102,"count":1},"ggttg-sa-cpp-d-inl0-sse4":{"avg":0.0448,"median":0.0448,"min":0.0448,"max":0.0448,"count":1},"ggttg-sa-cpp-d-inl1-sse4":{"avg":0.0417,"median":0.0417,"min":0.0417,"max":0.0417,"count":1},"ggttg-sa-cpp-f-inl0-sse4":{"avg":0.082,"median":0.082,"min":0.082,"max":0.082,"count":1},"ggttg-sa-cpp-f-inl1-sse4":{"avg":0.087,"median":0.087,"min":0.087,"max":0.087,"count":1},"ggttg-sa-cpp-d-inl0-avx2":{"avg":0.0873,"median":0.0873,"min":0.0873,"max":0.0873,"count":1},"ggttg-sa-cpp-d-inl1-avx2":{"avg":0.0806,"median":0.0806,"min":0.0806,"max":0.0806,"count":1},"ggttg-sa-cpp-f-inl0-avx2":{"avg":0.1742,"median":0.1742,"min":0.1742,"max":0.1742,"count":1},"ggttg-sa-cpp-f-inl1-avx2":{"avg":0.1402,"median":0.1402,"min":0.1402,"max":0.1402,"count":1},"ggttg-sa-cpp-d-inl0-512y":{"avg":0.1,"median":0.1,"min":0.1,"max":0.1,"count":1},"ggttg-sa-cpp-d-inl1-512y":{"avg":0.0889,"median":0.0889,"min":0.0889,"max":0.0889,"count":1},"ggttg-sa-cpp-f-inl0-512y":{"avg":0.1974,"median":0.1974,"min":0.1974,"max":0.1974,"count":1},"ggttg-sa-cpp-f-inl1-512y":{"avg":0.1555,"median":0.1555,"min":0.1555,"max":0.1555,"count":1},"ggttg-sa-cpp-d-inl0-512z":{"avg":0.0722,"median":0.0722,"min":0.0722,"max":0.0722,"count":1},"ggttg-sa-cpp-d-inl1-512z":{"avg":0.0648,"median":0.0648,"min":0.0648,"max":0.0648,"count":1},"ggttg-sa-cpp-f-inl0-512z":{"avg":0.1502,"median":0.1502,"min":0.1502,"max":0.1502,"count":1},"ggttg-sa-cpp-f-inl1-512z":{"avg":0.115,"median":0.115,"min":0.115,"max":0.115,"count":1},"ggttgg-sa-cuda-d-inl0":{"avg":0.4201,"median":0.4201,"min":0.4201,"max":0.4201,"count":1},"ggttgg-sa-cuda-d-inl1":{"avg":0.3868,"median":0.3868,"min":0.3868,"max":0.3868,"count":1},"ggttgg-sa-cuda-f-inl0":{"avg":0.8683,"median":0.8683,"min":0.8683,"max":0.8683,"count":1},"ggttgg-sa-cuda-f-inl1":{"avg":0.7768,"median":0.7768,"min":0.7768,"max":0.7768,"count":1},"ggttgg-sa-cpp-d-inl0-best":{"avg":0.0075,"median":0.0075,"min":0.0075,"max":0.0075,"count":1},"ggttgg-sa-cpp-d-inl0-none":{"avg":0.0017,"median":0.0017,"min":0.0017,"max":0.0017,"count":1},"ggttgg-sa-cpp-d-inl1-best":{"avg":0.0069,"median":0.0069,"min":0.0069,"max":0.0069,"count":1},"ggttgg-sa-cpp-d-inl1-none":{"avg":0.0004,"median":0.0004,"min":0.0004,"max":0.0004,"count":1},"ggttgg-sa-cpp-f-inl0-best":{"avg":0.0149,"median":0.0149,"min":0.0149,"max":0.0149,"count":1},"ggttgg-sa-cpp-f-inl0-none":{"avg":0.0018,"median":0.0018,"min":0.0018,"max":0.0018,"count":1},"ggttgg-sa-cpp-f-inl1-best":{"avg":0.0134,"median":0.0134,"min":0.0134,"max":0.0134,"count":1},"ggttgg-sa-cpp-f-inl1-none":{"avg":0.0005,"median":0.0005,"min":0.0005,"max":0.0005,"count":1},"ggttgg-sa-cpp-d-inl0-sse4":{"avg":0.0033,"median":0.0033,"min":0.0033,"max":0.0033,"count":1},"ggttgg-sa-cpp-d-inl1-sse4":{"avg":0.0028,"median":0.0028,"min":0.0028,"max":0.0028,"count":1},"ggttgg-sa-cpp-f-inl0-sse4":{"avg":0.0069,"median":0.0069,"min":0.0069,"max":0.0069,"count":1},"ggttgg-sa-cpp-f-inl1-sse4":{"avg":0.0061,"median":0.0061,"min":0.0061,"max":0.0061,"count":1},"ggttgg-sa-cpp-d-inl0-avx2":{"avg":0.0067,"median":0.0067,"min":0.0067,"max":0.0067,"count":1},"ggttgg-sa-cpp-d-inl1-avx2":{"avg":0.0054,"median":0.0054,"min":0.0054,"max":0.0054,"count":1},"ggttgg-sa-cpp-f-inl0-avx2":{"avg":0.0134,"median":0.0134,"min":0.0134,"max":0.0134,"count":1},"ggttgg-sa-cpp-f-inl1-avx2":{"avg":0.0106,"median":0.0106,"min":0.0106,"max":0.0106,"count":1},"ggttgg-sa-cpp-d-inl0-512y":{"avg":0.0075,"median":0.0075,"min":0.0075,"max":0.0075,"count":1},"ggttgg-sa-cpp-d-inl1-512y":{"avg":0.0069,"median":0.0069,"min":0.0069,"max":0.0069,"count":1},"ggttgg-sa-cpp-f-inl0-512y":{"avg":0.0149,"median":0.0149,"min":0.0149,"max":0.0149,"count":1},"ggttgg-sa-cpp-f-inl1-512y":{"avg":0.0134,"median":0.0134,"min":0.0134,"max":0.0134,"count":1},"ggttgg-sa-cpp-d-inl0-512z":{"avg":0.0065,"median":0.0065,"min":0.0065,"max":0.0065,"count":1},"ggttgg-sa-cpp-d-inl1-512z":{"avg":0.0065,"median":0.0065,"min":0.0065,"max":0.0065,"count":1},"ggttgg-sa-cpp-f-inl0-512z":{"avg":0.0131,"median":0.0131,"min":0.0131,"max":0.0131,"count":1},"ggttgg-sa-cpp-f-inl1-512z":{"avg":0.0126,"median":0.0126,"min":0.0126,"max":0.0126,"count":1}},"log":"ok"},"app":{"version":"ci-v0.6","description":"Madgraph5_aMCatNLO madgraph4gpu benchmark (2022)","cvmfs_checksum":"05f5179a44c0e2051bbb092a63cf0daf","bmkdata_checksum":"4eb8273563af22b829ddbf985ae0b0a9","bmk_checksum":"9b7bedb12e18a214106591542f8b3093","containment":"docker"}}
+{"run_info":{"copies":1,"threads_per_copy":1,"events_per_thread":2,"extra_arguments":"--both -eemumu -ggtt -ggttg -ggttgg -dbl -flt -inl0 -inl1"},"report":{"wl-scores":{"eemumu-sa-cuda-d-inl0":49.17082,"eemumu-sa-cuda-d-inl1":48.7865,"eemumu-sa-cuda-f-inl0":1424.712,"eemumu-sa-cuda-f-inl1":1381.75,"eemumu-sa-cpp-d-inl0-best":5.867042,"eemumu-sa-cpp-d-inl0-none":1.608947,"eemumu-sa-cpp-d-inl1-best":10.75539,"eemumu-sa-cpp-d-inl1-none":4.669422,"eemumu-sa-cpp-f-inl0-best":12.20688,"eemumu-sa-cpp-f-inl0-none":1.660083,"eemumu-sa-cpp-f-inl1-best":27.14961,"eemumu-sa-cpp-f-inl1-none":4.952965,"eemumu-sa-cpp-d-inl0-sse4":3.067335,"eemumu-sa-cpp-d-inl1-sse4":8.170056,"eemumu-sa-cpp-f-inl0-sse4":6.088195,"eemumu-sa-cpp-f-inl1-sse4":14.69091,"eemumu-sa-cpp-d-inl0-avx2":5.418349,"eemumu-sa-cpp-d-inl1-avx2":10.74482,"eemumu-sa-cpp-f-inl0-avx2":11.34434,"eemumu-sa-cpp-f-inl1-avx2":26.22451,"eemumu-sa-cpp-d-inl0-512y":5.867042,"eemumu-sa-cpp-d-inl1-512y":10.75539,"eemumu-sa-cpp-f-inl0-512y":12.20688,"eemumu-sa-cpp-f-inl1-512y":27.14961,"eemumu-sa-cpp-d-inl0-512z":4.790807,"eemumu-sa-cpp-d-inl1-512z":8.892809,"eemumu-sa-cpp-f-inl0-512z":9.889234,"eemumu-sa-cpp-f-inl1-512z":20.07931,"ggtt-sa-cuda-d-inl0":5.614885,"ggtt-sa-cuda-d-inl1":5.67835,"ggtt-sa-cuda-f-inl0":170.89,"ggtt-sa-cuda-f-inl1":166.1471,"ggtt-sa-cpp-d-inl0-best":0.624347,"ggtt-sa-cpp-d-inl0-none":0.191459,"ggtt-sa-cpp-d-inl1-best":0.478546,"ggtt-sa-cpp-d-inl1-none":0.233533,"ggtt-sa-cpp-f-inl0-best":1.124162,"ggtt-sa-cpp-f-inl0-none":0.200197,"ggtt-sa-cpp-f-inl1-best":0.720282,"ggtt-sa-cpp-f-inl1-none":0.243261,"ggtt-sa-cpp-d-inl0-sse4":0.321853,"ggtt-sa-cpp-d-inl1-sse4":0.277725,"ggtt-sa-cpp-f-inl0-sse4":0.478594,"ggtt-sa-cpp-f-inl1-sse4":0.563596,"ggtt-sa-cpp-d-inl0-avx2":0.55893,"ggtt-sa-cpp-d-inl1-avx2":0.459852,"ggtt-sa-cpp-f-inl0-avx2":1.041415,"ggtt-sa-cpp-f-inl1-avx2":0.718636,"ggtt-sa-cpp-d-inl0-512y":0.624347,"ggtt-sa-cpp-d-inl1-512y":0.478546,"ggtt-sa-cpp-f-inl0-512y":1.124162,"ggtt-sa-cpp-f-inl1-512y":0.720282,"ggtt-sa-cpp-d-inl0-512z":0.377197,"ggtt-sa-cpp-d-inl1-512z":0.349354,"ggtt-sa-cpp-f-inl0-512z":0.78713,"ggtt-sa-cpp-f-inl1-512z":0.56613,"ggttg-sa-cuda-d-inl0":0.818303,"ggttg-sa-cuda-d-inl1":0.818321,"ggttg-sa-cuda-f-inl0":16.53627,"ggttg-sa-cuda-f-inl1":18.2233,"ggttg-sa-cpp-d-inl0-best":0.099627,"ggttg-sa-cpp-d-inl0-none":0.023868,"ggttg-sa-cpp-d-inl1-best":0.089081,"ggttg-sa-cpp-d-inl1-none":0.006263,"ggttg-sa-cpp-f-inl0-best":0.19742,"ggttg-sa-cpp-f-inl0-none":0.024429,"ggttg-sa-cpp-f-inl1-best":0.155667,"ggttg-sa-cpp-f-inl1-none":0.010204,"ggttg-sa-cpp-d-inl0-sse4":0.044845,"ggttg-sa-cpp-d-inl1-sse4":0.041879,"ggttg-sa-cpp-f-inl0-sse4":0.082119,"ggttg-sa-cpp-f-inl1-sse4":0.08722,"ggttg-sa-cpp-d-inl0-avx2":0.087346,"ggttg-sa-cpp-d-inl1-avx2":0.080843,"ggttg-sa-cpp-f-inl0-avx2":0.175008,"ggttg-sa-cpp-f-inl1-avx2":0.140438,"ggttg-sa-cpp-d-inl0-512y":0.099627,"ggttg-sa-cpp-d-inl1-512y":0.089081,"ggttg-sa-cpp-f-inl0-512y":0.19742,"ggttg-sa-cpp-f-inl1-512y":0.155667,"ggttg-sa-cpp-d-inl0-512z":0.072385,"ggttg-sa-cpp-d-inl1-512z":0.064822,"ggttg-sa-cpp-f-inl0-512z":0.150176,"ggttg-sa-cpp-f-inl1-512z":0.115442,"ggttgg-sa-cuda-d-inl0":0.055409,"ggttgg-sa-cuda-d-inl1":0.061492,"ggttgg-sa-cuda-f-inl0":0.308086,"ggttgg-sa-cuda-f-inl1":0.265549,"ggttgg-sa-cpp-d-inl0-best":0.007546,"ggttgg-sa-cpp-d-inl0-none":0.001741,"ggttgg-sa-cpp-d-inl1-best":0.0069,"ggttgg-sa-cpp-d-inl1-none":0.000381,"ggttgg-sa-cpp-f-inl0-best":0.014982,"ggttgg-sa-cpp-f-inl0-none":0.001829,"ggttgg-sa-cpp-f-inl1-best":0.013474,"ggttgg-sa-cpp-f-inl1-none":0.000498,"ggttgg-sa-cpp-d-inl0-sse4":0.003348,"ggttgg-sa-cpp-d-inl1-sse4":0.002788,"ggttgg-sa-cpp-f-inl0-sse4":0.006897,"ggttgg-sa-cpp-f-inl1-sse4":0.006083,"ggttgg-sa-cpp-d-inl0-avx2":0.00668,"ggttgg-sa-cpp-d-inl1-avx2":0.005444,"ggttgg-sa-cpp-f-inl0-avx2":0.013352,"ggttgg-sa-cpp-f-inl1-avx2":0.010663,"ggttgg-sa-cpp-d-inl0-512y":0.007546,"ggttgg-sa-cpp-d-inl1-512y":0.0069,"ggttgg-sa-cpp-f-inl0-512y":0.014982,"ggttgg-sa-cpp-f-inl1-512y":0.013474,"ggttgg-sa-cpp-d-inl0-512z":0.006479,"ggttgg-sa-cpp-d-inl1-512z":0.006532,"ggttgg-sa-cpp-f-inl0-512z":0.013037,"ggttgg-sa-cpp-f-inl1-512z":0.012668},"wl-stats":{"eemumu-sa-cuda-d-inl0":{"avg":49.17082,"median":49.17082,"min":49.17082,"max":49.17082,"count":1},"eemumu-sa-cuda-d-inl1":{"avg":48.7865,"median":48.7865,"min":48.7865,"max":48.7865,"count":1},"eemumu-sa-cuda-f-inl0":{"avg":1424.712,"median":1424.712,"min":1424.712,"max":1424.712,"count":1},"eemumu-sa-cuda-f-inl1":{"avg":1381.75,"median":1381.75,"min":1381.75,"max":1381.75,"count":1},"eemumu-sa-cpp-d-inl0-best":{"avg":5.867042,"median":5.867042,"min":5.867042,"max":5.867042,"count":1},"eemumu-sa-cpp-d-inl0-none":{"avg":1.608947,"median":1.608947,"min":1.608947,"max":1.608947,"count":1},"eemumu-sa-cpp-d-inl1-best":{"avg":10.75539,"median":10.75539,"min":10.75539,"max":10.75539,"count":1},"eemumu-sa-cpp-d-inl1-none":{"avg":4.669422,"median":4.669422,"min":4.669422,"max":4.669422,"count":1},"eemumu-sa-cpp-f-inl0-best":{"avg":12.20688,"median":12.20688,"min":12.20688,"max":12.20688,"count":1},"eemumu-sa-cpp-f-inl0-none":{"avg":1.660083,"median":1.660083,"min":1.660083,"max":1.660083,"count":1},"eemumu-sa-cpp-f-inl1-best":{"avg":27.14961,"median":27.14961,"min":27.14961,"max":27.14961,"count":1},"eemumu-sa-cpp-f-inl1-none":{"avg":4.952965,"median":4.952965,"min":4.952965,"max":4.952965,"count":1},"eemumu-sa-cpp-d-inl0-sse4":{"avg":3.067335,"median":3.067335,"min":3.067335,"max":3.067335,"count":1},"eemumu-sa-cpp-d-inl1-sse4":{"avg":8.170056,"median":8.170056,"min":8.170056,"max":8.170056,"count":1},"eemumu-sa-cpp-f-inl0-sse4":{"avg":6.088195,"median":6.088195,"min":6.088195,"max":6.088195,"count":1},"eemumu-sa-cpp-f-inl1-sse4":{"avg":14.69091,"median":14.69091,"min":14.69091,"max":14.69091,"count":1},"eemumu-sa-cpp-d-inl0-avx2":{"avg":5.418349,"median":5.418349,"min":5.418349,"max":5.418349,"count":1},"eemumu-sa-cpp-d-inl1-avx2":{"avg":10.74482,"median":10.74482,"min":10.74482,"max":10.74482,"count":1},"eemumu-sa-cpp-f-inl0-avx2":{"avg":11.34434,"median":11.34434,"min":11.34434,"max":11.34434,"count":1},"eemumu-sa-cpp-f-inl1-avx2":{"avg":26.22451,"median":26.22451,"min":26.22451,"max":26.22451,"count":1},"eemumu-sa-cpp-d-inl0-512y":{"avg":5.867042,"median":5.867042,"min":5.867042,"max":5.867042,"count":1},"eemumu-sa-cpp-d-inl1-512y":{"avg":10.75539,"median":10.75539,"min":10.75539,"max":10.75539,"count":1},"eemumu-sa-cpp-f-inl0-512y":{"avg":12.20688,"median":12.20688,"min":12.20688,"max":12.20688,"count":1},"eemumu-sa-cpp-f-inl1-512y":{"avg":27.14961,"median":27.14961,"min":27.14961,"max":27.14961,"count":1},"eemumu-sa-cpp-d-inl0-512z":{"avg":4.790807,"median":4.790807,"min":4.790807,"max":4.790807,"count":1},"eemumu-sa-cpp-d-inl1-512z":{"avg":8.892809,"median":8.892809,"min":8.892809,"max":8.892809,"count":1},"eemumu-sa-cpp-f-inl0-512z":{"avg":9.889234,"median":9.889234,"min":9.889234,"max":9.889234,"count":1},"eemumu-sa-cpp-f-inl1-512z":{"avg":20.07931,"median":20.07931,"min":20.07931,"max":20.07931,"count":1},"ggtt-sa-cuda-d-inl0":{"avg":5.614885,"median":5.614885,"min":5.614885,"max":5.614885,"count":1},"ggtt-sa-cuda-d-inl1":{"avg":5.67835,"median":5.67835,"min":5.67835,"max":5.67835,"count":1},"ggtt-sa-cuda-f-inl0":{"avg":170.89,"median":170.89,"min":170.89,"max":170.89,"count":1},"ggtt-sa-cuda-f-inl1":{"avg":166.1471,"median":166.1471,"min":166.1471,"max":166.1471,"count":1},"ggtt-sa-cpp-d-inl0-best":{"avg":0.624347,"median":0.624347,"min":0.624347,"max":0.624347,"count":1},"ggtt-sa-cpp-d-inl0-none":{"avg":0.191459,"median":0.191459,"min":0.191459,"max":0.191459,"count":1},"ggtt-sa-cpp-d-inl1-best":{"avg":0.478546,"median":0.478546,"min":0.478546,"max":0.478546,"count":1},"ggtt-sa-cpp-d-inl1-none":{"avg":0.233533,"median":0.233533,"min":0.233533,"max":0.233533,"count":1},"ggtt-sa-cpp-f-inl0-best":{"avg":1.124162,"median":1.124162,"min":1.124162,"max":1.124162,"count":1},"ggtt-sa-cpp-f-inl0-none":{"avg":0.200197,"median":0.200197,"min":0.200197,"max":0.200197,"count":1},"ggtt-sa-cpp-f-inl1-best":{"avg":0.720282,"median":0.720282,"min":0.720282,"max":0.720282,"count":1},"ggtt-sa-cpp-f-inl1-none":{"avg":0.243261,"median":0.243261,"min":0.243261,"max":0.243261,"count":1},"ggtt-sa-cpp-d-inl0-sse4":{"avg":0.321853,"median":0.321853,"min":0.321853,"max":0.321853,"count":1},"ggtt-sa-cpp-d-inl1-sse4":{"avg":0.277725,"median":0.277725,"min":0.277725,"max":0.277725,"count":1},"ggtt-sa-cpp-f-inl0-sse4":{"avg":0.478594,"median":0.478594,"min":0.478594,"max":0.478594,"count":1},"ggtt-sa-cpp-f-inl1-sse4":{"avg":0.563596,"median":0.563596,"min":0.563596,"max":0.563596,"count":1},"ggtt-sa-cpp-d-inl0-avx2":{"avg":0.55893,"median":0.55893,"min":0.55893,"max":0.55893,"count":1},"ggtt-sa-cpp-d-inl1-avx2":{"avg":0.459852,"median":0.459852,"min":0.459852,"max":0.459852,"count":1},"ggtt-sa-cpp-f-inl0-avx2":{"avg":1.041415,"median":1.041415,"min":1.041415,"max":1.041415,"count":1},"ggtt-sa-cpp-f-inl1-avx2":{"avg":0.718636,"median":0.718636,"min":0.718636,"max":0.718636,"count":1},"ggtt-sa-cpp-d-inl0-512y":{"avg":0.624347,"median":0.624347,"min":0.624347,"max":0.624347,"count":1},"ggtt-sa-cpp-d-inl1-512y":{"avg":0.478546,"median":0.478546,"min":0.478546,"max":0.478546,"count":1},"ggtt-sa-cpp-f-inl0-512y":{"avg":1.124162,"median":1.124162,"min":1.124162,"max":1.124162,"count":1},"ggtt-sa-cpp-f-inl1-512y":{"avg":0.720282,"median":0.720282,"min":0.720282,"max":0.720282,"count":1},"ggtt-sa-cpp-d-inl0-512z":{"avg":0.377197,"median":0.377197,"min":0.377197,"max":0.377197,"count":1},"ggtt-sa-cpp-d-inl1-512z":{"avg":0.349354,"median":0.349354,"min":0.349354,"max":0.349354,"count":1},"ggtt-sa-cpp-f-inl0-512z":{"avg":0.78713,"median":0.78713,"min":0.78713,"max":0.78713,"count":1},"ggtt-sa-cpp-f-inl1-512z":{"avg":0.56613,"median":0.56613,"min":0.56613,"max":0.56613,"count":1},"ggttg-sa-cuda-d-inl0":{"avg":0.818303,"median":0.818303,"min":0.818303,"max":0.818303,"count":1},"ggttg-sa-cuda-d-inl1":{"avg":0.818321,"median":0.818321,"min":0.818321,"max":0.818321,"count":1},"ggttg-sa-cuda-f-inl0":{"avg":16.53627,"median":16.53627,"min":16.53627,"max":16.53627,"count":1},"ggttg-sa-cuda-f-inl1":{"avg":18.2233,"median":18.2233,"min":18.2233,"max":18.2233,"count":1},"ggttg-sa-cpp-d-inl0-best":{"avg":0.099627,"median":0.099627,"min":0.099627,"max":0.099627,"count":1},"ggttg-sa-cpp-d-inl0-none":{"avg":0.023868,"median":0.023868,"min":0.023868,"max":0.023868,"count":1},"ggttg-sa-cpp-d-inl1-best":{"avg":0.089081,"median":0.089081,"min":0.089081,"max":0.089081,"count":1},"ggttg-sa-cpp-d-inl1-none":{"avg":0.006263,"median":0.006263,"min":0.006263,"max":0.006263,"count":1},"ggttg-sa-cpp-f-inl0-best":{"avg":0.19742,"median":0.19742,"min":0.19742,"max":0.19742,"count":1},"ggttg-sa-cpp-f-inl0-none":{"avg":0.024429,"median":0.024429,"min":0.024429,"max":0.024429,"count":1},"ggttg-sa-cpp-f-inl1-best":{"avg":0.155667,"median":0.155667,"min":0.155667,"max":0.155667,"count":1},"ggttg-sa-cpp-f-inl1-none":{"avg":0.010204,"median":0.010204,"min":0.010204,"max":0.010204,"count":1},"ggttg-sa-cpp-d-inl0-sse4":{"avg":0.044845,"median":0.044845,"min":0.044845,"max":0.044845,"count":1},"ggttg-sa-cpp-d-inl1-sse4":{"avg":0.041879,"median":0.041879,"min":0.041879,"max":0.041879,"count":1},"ggttg-sa-cpp-f-inl0-sse4":{"avg":0.082119,"median":0.082119,"min":0.082119,"max":0.082119,"count":1},"ggttg-sa-cpp-f-inl1-sse4":{"avg":0.08722,"median":0.08722,"min":0.08722,"max":0.08722,"count":1},"ggttg-sa-cpp-d-inl0-avx2":{"avg":0.087346,"median":0.087346,"min":0.087346,"max":0.087346,"count":1},"ggttg-sa-cpp-d-inl1-avx2":{"avg":0.080843,"median":0.080843,"min":0.080843,"max":0.080843,"count":1},"ggttg-sa-cpp-f-inl0-avx2":{"avg":0.175008,"median":0.175008,"min":0.175008,"max":0.175008,"count":1},"ggttg-sa-cpp-f-inl1-avx2":{"avg":0.140438,"median":0.140438,"min":0.140438,"max":0.140438,"count":1},"ggttg-sa-cpp-d-inl0-512y":{"avg":0.099627,"median":0.099627,"min":0.099627,"max":0.099627,"count":1},"ggttg-sa-cpp-d-inl1-512y":{"avg":0.089081,"median":0.089081,"min":0.089081,"max":0.089081,"count":1},"ggttg-sa-cpp-f-inl0-512y":{"avg":0.19742,"median":0.19742,"min":0.19742,"max":0.19742,"count":1},"ggttg-sa-cpp-f-inl1-512y":{"avg":0.155667,"median":0.155667,"min":0.155667,"max":0.155667,"count":1},"ggttg-sa-cpp-d-inl0-512z":{"avg":0.072385,"median":0.072385,"min":0.072385,"max":0.072385,"count":1},"ggttg-sa-cpp-d-inl1-512z":{"avg":0.064822,"median":0.064822,"min":0.064822,"max":0.064822,"count":1},"ggttg-sa-cpp-f-inl0-512z":{"avg":0.150176,"median":0.150176,"min":0.150176,"max":0.150176,"count":1},"ggttg-sa-cpp-f-inl1-512z":{"avg":0.115442,"median":0.115442,"min":0.115442,"max":0.115442,"count":1},"ggttgg-sa-cuda-d-inl0":{"avg":0.055409,"median":0.055409,"min":0.055409,"max":0.055409,"count":1},"ggttgg-sa-cuda-d-inl1":{"avg":0.061492,"median":0.061492,"min":0.061492,"max":0.061492,"count":1},"ggttgg-sa-cuda-f-inl0":{"avg":0.308086,"median":0.308086,"min":0.308086,"max":0.308086,"count":1},"ggttgg-sa-cuda-f-inl1":{"avg":0.265549,"median":0.265549,"min":0.265549,"max":0.265549,"count":1},"ggttgg-sa-cpp-d-inl0-best":{"avg":0.007546,"median":0.007546,"min":0.007546,"max":0.007546,"count":1},"ggttgg-sa-cpp-d-inl0-none":{"avg":0.001741,"median":0.001741,"min":0.001741,"max":0.001741,"count":1},"ggttgg-sa-cpp-d-inl1-best":{"avg":0.0069,"median":0.0069,"min":0.0069,"max":0.0069,"count":1},"ggttgg-sa-cpp-d-inl1-none":{"avg":0.000381,"median":0.000381,"min":0.000381,"max":0.000381,"count":1},"ggttgg-sa-cpp-f-inl0-best":{"avg":0.014982,"median":0.014982,"min":0.014982,"max":0.014982,"count":1},"ggttgg-sa-cpp-f-inl0-none":{"avg":0.001829,"median":0.001829,"min":0.001829,"max":0.001829,"count":1},"ggttgg-sa-cpp-f-inl1-best":{"avg":0.013474,"median":0.013474,"min":0.013474,"max":0.013474,"count":1},"ggttgg-sa-cpp-f-inl1-none":{"avg":0.000498,"median":0.000498,"min":0.000498,"max":0.000498,"count":1},"ggttgg-sa-cpp-d-inl0-sse4":{"avg":0.003348,"median":0.003348,"min":0.003348,"max":0.003348,"count":1},"ggttgg-sa-cpp-d-inl1-sse4":{"avg":0.002788,"median":0.002788,"min":0.002788,"max":0.002788,"count":1},"ggttgg-sa-cpp-f-inl0-sse4":{"avg":0.006897,"median":0.006897,"min":0.006897,"max":0.006897,"count":1},"ggttgg-sa-cpp-f-inl1-sse4":{"avg":0.006083,"median":0.006083,"min":0.006083,"max":0.006083,"count":1},"ggttgg-sa-cpp-d-inl0-avx2":{"avg":0.00668,"median":0.00668,"min":0.00668,"max":0.00668,"count":1},"ggttgg-sa-cpp-d-inl1-avx2":{"avg":0.005444,"median":0.005444,"min":0.005444,"max":0.005444,"count":1},"ggttgg-sa-cpp-f-inl0-avx2":{"avg":0.013352,"median":0.013352,"min":0.013352,"max":0.013352,"count":1},"ggttgg-sa-cpp-f-inl1-avx2":{"avg":0.010663,"median":0.010663,"min":0.010663,"max":0.010663,"count":1},"ggttgg-sa-cpp-d-inl0-512y":{"avg":0.007546,"median":0.007546,"min":0.007546,"max":0.007546,"count":1},"ggttgg-sa-cpp-d-inl1-512y":{"avg":0.0069,"median":0.0069,"min":0.0069,"max":0.0069,"count":1},"ggttgg-sa-cpp-f-inl0-512y":{"avg":0.014982,"median":0.014982,"min":0.014982,"max":0.014982,"count":1},"ggttgg-sa-cpp-f-inl1-512y":{"avg":0.013474,"median":0.013474,"min":0.013474,"max":0.013474,"count":1},"ggttgg-sa-cpp-d-inl0-512z":{"avg":0.006479,"median":0.006479,"min":0.006479,"max":0.006479,"count":1},"ggttgg-sa-cpp-d-inl1-512z":{"avg":0.006532,"median":0.006532,"min":0.006532,"max":0.006532,"count":1},"ggttgg-sa-cpp-f-inl0-512z":{"avg":0.013037,"median":0.013037,"min":0.013037,"max":0.013037,"count":1},"ggttgg-sa-cpp-f-inl1-512z":{"avg":0.012668,"median":0.012668,"min":0.012668,"max":0.012668,"count":1}},"log":"ok"},"app":{"version":"ci-v0.7","description":"Madgraph5_aMCatNLO madgraph4gpu benchmark (2022)","cvmfs_checksum":"70fb8b581609b9e1f7dde9c41d8cd73f","bmkdata_checksum":"d4c9152ed732e012ca54b6518bf3de93","bmk_checksum":"1b9db5695b5654135a84207bfe143df2","containment":"singularity"}}
+{"run_info":{"copies":1,"threads_per_copy":1,"events_per_thread":2,"extra_arguments":"--both -eemumu -ggtt -ggttg -ggttgg -dbl -flt -inl0 -inl1"},"report":{"wl-scores":{"eemumu-sa-cuda-d-inl0":48.79672,"eemumu-sa-cuda-d-inl1":49.58971,"eemumu-sa-cuda-f-inl0":1485.295,"eemumu-sa-cuda-f-inl1":1420.555,"eemumu-sa-cpp-d-inl0-best":5.85542,"eemumu-sa-cpp-d-inl0-none":1.60346,"eemumu-sa-cpp-d-inl1-best":11.02532,"eemumu-sa-cpp-d-inl1-none":4.669919,"eemumu-sa-cpp-f-inl0-best":12.28219,"eemumu-sa-cpp-f-inl0-none":1.662875,"eemumu-sa-cpp-f-inl1-best":27.95492,"eemumu-sa-cpp-f-inl1-none":4.952863,"eemumu-sa-cpp-d-inl0-sse4":3.070359,"eemumu-sa-cpp-d-inl1-sse4":8.24349,"eemumu-sa-cpp-f-inl0-sse4":6.108306,"eemumu-sa-cpp-f-inl1-sse4":14.71368,"eemumu-sa-cpp-d-inl0-avx2":5.434791,"eemumu-sa-cpp-d-inl1-avx2":11.02532,"eemumu-sa-cpp-f-inl0-avx2":11.37094,"eemumu-sa-cpp-f-inl1-avx2":27.61771,"eemumu-sa-cpp-d-inl0-512y":5.85542,"eemumu-sa-cpp-d-inl1-512y":10.94437,"eemumu-sa-cpp-f-inl0-512y":12.28219,"eemumu-sa-cpp-f-inl1-512y":27.95492,"eemumu-sa-cpp-d-inl0-512z":4.919846,"eemumu-sa-cpp-d-inl1-512z":9.140349,"eemumu-sa-cpp-f-inl0-512z":10.05686,"eemumu-sa-cpp-f-inl1-512z":20.54445,"ggtt-sa-cuda-d-inl0":5.745921,"ggtt-sa-cuda-d-inl1":5.897079,"ggtt-sa-cuda-f-inl0":175.4402,"ggtt-sa-cuda-f-inl1":170.835,"ggtt-sa-cpp-d-inl0-best":0.625262,"ggtt-sa-cpp-d-inl0-none":0.191705,"ggtt-sa-cpp-d-inl1-best":0.481277,"ggtt-sa-cpp-d-inl1-none":0.233871,"ggtt-sa-cpp-f-inl0-best":1.115452,"ggtt-sa-cpp-f-inl0-none":0.200632,"ggtt-sa-cpp-f-inl1-best":0.717432,"ggtt-sa-cpp-f-inl1-none":0.243362,"ggtt-sa-cpp-d-inl0-sse4":0.322312,"ggtt-sa-cpp-d-inl1-sse4":0.278407,"ggtt-sa-cpp-f-inl0-sse4":0.478232,"ggtt-sa-cpp-f-inl1-sse4":0.562256,"ggtt-sa-cpp-d-inl0-avx2":0.559118,"ggtt-sa-cpp-d-inl1-avx2":0.461578,"ggtt-sa-cpp-f-inl0-avx2":1.038209,"ggtt-sa-cpp-f-inl1-avx2":0.717164,"ggtt-sa-cpp-d-inl0-512y":0.625262,"ggtt-sa-cpp-d-inl1-512y":0.481277,"ggtt-sa-cpp-f-inl0-512y":1.115452,"ggtt-sa-cpp-f-inl1-512y":0.717432,"ggtt-sa-cpp-d-inl0-512z":0.374524,"ggtt-sa-cpp-d-inl1-512z":0.347206,"ggtt-sa-cpp-f-inl0-512z":0.781307,"ggtt-sa-cpp-f-inl1-512z":0.564741,"ggttg-sa-cuda-d-inl0":0.818309,"ggttg-sa-cuda-d-inl1":0.818317,"ggttg-sa-cuda-f-inl0":18.42414,"ggttg-sa-cuda-f-inl1":18.37018,"ggttg-sa-cpp-d-inl0-best":0.100087,"ggttg-sa-cpp-d-inl0-none":0.023867,"ggttg-sa-cpp-d-inl1-best":0.089018,"ggttg-sa-cpp-d-inl1-none":0.006266,"ggttg-sa-cpp-f-inl0-best":0.197983,"ggttg-sa-cpp-f-inl0-none":0.024443,"ggttg-sa-cpp-f-inl1-best":0.155876,"ggttg-sa-cpp-f-inl1-none":0.010211,"ggttg-sa-cpp-d-inl0-sse4":0.044909,"ggttg-sa-cpp-d-inl1-sse4":0.041899,"ggttg-sa-cpp-f-inl0-sse4":0.082025,"ggttg-sa-cpp-f-inl1-sse4":0.087215,"ggttg-sa-cpp-d-inl0-avx2":0.087359,"ggttg-sa-cpp-d-inl1-avx2":0.08088,"ggttg-sa-cpp-f-inl0-avx2":0.174366,"ggttg-sa-cpp-f-inl1-avx2":0.140372,"ggttg-sa-cpp-d-inl0-512y":0.100087,"ggttg-sa-cpp-d-inl1-512y":0.089018,"ggttg-sa-cpp-f-inl0-512y":0.197983,"ggttg-sa-cpp-f-inl1-512y":0.155876,"ggttg-sa-cpp-d-inl0-512z":0.072352,"ggttg-sa-cpp-d-inl1-512z":0.064912,"ggttg-sa-cpp-f-inl0-512z":0.150358,"ggttg-sa-cpp-f-inl1-512z":0.115493,"ggttgg-sa-cuda-d-inl0":0.055489,"ggttgg-sa-cuda-d-inl1":0.062788,"ggttgg-sa-cuda-f-inl0":0.308794,"ggttgg-sa-cuda-f-inl1":0.263863,"ggttgg-sa-cpp-d-inl0-best":0.007537,"ggttgg-sa-cpp-d-inl0-none":0.001743,"ggttgg-sa-cpp-d-inl1-best":0.006903,"ggttgg-sa-cpp-d-inl1-none":0.000386,"ggttgg-sa-cpp-f-inl0-best":0.014863,"ggttgg-sa-cpp-f-inl0-none":0.001829,"ggttgg-sa-cpp-f-inl1-best":0.013425,"ggttgg-sa-cpp-f-inl1-none":0.000499,"ggttgg-sa-cpp-d-inl0-sse4":0.00335,"ggttgg-sa-cpp-d-inl1-sse4":0.002792,"ggttgg-sa-cpp-f-inl0-sse4":0.006907,"ggttgg-sa-cpp-f-inl1-sse4":0.006093,"ggttgg-sa-cpp-d-inl0-avx2":0.006673,"ggttgg-sa-cpp-d-inl1-avx2":0.00545,"ggttgg-sa-cpp-f-inl0-avx2":0.013348,"ggttgg-sa-cpp-f-inl1-avx2":0.010681,"ggttgg-sa-cpp-d-inl0-512y":0.007537,"ggttgg-sa-cpp-d-inl1-512y":0.006903,"ggttgg-sa-cpp-f-inl0-512y":0.014863,"ggttgg-sa-cpp-f-inl1-512y":0.013425,"ggttgg-sa-cpp-d-inl0-512z":0.006486,"ggttgg-sa-cpp-d-inl1-512z":0.006547,"ggttgg-sa-cpp-f-inl0-512z":0.013055,"ggttgg-sa-cpp-f-inl1-512z":0.012701},"wl-stats":{"eemumu-sa-cuda-d-inl0":{"avg":48.79672,"median":48.79672,"min":48.79672,"max":48.79672,"count":1},"eemumu-sa-cuda-d-inl1":{"avg":49.58971,"median":49.58971,"min":49.58971,"max":49.58971,"count":1},"eemumu-sa-cuda-f-inl0":{"avg":1485.295,"median":1485.295,"min":1485.295,"max":1485.295,"count":1},"eemumu-sa-cuda-f-inl1":{"avg":1420.555,"median":1420.555,"min":1420.555,"max":1420.555,"count":1},"eemumu-sa-cpp-d-inl0-best":{"avg":5.85542,"median":5.85542,"min":5.85542,"max":5.85542,"count":1},"eemumu-sa-cpp-d-inl0-none":{"avg":1.60346,"median":1.60346,"min":1.60346,"max":1.60346,"count":1},"eemumu-sa-cpp-d-inl1-best":{"avg":11.02532,"median":11.02532,"min":11.02532,"max":11.02532,"count":1},"eemumu-sa-cpp-d-inl1-none":{"avg":4.669919,"median":4.669919,"min":4.669919,"max":4.669919,"count":1},"eemumu-sa-cpp-f-inl0-best":{"avg":12.28219,"median":12.28219,"min":12.28219,"max":12.28219,"count":1},"eemumu-sa-cpp-f-inl0-none":{"avg":1.662875,"median":1.662875,"min":1.662875,"max":1.662875,"count":1},"eemumu-sa-cpp-f-inl1-best":{"avg":27.95492,"median":27.95492,"min":27.95492,"max":27.95492,"count":1},"eemumu-sa-cpp-f-inl1-none":{"avg":4.952863,"median":4.952863,"min":4.952863,"max":4.952863,"count":1},"eemumu-sa-cpp-d-inl0-sse4":{"avg":3.070359,"median":3.070359,"min":3.070359,"max":3.070359,"count":1},"eemumu-sa-cpp-d-inl1-sse4":{"avg":8.24349,"median":8.24349,"min":8.24349,"max":8.24349,"count":1},"eemumu-sa-cpp-f-inl0-sse4":{"avg":6.108306,"median":6.108306,"min":6.108306,"max":6.108306,"count":1},"eemumu-sa-cpp-f-inl1-sse4":{"avg":14.71368,"median":14.71368,"min":14.71368,"max":14.71368,"count":1},"eemumu-sa-cpp-d-inl0-avx2":{"avg":5.434791,"median":5.434791,"min":5.434791,"max":5.434791,"count":1},"eemumu-sa-cpp-d-inl1-avx2":{"avg":11.02532,"median":11.02532,"min":11.02532,"max":11.02532,"count":1},"eemumu-sa-cpp-f-inl0-avx2":{"avg":11.37094,"median":11.37094,"min":11.37094,"max":11.37094,"count":1},"eemumu-sa-cpp-f-inl1-avx2":{"avg":27.61771,"median":27.61771,"min":27.61771,"max":27.61771,"count":1},"eemumu-sa-cpp-d-inl0-512y":{"avg":5.85542,"median":5.85542,"min":5.85542,"max":5.85542,"count":1},"eemumu-sa-cpp-d-inl1-512y":{"avg":10.94437,"median":10.94437,"min":10.94437,"max":10.94437,"count":1},"eemumu-sa-cpp-f-inl0-512y":{"avg":12.28219,"median":12.28219,"min":12.28219,"max":12.28219,"count":1},"eemumu-sa-cpp-f-inl1-512y":{"avg":27.95492,"median":27.95492,"min":27.95492,"max":27.95492,"count":1},"eemumu-sa-cpp-d-inl0-512z":{"avg":4.919846,"median":4.919846,"min":4.919846,"max":4.919846,"count":1},"eemumu-sa-cpp-d-inl1-512z":{"avg":9.140349,"median":9.140349,"min":9.140349,"max":9.140349,"count":1},"eemumu-sa-cpp-f-inl0-512z":{"avg":10.05686,"median":10.05686,"min":10.05686,"max":10.05686,"count":1},"eemumu-sa-cpp-f-inl1-512z":{"avg":20.54445,"median":20.54445,"min":20.54445,"max":20.54445,"count":1},"ggtt-sa-cuda-d-inl0":{"avg":5.745921,"median":5.745921,"min":5.745921,"max":5.745921,"count":1},"ggtt-sa-cuda-d-inl1":{"avg":5.897079,"median":5.897079,"min":5.897079,"max":5.897079,"count":1},"ggtt-sa-cuda-f-inl0":{"avg":175.4402,"median":175.4402,"min":175.4402,"max":175.4402,"count":1},"ggtt-sa-cuda-f-inl1":{"avg":170.835,"median":170.835,"min":170.835,"max":170.835,"count":1},"ggtt-sa-cpp-d-inl0-best":{"avg":0.625262,"median":0.625262,"min":0.625262,"max":0.625262,"count":1},"ggtt-sa-cpp-d-inl0-none":{"avg":0.191705,"median":0.191705,"min":0.191705,"max":0.191705,"count":1},"ggtt-sa-cpp-d-inl1-best":{"avg":0.481277,"median":0.481277,"min":0.481277,"max":0.481277,"count":1},"ggtt-sa-cpp-d-inl1-none":{"avg":0.233871,"median":0.233871,"min":0.233871,"max":0.233871,"count":1},"ggtt-sa-cpp-f-inl0-best":{"avg":1.115452,"median":1.115452,"min":1.115452,"max":1.115452,"count":1},"ggtt-sa-cpp-f-inl0-none":{"avg":0.200632,"median":0.200632,"min":0.200632,"max":0.200632,"count":1},"ggtt-sa-cpp-f-inl1-best":{"avg":0.717432,"median":0.717432,"min":0.717432,"max":0.717432,"count":1},"ggtt-sa-cpp-f-inl1-none":{"avg":0.243362,"median":0.243362,"min":0.243362,"max":0.243362,"count":1},"ggtt-sa-cpp-d-inl0-sse4":{"avg":0.322312,"median":0.322312,"min":0.322312,"max":0.322312,"count":1},"ggtt-sa-cpp-d-inl1-sse4":{"avg":0.278407,"median":0.278407,"min":0.278407,"max":0.278407,"count":1},"ggtt-sa-cpp-f-inl0-sse4":{"avg":0.478232,"median":0.478232,"min":0.478232,"max":0.478232,"count":1},"ggtt-sa-cpp-f-inl1-sse4":{"avg":0.562256,"median":0.562256,"min":0.562256,"max":0.562256,"count":1},"ggtt-sa-cpp-d-inl0-avx2":{"avg":0.559118,"median":0.559118,"min":0.559118,"max":0.559118,"count":1},"ggtt-sa-cpp-d-inl1-avx2":{"avg":0.461578,"median":0.461578,"min":0.461578,"max":0.461578,"count":1},"ggtt-sa-cpp-f-inl0-avx2":{"avg":1.038209,"median":1.038209,"min":1.038209,"max":1.038209,"count":1},"ggtt-sa-cpp-f-inl1-avx2":{"avg":0.717164,"median":0.717164,"min":0.717164,"max":0.717164,"count":1},"ggtt-sa-cpp-d-inl0-512y":{"avg":0.625262,"median":0.625262,"min":0.625262,"max":0.625262,"count":1},"ggtt-sa-cpp-d-inl1-512y":{"avg":0.481277,"median":0.481277,"min":0.481277,"max":0.481277,"count":1},"ggtt-sa-cpp-f-inl0-512y":{"avg":1.115452,"median":1.115452,"min":1.115452,"max":1.115452,"count":1},"ggtt-sa-cpp-f-inl1-512y":{"avg":0.717432,"median":0.717432,"min":0.717432,"max":0.717432,"count":1},"ggtt-sa-cpp-d-inl0-512z":{"avg":0.374524,"median":0.374524,"min":0.374524,"max":0.374524,"count":1},"ggtt-sa-cpp-d-inl1-512z":{"avg":0.347206,"median":0.347206,"min":0.347206,"max":0.347206,"count":1},"ggtt-sa-cpp-f-inl0-512z":{"avg":0.781307,"median":0.781307,"min":0.781307,"max":0.781307,"count":1},"ggtt-sa-cpp-f-inl1-512z":{"avg":0.564741,"median":0.564741,"min":0.564741,"max":0.564741,"count":1},"ggttg-sa-cuda-d-inl0":{"avg":0.818309,"median":0.818309,"min":0.818309,"max":0.818309,"count":1},"ggttg-sa-cuda-d-inl1":{"avg":0.818317,"median":0.818317,"min":0.818317,"max":0.818317,"count":1},"ggttg-sa-cuda-f-inl0":{"avg":18.42414,"median":18.42414,"min":18.42414,"max":18.42414,"count":1},"ggttg-sa-cuda-f-inl1":{"avg":18.37018,"median":18.37018,"min":18.37018,"max":18.37018,"count":1},"ggttg-sa-cpp-d-inl0-best":{"avg":0.100087,"median":0.100087,"min":0.100087,"max":0.100087,"count":1},"ggttg-sa-cpp-d-inl0-none":{"avg":0.023867,"median":0.023867,"min":0.023867,"max":0.023867,"count":1},"ggttg-sa-cpp-d-inl1-best":{"avg":0.089018,"median":0.089018,"min":0.089018,"max":0.089018,"count":1},"ggttg-sa-cpp-d-inl1-none":{"avg":0.006266,"median":0.006266,"min":0.006266,"max":0.006266,"count":1},"ggttg-sa-cpp-f-inl0-best":{"avg":0.197983,"median":0.197983,"min":0.197983,"max":0.197983,"count":1},"ggttg-sa-cpp-f-inl0-none":{"avg":0.024443,"median":0.024443,"min":0.024443,"max":0.024443,"count":1},"ggttg-sa-cpp-f-inl1-best":{"avg":0.155876,"median":0.155876,"min":0.155876,"max":0.155876,"count":1},"ggttg-sa-cpp-f-inl1-none":{"avg":0.010211,"median":0.010211,"min":0.010211,"max":0.010211,"count":1},"ggttg-sa-cpp-d-inl0-sse4":{"avg":0.044909,"median":0.044909,"min":0.044909,"max":0.044909,"count":1},"ggttg-sa-cpp-d-inl1-sse4":{"avg":0.041899,"median":0.041899,"min":0.041899,"max":0.041899,"count":1},"ggttg-sa-cpp-f-inl0-sse4":{"avg":0.082025,"median":0.082025,"min":0.082025,"max":0.082025,"count":1},"ggttg-sa-cpp-f-inl1-sse4":{"avg":0.087215,"median":0.087215,"min":0.087215,"max":0.087215,"count":1},"ggttg-sa-cpp-d-inl0-avx2":{"avg":0.087359,"median":0.087359,"min":0.087359,"max":0.087359,"count":1},"ggttg-sa-cpp-d-inl1-avx2":{"avg":0.08088,"median":0.08088,"min":0.08088,"max":0.08088,"count":1},"ggttg-sa-cpp-f-inl0-avx2":{"avg":0.174366,"median":0.174366,"min":0.174366,"max":0.174366,"count":1},"ggttg-sa-cpp-f-inl1-avx2":{"avg":0.140372,"median":0.140372,"min":0.140372,"max":0.140372,"count":1},"ggttg-sa-cpp-d-inl0-512y":{"avg":0.100087,"median":0.100087,"min":0.100087,"max":0.100087,"count":1},"ggttg-sa-cpp-d-inl1-512y":{"avg":0.089018,"median":0.089018,"min":0.089018,"max":0.089018,"count":1},"ggttg-sa-cpp-f-inl0-512y":{"avg":0.197983,"median":0.197983,"min":0.197983,"max":0.197983,"count":1},"ggttg-sa-cpp-f-inl1-512y":{"avg":0.155876,"median":0.155876,"min":0.155876,"max":0.155876,"count":1},"ggttg-sa-cpp-d-inl0-512z":{"avg":0.072352,"median":0.072352,"min":0.072352,"max":0.072352,"count":1},"ggttg-sa-cpp-d-inl1-512z":{"avg":0.064912,"median":0.064912,"min":0.064912,"max":0.064912,"count":1},"ggttg-sa-cpp-f-inl0-512z":{"avg":0.150358,"median":0.150358,"min":0.150358,"max":0.150358,"count":1},"ggttg-sa-cpp-f-inl1-512z":{"avg":0.115493,"median":0.115493,"min":0.115493,"max":0.115493,"count":1},"ggttgg-sa-cuda-d-inl0":{"avg":0.055489,"median":0.055489,"min":0.055489,"max":0.055489,"count":1},"ggttgg-sa-cuda-d-inl1":{"avg":0.062788,"median":0.062788,"min":0.062788,"max":0.062788,"count":1},"ggttgg-sa-cuda-f-inl0":{"avg":0.308794,"median":0.308794,"min":0.308794,"max":0.308794,"count":1},"ggttgg-sa-cuda-f-inl1":{"avg":0.263863,"median":0.263863,"min":0.263863,"max":0.263863,"count":1},"ggttgg-sa-cpp-d-inl0-best":{"avg":0.007537,"median":0.007537,"min":0.007537,"max":0.007537,"count":1},"ggttgg-sa-cpp-d-inl0-none":{"avg":0.001743,"median":0.001743,"min":0.001743,"max":0.001743,"count":1},"ggttgg-sa-cpp-d-inl1-best":{"avg":0.006903,"median":0.006903,"min":0.006903,"max":0.006903,"count":1},"ggttgg-sa-cpp-d-inl1-none":{"avg":0.000386,"median":0.000386,"min":0.000386,"max":0.000386,"count":1},"ggttgg-sa-cpp-f-inl0-best":{"avg":0.014863,"median":0.014863,"min":0.014863,"max":0.014863,"count":1},"ggttgg-sa-cpp-f-inl0-none":{"avg":0.001829,"median":0.001829,"min":0.001829,"max":0.001829,"count":1},"ggttgg-sa-cpp-f-inl1-best":{"avg":0.013425,"median":0.013425,"min":0.013425,"max":0.013425,"count":1},"ggttgg-sa-cpp-f-inl1-none":{"avg":0.000499,"median":0.000499,"min":0.000499,"max":0.000499,"count":1},"ggttgg-sa-cpp-d-inl0-sse4":{"avg":0.00335,"median":0.00335,"min":0.00335,"max":0.00335,"count":1},"ggttgg-sa-cpp-d-inl1-sse4":{"avg":0.002792,"median":0.002792,"min":0.002792,"max":0.002792,"count":1},"ggttgg-sa-cpp-f-inl0-sse4":{"avg":0.006907,"median":0.006907,"min":0.006907,"max":0.006907,"count":1},"ggttgg-sa-cpp-f-inl1-sse4":{"avg":0.006093,"median":0.006093,"min":0.006093,"max":0.006093,"count":1},"ggttgg-sa-cpp-d-inl0-avx2":{"avg":0.006673,"median":0.006673,"min":0.006673,"max":0.006673,"count":1},"ggttgg-sa-cpp-d-inl1-avx2":{"avg":0.00545,"median":0.00545,"min":0.00545,"max":0.00545,"count":1},"ggttgg-sa-cpp-f-inl0-avx2":{"avg":0.013348,"median":0.013348,"min":0.013348,"max":0.013348,"count":1},"ggttgg-sa-cpp-f-inl1-avx2":{"avg":0.010681,"median":0.010681,"min":0.010681,"max":0.010681,"count":1},"ggttgg-sa-cpp-d-inl0-512y":{"avg":0.007537,"median":0.007537,"min":0.007537,"max":0.007537,"count":1},"ggttgg-sa-cpp-d-inl1-512y":{"avg":0.006903,"median":0.006903,"min":0.006903,"max":0.006903,"count":1},"ggttgg-sa-cpp-f-inl0-512y":{"avg":0.014863,"median":0.014863,"min":0.014863,"max":0.014863,"count":1},"ggttgg-sa-cpp-f-inl1-512y":{"avg":0.013425,"median":0.013425,"min":0.013425,"max":0.013425,"count":1},"ggttgg-sa-cpp-d-inl0-512z":{"avg":0.006486,"median":0.006486,"min":0.006486,"max":0.006486,"count":1},"ggttgg-sa-cpp-d-inl1-512z":{"avg":0.006547,"median":0.006547,"min":0.006547,"max":0.006547,"count":1},"ggttgg-sa-cpp-f-inl0-512z":{"avg":0.013055,"median":0.013055,"min":0.013055,"max":0.013055,"count":1},"ggttgg-sa-cpp-f-inl1-512z":{"avg":0.012701,"median":0.012701,"min":0.012701,"max":0.012701,"count":1}},"log":"ok"},"app":{"version":"ci-v0.7","description":"Madgraph5_aMCatNLO madgraph4gpu benchmark (2022)","cvmfs_checksum":"34ff738c57b9b7a8a398e4769cba101d","bmkdata_checksum":"d4c9152ed732e012ca54b6518bf3de93","bmk_checksum":"3c9f62f161ec52296be50b21648606b0","containment":"docker"}}
diff --git a/mg5amc/madgraph4gpu-2022/mg5amc-madgraph4gpu-2022/jobs/good_1/cvmfs-sft.cern.ch.spec.txt b/mg5amc/madgraph4gpu-2022/mg5amc-madgraph4gpu-2022/jobs/good_1/cvmfs-sft.cern.ch.spec.txt
index 148a74d7ca41bd8802ff605c9616160a57c2cd3b..e93193b11af099d9fcec7425e6a7113ee9e8daf9 100644
--- a/mg5amc/madgraph4gpu-2022/mg5amc-madgraph4gpu-2022/jobs/good_1/cvmfs-sft.cern.ch.spec.txt
+++ b/mg5amc/madgraph4gpu-2022/mg5amc-madgraph4gpu-2022/jobs/good_1/cvmfs-sft.cern.ch.spec.txt
@@ -32,7 +32,6 @@
 ^/lcg/releases/CMake/3.18.4-2ffec/x86_64-centos7-gcc8-opt/bin/grep
 ^/lcg/releases/CMake/3.18.4-2ffec/x86_64-centos7-gcc8-opt/bin/gstrip
 ^/lcg/releases/CMake/3.18.4-2ffec/x86_64-centos7-gcc8-opt/bin/head
-^/lcg/releases/CMake/3.18.4-2ffec/x86_64-centos7-gcc8-opt/bin/hostname
 ^/lcg/releases/CMake/3.18.4-2ffec/x86_64-centos7-gcc8-opt/bin/ld
 ^/lcg/releases/CMake/3.18.4-2ffec/x86_64-centos7-gcc8-opt/bin/ls
 ^/lcg/releases/CMake/3.18.4-2ffec/x86_64-centos7-gcc8-opt/bin/make
@@ -120,7 +119,6 @@
 ^/lcg/releases/binutils/2.37-4177a/x86_64-centos7/bin/grep
 ^/lcg/releases/binutils/2.37-4177a/x86_64-centos7/bin/gstrip
 ^/lcg/releases/binutils/2.37-4177a/x86_64-centos7/bin/head
-^/lcg/releases/binutils/2.37-4177a/x86_64-centos7/bin/hostname
 ^/lcg/releases/binutils/2.37-4177a/x86_64-centos7/bin/ld
 ^/lcg/releases/binutils/2.37-4177a/x86_64-centos7/bin/ls
 ^/lcg/releases/binutils/2.37-4177a/x86_64-centos7/bin/make
@@ -176,7 +174,6 @@
 ^/lcg/releases/binutils/2.37-4177a/x86_64-centos7/lib/liblber-2.4.so.2
 ^/lcg/releases/binutils/2.37-4177a/x86_64-centos7/lib/libldap-2.4.so.2
 ^/lcg/releases/binutils/2.37-4177a/x86_64-centos7/lib/libm.so.6
-^/lcg/releases/binutils/2.37-4177a/x86_64-centos7/lib/libnsl.so.1
 ^/lcg/releases/binutils/2.37-4177a/x86_64-centos7/lib/libnspr4.so
 ^/lcg/releases/binutils/2.37-4177a/x86_64-centos7/lib/libnss3.so
 ^/lcg/releases/binutils/2.37-4177a/x86_64-centos7/lib/libnss_dns.so.2
@@ -185,7 +182,6 @@
 ^/lcg/releases/binutils/2.37-4177a/x86_64-centos7/lib/libnsssysinit.so
 ^/lcg/releases/binutils/2.37-4177a/x86_64-centos7/lib/libnssutil3.so
 ^/lcg/releases/binutils/2.37-4177a/x86_64-centos7/lib/libnvidia-ml.so.1
-^/lcg/releases/binutils/2.37-4177a/x86_64-centos7/lib/libnvidia-ptxjitcompiler.so.1
 ^/lcg/releases/binutils/2.37-4177a/x86_64-centos7/lib/libpcre.so.1
 ^/lcg/releases/binutils/2.37-4177a/x86_64-centos7/lib/libplc4.so
 ^/lcg/releases/binutils/2.37-4177a/x86_64-centos7/lib/libplds4.so
@@ -240,7 +236,6 @@
 ^/lcg/releases/ccache/4.3-ed8d3/x86_64-centos7-gcc8-opt/bin/grep
 ^/lcg/releases/ccache/4.3-ed8d3/x86_64-centos7-gcc8-opt/bin/gstrip
 ^/lcg/releases/ccache/4.3-ed8d3/x86_64-centos7-gcc8-opt/bin/head
-^/lcg/releases/ccache/4.3-ed8d3/x86_64-centos7-gcc8-opt/bin/hostname
 ^/lcg/releases/ccache/4.3-ed8d3/x86_64-centos7-gcc8-opt/bin/ld
 ^/lcg/releases/ccache/4.3-ed8d3/x86_64-centos7-gcc8-opt/bin/ls
 ^/lcg/releases/ccache/4.3-ed8d3/x86_64-centos7-gcc8-opt/bin/make
@@ -308,7 +303,6 @@
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/grep
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gstrip
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/head
-^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/hostname
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/ld
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/ls
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/make
@@ -381,6 +375,7 @@
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/backward/bits
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/backward/ctype.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/backward/dlfcn.h
+^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/backward/emmintrin.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/backward/endian.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/backward/errno.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/backward/fcntl.h
@@ -394,8 +389,11 @@
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/backward/linux
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/backward/locale.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/backward/math.h
+^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/backward/mm_malloc.h
+^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/backward/mmintrin.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/backward/netdb.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/backward/netinet
+^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/backward/pmmintrin.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/backward/pthread.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/backward/regex.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/backward/rpc
@@ -415,9 +413,11 @@
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/backward/tbb
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/backward/time.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/backward/unistd.h
+^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/backward/unistd.h.gch
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/backward/wchar.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/backward/wctype.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/backward/xlocale.h
+^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/backward/xmmintrin.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/backward
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/bit
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/bits/algorithmfwd.h
@@ -495,6 +495,7 @@
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/bits/locale_facets_nonio.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/bits/locale_facets_nonio.tcc
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/bits/localefwd.h
+^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/bits/math-finite.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/bits/mathcalls.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/bits/mathdef.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/bits/mathinline.h
@@ -622,6 +623,7 @@
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/debug/debug.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/debug
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/dlfcn.h
+^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/emmintrin.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/endian.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/errno.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/exception
@@ -661,6 +663,8 @@
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/map
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/math.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/memory
+^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/mm_malloc.h
+^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/mmintrin.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/mutex
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/netdb.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/netinet
@@ -668,6 +672,7 @@
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/numeric
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/optional
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/ostream
+^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/pmmintrin.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/pstl/execution_defs.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/pstl/glue_algorithm_defs.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/pstl/glue_memory_defs.h
@@ -719,6 +724,7 @@
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/type_traits
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/typeinfo
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/unistd.h
+^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/unistd.h.gch
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/unordered_map
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/utility
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/variant
@@ -761,6 +767,7 @@
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/x86_64-pc-linux-gnu/bits/inf.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/x86_64-pc-linux-gnu/bits/local_lim.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/x86_64-pc-linux-gnu/bits/locale.h
+^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/x86_64-pc-linux-gnu/bits/math-finite.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/x86_64-pc-linux-gnu/bits/mathcalls.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/x86_64-pc-linux-gnu/bits/mathdef.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/x86_64-pc-linux-gnu/bits/mathinline.h
@@ -806,6 +813,7 @@
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/x86_64-pc-linux-gnu/bits
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/x86_64-pc-linux-gnu/ctype.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/x86_64-pc-linux-gnu/dlfcn.h
+^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/x86_64-pc-linux-gnu/emmintrin.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/x86_64-pc-linux-gnu/endian.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/x86_64-pc-linux-gnu/errno.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/x86_64-pc-linux-gnu/fcntl.h
@@ -819,8 +827,11 @@
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/x86_64-pc-linux-gnu/linux
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/x86_64-pc-linux-gnu/locale.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/x86_64-pc-linux-gnu/math.h
+^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/x86_64-pc-linux-gnu/mm_malloc.h
+^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/x86_64-pc-linux-gnu/mmintrin.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/x86_64-pc-linux-gnu/netdb.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/x86_64-pc-linux-gnu/netinet
+^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/x86_64-pc-linux-gnu/pmmintrin.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/x86_64-pc-linux-gnu/pthread.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/x86_64-pc-linux-gnu/regex.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/x86_64-pc-linux-gnu/rpc
@@ -840,11 +851,14 @@
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/x86_64-pc-linux-gnu/tbb
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/x86_64-pc-linux-gnu/time.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/x86_64-pc-linux-gnu/unistd.h
+^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/x86_64-pc-linux-gnu/unistd.h.gch
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/x86_64-pc-linux-gnu/wchar.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/x86_64-pc-linux-gnu/wctype.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/x86_64-pc-linux-gnu/xlocale.h
+^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/x86_64-pc-linux-gnu/xmmintrin.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/x86_64-pc-linux-gnu
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/xlocale.h
+^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0/xmmintrin.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++/11.2.0
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/c++
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/cassert
@@ -870,6 +884,7 @@
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/cxxabi.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/debug
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/dlfcn.h
+^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/emmintrin.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/endian.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/errno.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/exception
@@ -901,6 +916,8 @@
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/map
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/math.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/memory
+^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/mm_malloc.h
+^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/mmintrin.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/mutex
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/netdb.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/netinet
@@ -908,6 +925,7 @@
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/numeric
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/optional
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/ostream
+^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/pmmintrin.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/pstl
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/pthread.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/pthread.h.gch
@@ -943,6 +961,7 @@
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/type_traits
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/typeinfo
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/unistd.h
+^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/unistd.h.gch
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/unordered_map
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/utility
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/variant
@@ -951,6 +970,7 @@
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/wchar.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/wctype.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/xlocale.h
+^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/include/xmmintrin.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/ld
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib/gcc/crt1.o
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib/gcc/crti.o
@@ -1038,6 +1058,7 @@
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib/gcc/x86_64-pc-linux-gnu/11.2.0/include-fixed/tbb
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib/gcc/x86_64-pc-linux-gnu/11.2.0/include-fixed/time.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib/gcc/x86_64-pc-linux-gnu/11.2.0/include-fixed/unistd.h
+^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib/gcc/x86_64-pc-linux-gnu/11.2.0/include-fixed/unistd.h.gch
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib/gcc/x86_64-pc-linux-gnu/11.2.0/include-fixed/wchar.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib/gcc/x86_64-pc-linux-gnu/11.2.0/include-fixed/wctype.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib/gcc/x86_64-pc-linux-gnu/11.2.0/include-fixed/xlocale.h
@@ -1090,6 +1111,7 @@
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib/gcc/x86_64-pc-linux-gnu/11.2.0/include/tbb
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib/gcc/x86_64-pc-linux-gnu/11.2.0/include/time.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib/gcc/x86_64-pc-linux-gnu/11.2.0/include/unistd.h
+^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib/gcc/x86_64-pc-linux-gnu/11.2.0/include/unistd.h.gch
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib/gcc/x86_64-pc-linux-gnu/11.2.0/include/wchar.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib/gcc/x86_64-pc-linux-gnu/11.2.0/include/wctype.h
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib/gcc/x86_64-pc-linux-gnu/11.2.0/include/xlocale.h
@@ -1149,7 +1171,6 @@
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib/liblber-2.4.so.2
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib/libldap-2.4.so.2
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib/libm.so.6
-^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib/libnsl.so.1
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib/libnspr4.so
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib/libnss3.so
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib/libnss_dns.so.2
@@ -1158,7 +1179,6 @@
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib/libnsssysinit.so
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib/libnssutil3.so
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib/libnvidia-ml.so.1
-^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib/libnvidia-ptxjitcompiler.so.1
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib/libpcre.so.1
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib/libplc4.so
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib/libplds4.so
@@ -1225,7 +1245,6 @@
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib64/libm.a
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib64/libm.so
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib64/libm.so.6
-^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib64/libnsl.so.1
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib64/libnspr4.so
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib64/libnss3.so
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib64/libnss_dns.so.2
@@ -1234,7 +1253,6 @@
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib64/libnsssysinit.so
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib64/libnssutil3.so
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib64/libnvidia-ml.so.1
-^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib64/libnvidia-ptxjitcompiler.so.1
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib64/libpcre.so.1
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib64/libplc4.so
 ^/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/lib64/libplds4.so
diff --git a/mg5amc/madgraph4gpu-2022/mg5amc-madgraph4gpu-2022/jobs/good_1/joburl.txt b/mg5amc/madgraph4gpu-2022/mg5amc-madgraph4gpu-2022/jobs/good_1/joburl.txt
index 7a30c34e9bfcde7d6e45a951f8170b8745ad8991..a461da7bfdb40800d41cf7bf7d1f0b2a919586ee 100644
--- a/mg5amc/madgraph4gpu-2022/mg5amc-madgraph4gpu-2022/jobs/good_1/joburl.txt
+++ b/mg5amc/madgraph4gpu-2022/mg5amc-madgraph4gpu-2022/jobs/good_1/joburl.txt
@@ -1 +1 @@
-https://gitlab.cern.ch/valassi/hep-workloads/-/jobs/24278318
+https://gitlab.cern.ch/hep-benchmarks/hep-workloads/-/jobs/24758928
diff --git a/mg5amc/madgraph4gpu-2022/mg5amc-madgraph4gpu-2022/jobs/good_1/mg5amc-madgraph4gpu-2022_summary.json b/mg5amc/madgraph4gpu-2022/mg5amc-madgraph4gpu-2022/jobs/good_1/mg5amc-madgraph4gpu-2022_summary.json
index 3e14db986d43eaf3d86b4ea7cf5aeb61f946c35f..21a830720fb16e27f8d9ab3e35c796b4fef226bc 100644
--- a/mg5amc/madgraph4gpu-2022/mg5amc-madgraph4gpu-2022/jobs/good_1/mg5amc-madgraph4gpu-2022_summary.json
+++ b/mg5amc/madgraph4gpu-2022/mg5amc-madgraph4gpu-2022/jobs/good_1/mg5amc-madgraph4gpu-2022_summary.json
@@ -7,755 +7,755 @@
   },
   "report": {
     "wl-scores": {
-      "eemumu-sa-cuda-d-inl0": 1130.432,
-      "eemumu-sa-cuda-d-inl1": 1128.067,
-      "eemumu-sa-cuda-f-inl0": 3036.306,
-      "eemumu-sa-cuda-f-inl1": 3029.1,
-      "eemumu-sa-cpp-d-inl0-best": 5.846252,
-      "eemumu-sa-cpp-d-inl0-none": 1.602924,
-      "eemumu-sa-cpp-d-inl1-best": 10.23114,
-      "eemumu-sa-cpp-d-inl1-none": 4.650216,
-      "eemumu-sa-cpp-f-inl0-best": 12.06278,
-      "eemumu-sa-cpp-f-inl0-none": 1.655938,
-      "eemumu-sa-cpp-f-inl1-best": 25.14256,
-      "eemumu-sa-cpp-f-inl1-none": 4.936409,
-      "eemumu-sa-cpp-d-inl0-sse4": 3.06225,
-      "eemumu-sa-cpp-d-inl1-sse4": 7.925393,
-      "eemumu-sa-cpp-f-inl0-sse4": 6.08885,
-      "eemumu-sa-cpp-f-inl1-sse4": 14.29687,
-      "eemumu-sa-cpp-d-inl0-avx2": 5.372729,
-      "eemumu-sa-cpp-d-inl1-avx2": 10.23114,
-      "eemumu-sa-cpp-f-inl0-avx2": 11.23831,
-      "eemumu-sa-cpp-f-inl1-avx2": 24.62085,
-      "eemumu-sa-cpp-d-inl0-512y": 5.846252,
-      "eemumu-sa-cpp-d-inl1-512y": 10.21613,
-      "eemumu-sa-cpp-f-inl0-512y": 12.06278,
-      "eemumu-sa-cpp-f-inl1-512y": 25.14256,
-      "eemumu-sa-cpp-d-inl0-512z": 4.743013,
-      "eemumu-sa-cpp-d-inl1-512z": 8.547101,
-      "eemumu-sa-cpp-f-inl0-512z": 9.644016,
-      "eemumu-sa-cpp-f-inl1-512z": 18.31693,
-      "ggtt-sa-cuda-d-inl0": 130.0122,
-      "ggtt-sa-cuda-d-inl1": 130.2486,
-      "ggtt-sa-cuda-f-inl0": 363.6906,
-      "ggtt-sa-cuda-f-inl1": 363.4642,
-      "ggtt-sa-cpp-d-inl0-best": 0.621275,
-      "ggtt-sa-cpp-d-inl0-none": 0.191205,
-      "ggtt-sa-cpp-d-inl1-best": 0.4756,
-      "ggtt-sa-cpp-d-inl1-none": 0.233498,
-      "ggtt-sa-cpp-f-inl0-best": 1.112862,
-      "ggtt-sa-cpp-f-inl0-none": 0.199978,
-      "ggtt-sa-cpp-f-inl1-best": 0.709898,
-      "ggtt-sa-cpp-f-inl1-none": 0.242443,
-      "ggtt-sa-cpp-d-inl0-sse4": 0.320444,
-      "ggtt-sa-cpp-d-inl1-sse4": 0.276818,
-      "ggtt-sa-cpp-f-inl0-sse4": 0.476373,
-      "ggtt-sa-cpp-f-inl1-sse4": 0.560182,
-      "ggtt-sa-cpp-d-inl0-avx2": 0.557379,
-      "ggtt-sa-cpp-d-inl1-avx2": 0.459304,
-      "ggtt-sa-cpp-f-inl0-avx2": 1.035333,
-      "ggtt-sa-cpp-f-inl1-avx2": 0.701411,
-      "ggtt-sa-cpp-d-inl0-512y": 0.621275,
-      "ggtt-sa-cpp-d-inl1-512y": 0.4756,
-      "ggtt-sa-cpp-f-inl0-512y": 1.112862,
-      "ggtt-sa-cpp-f-inl1-512y": 0.709898,
-      "ggtt-sa-cpp-d-inl0-512z": 0.373228,
-      "ggtt-sa-cpp-d-inl1-512z": 0.343774,
-      "ggtt-sa-cpp-f-inl0-512z": 0.776214,
-      "ggtt-sa-cpp-f-inl1-512z": 0.563786,
-      "ggttg-sa-cuda-d-inl0": 13.42965,
-      "ggttg-sa-cuda-d-inl1": 13.42074,
-      "ggttg-sa-cuda-f-inl0": 45.87926,
-      "ggttg-sa-cuda-f-inl1": 45.53218,
-      "ggttg-sa-cpp-d-inl0-best": 0.100039,
-      "ggttg-sa-cpp-d-inl0-none": 0.02382,
-      "ggttg-sa-cpp-d-inl1-best": 0.088939,
-      "ggttg-sa-cpp-d-inl1-none": 0.006257,
-      "ggttg-sa-cpp-f-inl0-best": 0.19736,
-      "ggttg-sa-cpp-f-inl0-none": 0.024398,
-      "ggttg-sa-cpp-f-inl1-best": 0.155494,
-      "ggttg-sa-cpp-f-inl1-none": 0.010191,
-      "ggttg-sa-cpp-d-inl0-sse4": 0.044798,
-      "ggttg-sa-cpp-d-inl1-sse4": 0.041744,
-      "ggttg-sa-cpp-f-inl0-sse4": 0.081961,
-      "ggttg-sa-cpp-f-inl1-sse4": 0.087043,
-      "ggttg-sa-cpp-d-inl0-avx2": 0.087299,
-      "ggttg-sa-cpp-d-inl1-avx2": 0.080643,
-      "ggttg-sa-cpp-f-inl0-avx2": 0.174154,
-      "ggttg-sa-cpp-f-inl1-avx2": 0.140233,
-      "ggttg-sa-cpp-d-inl0-512y": 0.100039,
-      "ggttg-sa-cpp-d-inl1-512y": 0.088939,
-      "ggttg-sa-cpp-f-inl0-512y": 0.19736,
-      "ggttg-sa-cpp-f-inl1-512y": 0.155494,
-      "ggttg-sa-cpp-d-inl0-512z": 0.072167,
-      "ggttg-sa-cpp-d-inl1-512z": 0.064795,
-      "ggttg-sa-cpp-f-inl0-512z": 0.150164,
-      "ggttg-sa-cpp-f-inl1-512z": 0.11501,
-      "ggttgg-sa-cuda-d-inl0": 0.420085,
-      "ggttgg-sa-cuda-d-inl1": 0.386847,
-      "ggttgg-sa-cuda-f-inl0": 0.868273,
-      "ggttgg-sa-cuda-f-inl1": 0.776756,
-      "ggttgg-sa-cpp-d-inl0-best": 0.007535,
-      "ggttgg-sa-cpp-d-inl0-none": 0.001741,
-      "ggttgg-sa-cpp-d-inl1-best": 0.006889,
+      "eemumu-sa-cuda-d-inl0": 48.79672,
+      "eemumu-sa-cuda-d-inl1": 49.58971,
+      "eemumu-sa-cuda-f-inl0": 1485.295,
+      "eemumu-sa-cuda-f-inl1": 1420.555,
+      "eemumu-sa-cpp-d-inl0-best": 5.85542,
+      "eemumu-sa-cpp-d-inl0-none": 1.60346,
+      "eemumu-sa-cpp-d-inl1-best": 11.02532,
+      "eemumu-sa-cpp-d-inl1-none": 4.669919,
+      "eemumu-sa-cpp-f-inl0-best": 12.28219,
+      "eemumu-sa-cpp-f-inl0-none": 1.662875,
+      "eemumu-sa-cpp-f-inl1-best": 27.95492,
+      "eemumu-sa-cpp-f-inl1-none": 4.952863,
+      "eemumu-sa-cpp-d-inl0-sse4": 3.070359,
+      "eemumu-sa-cpp-d-inl1-sse4": 8.24349,
+      "eemumu-sa-cpp-f-inl0-sse4": 6.108306,
+      "eemumu-sa-cpp-f-inl1-sse4": 14.71368,
+      "eemumu-sa-cpp-d-inl0-avx2": 5.434791,
+      "eemumu-sa-cpp-d-inl1-avx2": 11.02532,
+      "eemumu-sa-cpp-f-inl0-avx2": 11.37094,
+      "eemumu-sa-cpp-f-inl1-avx2": 27.61771,
+      "eemumu-sa-cpp-d-inl0-512y": 5.85542,
+      "eemumu-sa-cpp-d-inl1-512y": 10.94437,
+      "eemumu-sa-cpp-f-inl0-512y": 12.28219,
+      "eemumu-sa-cpp-f-inl1-512y": 27.95492,
+      "eemumu-sa-cpp-d-inl0-512z": 4.919846,
+      "eemumu-sa-cpp-d-inl1-512z": 9.140349,
+      "eemumu-sa-cpp-f-inl0-512z": 10.05686,
+      "eemumu-sa-cpp-f-inl1-512z": 20.54445,
+      "ggtt-sa-cuda-d-inl0": 5.745921,
+      "ggtt-sa-cuda-d-inl1": 5.897079,
+      "ggtt-sa-cuda-f-inl0": 175.4402,
+      "ggtt-sa-cuda-f-inl1": 170.835,
+      "ggtt-sa-cpp-d-inl0-best": 0.625262,
+      "ggtt-sa-cpp-d-inl0-none": 0.191705,
+      "ggtt-sa-cpp-d-inl1-best": 0.481277,
+      "ggtt-sa-cpp-d-inl1-none": 0.233871,
+      "ggtt-sa-cpp-f-inl0-best": 1.115452,
+      "ggtt-sa-cpp-f-inl0-none": 0.200632,
+      "ggtt-sa-cpp-f-inl1-best": 0.717432,
+      "ggtt-sa-cpp-f-inl1-none": 0.243362,
+      "ggtt-sa-cpp-d-inl0-sse4": 0.322312,
+      "ggtt-sa-cpp-d-inl1-sse4": 0.278407,
+      "ggtt-sa-cpp-f-inl0-sse4": 0.478232,
+      "ggtt-sa-cpp-f-inl1-sse4": 0.562256,
+      "ggtt-sa-cpp-d-inl0-avx2": 0.559118,
+      "ggtt-sa-cpp-d-inl1-avx2": 0.461578,
+      "ggtt-sa-cpp-f-inl0-avx2": 1.038209,
+      "ggtt-sa-cpp-f-inl1-avx2": 0.717164,
+      "ggtt-sa-cpp-d-inl0-512y": 0.625262,
+      "ggtt-sa-cpp-d-inl1-512y": 0.481277,
+      "ggtt-sa-cpp-f-inl0-512y": 1.115452,
+      "ggtt-sa-cpp-f-inl1-512y": 0.717432,
+      "ggtt-sa-cpp-d-inl0-512z": 0.374524,
+      "ggtt-sa-cpp-d-inl1-512z": 0.347206,
+      "ggtt-sa-cpp-f-inl0-512z": 0.781307,
+      "ggtt-sa-cpp-f-inl1-512z": 0.564741,
+      "ggttg-sa-cuda-d-inl0": 0.818309,
+      "ggttg-sa-cuda-d-inl1": 0.818317,
+      "ggttg-sa-cuda-f-inl0": 18.42414,
+      "ggttg-sa-cuda-f-inl1": 18.37018,
+      "ggttg-sa-cpp-d-inl0-best": 0.100087,
+      "ggttg-sa-cpp-d-inl0-none": 0.023867,
+      "ggttg-sa-cpp-d-inl1-best": 0.089018,
+      "ggttg-sa-cpp-d-inl1-none": 0.006266,
+      "ggttg-sa-cpp-f-inl0-best": 0.197983,
+      "ggttg-sa-cpp-f-inl0-none": 0.024443,
+      "ggttg-sa-cpp-f-inl1-best": 0.155876,
+      "ggttg-sa-cpp-f-inl1-none": 0.010211,
+      "ggttg-sa-cpp-d-inl0-sse4": 0.044909,
+      "ggttg-sa-cpp-d-inl1-sse4": 0.041899,
+      "ggttg-sa-cpp-f-inl0-sse4": 0.082025,
+      "ggttg-sa-cpp-f-inl1-sse4": 0.087215,
+      "ggttg-sa-cpp-d-inl0-avx2": 0.087359,
+      "ggttg-sa-cpp-d-inl1-avx2": 0.08088,
+      "ggttg-sa-cpp-f-inl0-avx2": 0.174366,
+      "ggttg-sa-cpp-f-inl1-avx2": 0.140372,
+      "ggttg-sa-cpp-d-inl0-512y": 0.100087,
+      "ggttg-sa-cpp-d-inl1-512y": 0.089018,
+      "ggttg-sa-cpp-f-inl0-512y": 0.197983,
+      "ggttg-sa-cpp-f-inl1-512y": 0.155876,
+      "ggttg-sa-cpp-d-inl0-512z": 0.072352,
+      "ggttg-sa-cpp-d-inl1-512z": 0.064912,
+      "ggttg-sa-cpp-f-inl0-512z": 0.150358,
+      "ggttg-sa-cpp-f-inl1-512z": 0.115493,
+      "ggttgg-sa-cuda-d-inl0": 0.055489,
+      "ggttgg-sa-cuda-d-inl1": 0.062788,
+      "ggttgg-sa-cuda-f-inl0": 0.308794,
+      "ggttgg-sa-cuda-f-inl1": 0.263863,
+      "ggttgg-sa-cpp-d-inl0-best": 0.007537,
+      "ggttgg-sa-cpp-d-inl0-none": 0.001743,
+      "ggttgg-sa-cpp-d-inl1-best": 0.006903,
       "ggttgg-sa-cpp-d-inl1-none": 0.000386,
-      "ggttgg-sa-cpp-f-inl0-best": 0.014947,
-      "ggttgg-sa-cpp-f-inl0-none": 0.001824,
-      "ggttgg-sa-cpp-f-inl1-best": 0.013404,
+      "ggttgg-sa-cpp-f-inl0-best": 0.014863,
+      "ggttgg-sa-cpp-f-inl0-none": 0.001829,
+      "ggttgg-sa-cpp-f-inl1-best": 0.013425,
       "ggttgg-sa-cpp-f-inl1-none": 0.000499,
-      "ggttgg-sa-cpp-d-inl0-sse4": 0.003343,
-      "ggttgg-sa-cpp-d-inl1-sse4": 0.002787,
-      "ggttgg-sa-cpp-f-inl0-sse4": 0.006896,
-      "ggttgg-sa-cpp-f-inl1-sse4": 0.006075,
-      "ggttgg-sa-cpp-d-inl0-avx2": 0.006661,
-      "ggttgg-sa-cpp-d-inl1-avx2": 0.005439,
-      "ggttgg-sa-cpp-f-inl0-avx2": 0.013351,
-      "ggttgg-sa-cpp-f-inl1-avx2": 0.010642,
-      "ggttgg-sa-cpp-d-inl0-512y": 0.007535,
-      "ggttgg-sa-cpp-d-inl1-512y": 0.006889,
-      "ggttgg-sa-cpp-f-inl0-512y": 0.014947,
-      "ggttgg-sa-cpp-f-inl1-512y": 0.013404,
-      "ggttgg-sa-cpp-d-inl0-512z": 0.006467,
-      "ggttgg-sa-cpp-d-inl1-512z": 0.006525,
-      "ggttgg-sa-cpp-f-inl0-512z": 0.013052,
-      "ggttgg-sa-cpp-f-inl1-512z": 0.01263
+      "ggttgg-sa-cpp-d-inl0-sse4": 0.00335,
+      "ggttgg-sa-cpp-d-inl1-sse4": 0.002792,
+      "ggttgg-sa-cpp-f-inl0-sse4": 0.006907,
+      "ggttgg-sa-cpp-f-inl1-sse4": 0.006093,
+      "ggttgg-sa-cpp-d-inl0-avx2": 0.006673,
+      "ggttgg-sa-cpp-d-inl1-avx2": 0.00545,
+      "ggttgg-sa-cpp-f-inl0-avx2": 0.013348,
+      "ggttgg-sa-cpp-f-inl1-avx2": 0.010681,
+      "ggttgg-sa-cpp-d-inl0-512y": 0.007537,
+      "ggttgg-sa-cpp-d-inl1-512y": 0.006903,
+      "ggttgg-sa-cpp-f-inl0-512y": 0.014863,
+      "ggttgg-sa-cpp-f-inl1-512y": 0.013425,
+      "ggttgg-sa-cpp-d-inl0-512z": 0.006486,
+      "ggttgg-sa-cpp-d-inl1-512z": 0.006547,
+      "ggttgg-sa-cpp-f-inl0-512z": 0.013055,
+      "ggttgg-sa-cpp-f-inl1-512z": 0.012701
     },
     "wl-stats": {
       "eemumu-sa-cuda-d-inl0": {
-        "avg": 1130.432,
-        "median": 1130.432,
-        "min": 1130.432,
-        "max": 1130.432,
+        "avg": 48.79672,
+        "median": 48.79672,
+        "min": 48.79672,
+        "max": 48.79672,
         "count": 1
       },
       "eemumu-sa-cuda-d-inl1": {
-        "avg": 1128.067,
-        "median": 1128.067,
-        "min": 1128.067,
-        "max": 1128.067,
+        "avg": 49.58971,
+        "median": 49.58971,
+        "min": 49.58971,
+        "max": 49.58971,
         "count": 1
       },
       "eemumu-sa-cuda-f-inl0": {
-        "avg": 3036.306,
-        "median": 3036.306,
-        "min": 3036.306,
-        "max": 3036.306,
+        "avg": 1485.295,
+        "median": 1485.295,
+        "min": 1485.295,
+        "max": 1485.295,
         "count": 1
       },
       "eemumu-sa-cuda-f-inl1": {
-        "avg": 3029.1,
-        "median": 3029.1,
-        "min": 3029.1,
-        "max": 3029.1,
+        "avg": 1420.555,
+        "median": 1420.555,
+        "min": 1420.555,
+        "max": 1420.555,
         "count": 1
       },
       "eemumu-sa-cpp-d-inl0-best": {
-        "avg": 5.846252,
-        "median": 5.846252,
-        "min": 5.846252,
-        "max": 5.846252,
+        "avg": 5.85542,
+        "median": 5.85542,
+        "min": 5.85542,
+        "max": 5.85542,
         "count": 1
       },
       "eemumu-sa-cpp-d-inl0-none": {
-        "avg": 1.602924,
-        "median": 1.602924,
-        "min": 1.602924,
-        "max": 1.602924,
+        "avg": 1.60346,
+        "median": 1.60346,
+        "min": 1.60346,
+        "max": 1.60346,
         "count": 1
       },
       "eemumu-sa-cpp-d-inl1-best": {
-        "avg": 10.23114,
-        "median": 10.23114,
-        "min": 10.23114,
-        "max": 10.23114,
+        "avg": 11.02532,
+        "median": 11.02532,
+        "min": 11.02532,
+        "max": 11.02532,
         "count": 1
       },
       "eemumu-sa-cpp-d-inl1-none": {
-        "avg": 4.650216,
-        "median": 4.650216,
-        "min": 4.650216,
-        "max": 4.650216,
+        "avg": 4.669919,
+        "median": 4.669919,
+        "min": 4.669919,
+        "max": 4.669919,
         "count": 1
       },
       "eemumu-sa-cpp-f-inl0-best": {
-        "avg": 12.06278,
-        "median": 12.06278,
-        "min": 12.06278,
-        "max": 12.06278,
+        "avg": 12.28219,
+        "median": 12.28219,
+        "min": 12.28219,
+        "max": 12.28219,
         "count": 1
       },
       "eemumu-sa-cpp-f-inl0-none": {
-        "avg": 1.655938,
-        "median": 1.655938,
-        "min": 1.655938,
-        "max": 1.655938,
+        "avg": 1.662875,
+        "median": 1.662875,
+        "min": 1.662875,
+        "max": 1.662875,
         "count": 1
       },
       "eemumu-sa-cpp-f-inl1-best": {
-        "avg": 25.14256,
-        "median": 25.14256,
-        "min": 25.14256,
-        "max": 25.14256,
+        "avg": 27.95492,
+        "median": 27.95492,
+        "min": 27.95492,
+        "max": 27.95492,
         "count": 1
       },
       "eemumu-sa-cpp-f-inl1-none": {
-        "avg": 4.936409,
-        "median": 4.936409,
-        "min": 4.936409,
-        "max": 4.936409,
+        "avg": 4.952863,
+        "median": 4.952863,
+        "min": 4.952863,
+        "max": 4.952863,
         "count": 1
       },
       "eemumu-sa-cpp-d-inl0-sse4": {
-        "avg": 3.06225,
-        "median": 3.06225,
-        "min": 3.06225,
-        "max": 3.06225,
+        "avg": 3.070359,
+        "median": 3.070359,
+        "min": 3.070359,
+        "max": 3.070359,
         "count": 1
       },
       "eemumu-sa-cpp-d-inl1-sse4": {
-        "avg": 7.925393,
-        "median": 7.925393,
-        "min": 7.925393,
-        "max": 7.925393,
+        "avg": 8.24349,
+        "median": 8.24349,
+        "min": 8.24349,
+        "max": 8.24349,
         "count": 1
       },
       "eemumu-sa-cpp-f-inl0-sse4": {
-        "avg": 6.08885,
-        "median": 6.08885,
-        "min": 6.08885,
-        "max": 6.08885,
+        "avg": 6.108306,
+        "median": 6.108306,
+        "min": 6.108306,
+        "max": 6.108306,
         "count": 1
       },
       "eemumu-sa-cpp-f-inl1-sse4": {
-        "avg": 14.29687,
-        "median": 14.29687,
-        "min": 14.29687,
-        "max": 14.29687,
+        "avg": 14.71368,
+        "median": 14.71368,
+        "min": 14.71368,
+        "max": 14.71368,
         "count": 1
       },
       "eemumu-sa-cpp-d-inl0-avx2": {
-        "avg": 5.372729,
-        "median": 5.372729,
-        "min": 5.372729,
-        "max": 5.372729,
+        "avg": 5.434791,
+        "median": 5.434791,
+        "min": 5.434791,
+        "max": 5.434791,
         "count": 1
       },
       "eemumu-sa-cpp-d-inl1-avx2": {
-        "avg": 10.23114,
-        "median": 10.23114,
-        "min": 10.23114,
-        "max": 10.23114,
+        "avg": 11.02532,
+        "median": 11.02532,
+        "min": 11.02532,
+        "max": 11.02532,
         "count": 1
       },
       "eemumu-sa-cpp-f-inl0-avx2": {
-        "avg": 11.23831,
-        "median": 11.23831,
-        "min": 11.23831,
-        "max": 11.23831,
+        "avg": 11.37094,
+        "median": 11.37094,
+        "min": 11.37094,
+        "max": 11.37094,
         "count": 1
       },
       "eemumu-sa-cpp-f-inl1-avx2": {
-        "avg": 24.62085,
-        "median": 24.62085,
-        "min": 24.62085,
-        "max": 24.62085,
+        "avg": 27.61771,
+        "median": 27.61771,
+        "min": 27.61771,
+        "max": 27.61771,
         "count": 1
       },
       "eemumu-sa-cpp-d-inl0-512y": {
-        "avg": 5.846252,
-        "median": 5.846252,
-        "min": 5.846252,
-        "max": 5.846252,
+        "avg": 5.85542,
+        "median": 5.85542,
+        "min": 5.85542,
+        "max": 5.85542,
         "count": 1
       },
       "eemumu-sa-cpp-d-inl1-512y": {
-        "avg": 10.21613,
-        "median": 10.21613,
-        "min": 10.21613,
-        "max": 10.21613,
+        "avg": 10.94437,
+        "median": 10.94437,
+        "min": 10.94437,
+        "max": 10.94437,
         "count": 1
       },
       "eemumu-sa-cpp-f-inl0-512y": {
-        "avg": 12.06278,
-        "median": 12.06278,
-        "min": 12.06278,
-        "max": 12.06278,
+        "avg": 12.28219,
+        "median": 12.28219,
+        "min": 12.28219,
+        "max": 12.28219,
         "count": 1
       },
       "eemumu-sa-cpp-f-inl1-512y": {
-        "avg": 25.14256,
-        "median": 25.14256,
-        "min": 25.14256,
-        "max": 25.14256,
+        "avg": 27.95492,
+        "median": 27.95492,
+        "min": 27.95492,
+        "max": 27.95492,
         "count": 1
       },
       "eemumu-sa-cpp-d-inl0-512z": {
-        "avg": 4.743013,
-        "median": 4.743013,
-        "min": 4.743013,
-        "max": 4.743013,
+        "avg": 4.919846,
+        "median": 4.919846,
+        "min": 4.919846,
+        "max": 4.919846,
         "count": 1
       },
       "eemumu-sa-cpp-d-inl1-512z": {
-        "avg": 8.547101,
-        "median": 8.547101,
-        "min": 8.547101,
-        "max": 8.547101,
+        "avg": 9.140349,
+        "median": 9.140349,
+        "min": 9.140349,
+        "max": 9.140349,
         "count": 1
       },
       "eemumu-sa-cpp-f-inl0-512z": {
-        "avg": 9.644016,
-        "median": 9.644016,
-        "min": 9.644016,
-        "max": 9.644016,
+        "avg": 10.05686,
+        "median": 10.05686,
+        "min": 10.05686,
+        "max": 10.05686,
         "count": 1
       },
       "eemumu-sa-cpp-f-inl1-512z": {
-        "avg": 18.31693,
-        "median": 18.31693,
-        "min": 18.31693,
-        "max": 18.31693,
+        "avg": 20.54445,
+        "median": 20.54445,
+        "min": 20.54445,
+        "max": 20.54445,
         "count": 1
       },
       "ggtt-sa-cuda-d-inl0": {
-        "avg": 130.0122,
-        "median": 130.0122,
-        "min": 130.0122,
-        "max": 130.0122,
+        "avg": 5.745921,
+        "median": 5.745921,
+        "min": 5.745921,
+        "max": 5.745921,
         "count": 1
       },
       "ggtt-sa-cuda-d-inl1": {
-        "avg": 130.2486,
-        "median": 130.2486,
-        "min": 130.2486,
-        "max": 130.2486,
+        "avg": 5.897079,
+        "median": 5.897079,
+        "min": 5.897079,
+        "max": 5.897079,
         "count": 1
       },
       "ggtt-sa-cuda-f-inl0": {
-        "avg": 363.6906,
-        "median": 363.6906,
-        "min": 363.6906,
-        "max": 363.6906,
+        "avg": 175.4402,
+        "median": 175.4402,
+        "min": 175.4402,
+        "max": 175.4402,
         "count": 1
       },
       "ggtt-sa-cuda-f-inl1": {
-        "avg": 363.4642,
-        "median": 363.4642,
-        "min": 363.4642,
-        "max": 363.4642,
+        "avg": 170.835,
+        "median": 170.835,
+        "min": 170.835,
+        "max": 170.835,
         "count": 1
       },
       "ggtt-sa-cpp-d-inl0-best": {
-        "avg": 0.621275,
-        "median": 0.621275,
-        "min": 0.621275,
-        "max": 0.621275,
+        "avg": 0.625262,
+        "median": 0.625262,
+        "min": 0.625262,
+        "max": 0.625262,
         "count": 1
       },
       "ggtt-sa-cpp-d-inl0-none": {
-        "avg": 0.191205,
-        "median": 0.191205,
-        "min": 0.191205,
-        "max": 0.191205,
+        "avg": 0.191705,
+        "median": 0.191705,
+        "min": 0.191705,
+        "max": 0.191705,
         "count": 1
       },
       "ggtt-sa-cpp-d-inl1-best": {
-        "avg": 0.4756,
-        "median": 0.4756,
-        "min": 0.4756,
-        "max": 0.4756,
+        "avg": 0.481277,
+        "median": 0.481277,
+        "min": 0.481277,
+        "max": 0.481277,
         "count": 1
       },
       "ggtt-sa-cpp-d-inl1-none": {
-        "avg": 0.233498,
-        "median": 0.233498,
-        "min": 0.233498,
-        "max": 0.233498,
+        "avg": 0.233871,
+        "median": 0.233871,
+        "min": 0.233871,
+        "max": 0.233871,
         "count": 1
       },
       "ggtt-sa-cpp-f-inl0-best": {
-        "avg": 1.112862,
-        "median": 1.112862,
-        "min": 1.112862,
-        "max": 1.112862,
+        "avg": 1.115452,
+        "median": 1.115452,
+        "min": 1.115452,
+        "max": 1.115452,
         "count": 1
       },
       "ggtt-sa-cpp-f-inl0-none": {
-        "avg": 0.199978,
-        "median": 0.199978,
-        "min": 0.199978,
-        "max": 0.199978,
+        "avg": 0.200632,
+        "median": 0.200632,
+        "min": 0.200632,
+        "max": 0.200632,
         "count": 1
       },
       "ggtt-sa-cpp-f-inl1-best": {
-        "avg": 0.709898,
-        "median": 0.709898,
-        "min": 0.709898,
-        "max": 0.709898,
+        "avg": 0.717432,
+        "median": 0.717432,
+        "min": 0.717432,
+        "max": 0.717432,
         "count": 1
       },
       "ggtt-sa-cpp-f-inl1-none": {
-        "avg": 0.242443,
-        "median": 0.242443,
-        "min": 0.242443,
-        "max": 0.242443,
+        "avg": 0.243362,
+        "median": 0.243362,
+        "min": 0.243362,
+        "max": 0.243362,
         "count": 1
       },
       "ggtt-sa-cpp-d-inl0-sse4": {
-        "avg": 0.320444,
-        "median": 0.320444,
-        "min": 0.320444,
-        "max": 0.320444,
+        "avg": 0.322312,
+        "median": 0.322312,
+        "min": 0.322312,
+        "max": 0.322312,
         "count": 1
       },
       "ggtt-sa-cpp-d-inl1-sse4": {
-        "avg": 0.276818,
-        "median": 0.276818,
-        "min": 0.276818,
-        "max": 0.276818,
+        "avg": 0.278407,
+        "median": 0.278407,
+        "min": 0.278407,
+        "max": 0.278407,
         "count": 1
       },
       "ggtt-sa-cpp-f-inl0-sse4": {
-        "avg": 0.476373,
-        "median": 0.476373,
-        "min": 0.476373,
-        "max": 0.476373,
+        "avg": 0.478232,
+        "median": 0.478232,
+        "min": 0.478232,
+        "max": 0.478232,
         "count": 1
       },
       "ggtt-sa-cpp-f-inl1-sse4": {
-        "avg": 0.560182,
-        "median": 0.560182,
-        "min": 0.560182,
-        "max": 0.560182,
+        "avg": 0.562256,
+        "median": 0.562256,
+        "min": 0.562256,
+        "max": 0.562256,
         "count": 1
       },
       "ggtt-sa-cpp-d-inl0-avx2": {
-        "avg": 0.557379,
-        "median": 0.557379,
-        "min": 0.557379,
-        "max": 0.557379,
+        "avg": 0.559118,
+        "median": 0.559118,
+        "min": 0.559118,
+        "max": 0.559118,
         "count": 1
       },
       "ggtt-sa-cpp-d-inl1-avx2": {
-        "avg": 0.459304,
-        "median": 0.459304,
-        "min": 0.459304,
-        "max": 0.459304,
+        "avg": 0.461578,
+        "median": 0.461578,
+        "min": 0.461578,
+        "max": 0.461578,
         "count": 1
       },
       "ggtt-sa-cpp-f-inl0-avx2": {
-        "avg": 1.035333,
-        "median": 1.035333,
-        "min": 1.035333,
-        "max": 1.035333,
+        "avg": 1.038209,
+        "median": 1.038209,
+        "min": 1.038209,
+        "max": 1.038209,
         "count": 1
       },
       "ggtt-sa-cpp-f-inl1-avx2": {
-        "avg": 0.701411,
-        "median": 0.701411,
-        "min": 0.701411,
-        "max": 0.701411,
+        "avg": 0.717164,
+        "median": 0.717164,
+        "min": 0.717164,
+        "max": 0.717164,
         "count": 1
       },
       "ggtt-sa-cpp-d-inl0-512y": {
-        "avg": 0.621275,
-        "median": 0.621275,
-        "min": 0.621275,
-        "max": 0.621275,
+        "avg": 0.625262,
+        "median": 0.625262,
+        "min": 0.625262,
+        "max": 0.625262,
         "count": 1
       },
       "ggtt-sa-cpp-d-inl1-512y": {
-        "avg": 0.4756,
-        "median": 0.4756,
-        "min": 0.4756,
-        "max": 0.4756,
+        "avg": 0.481277,
+        "median": 0.481277,
+        "min": 0.481277,
+        "max": 0.481277,
         "count": 1
       },
       "ggtt-sa-cpp-f-inl0-512y": {
-        "avg": 1.112862,
-        "median": 1.112862,
-        "min": 1.112862,
-        "max": 1.112862,
+        "avg": 1.115452,
+        "median": 1.115452,
+        "min": 1.115452,
+        "max": 1.115452,
         "count": 1
       },
       "ggtt-sa-cpp-f-inl1-512y": {
-        "avg": 0.709898,
-        "median": 0.709898,
-        "min": 0.709898,
-        "max": 0.709898,
+        "avg": 0.717432,
+        "median": 0.717432,
+        "min": 0.717432,
+        "max": 0.717432,
         "count": 1
       },
       "ggtt-sa-cpp-d-inl0-512z": {
-        "avg": 0.373228,
-        "median": 0.373228,
-        "min": 0.373228,
-        "max": 0.373228,
+        "avg": 0.374524,
+        "median": 0.374524,
+        "min": 0.374524,
+        "max": 0.374524,
         "count": 1
       },
       "ggtt-sa-cpp-d-inl1-512z": {
-        "avg": 0.343774,
-        "median": 0.343774,
-        "min": 0.343774,
-        "max": 0.343774,
+        "avg": 0.347206,
+        "median": 0.347206,
+        "min": 0.347206,
+        "max": 0.347206,
         "count": 1
       },
       "ggtt-sa-cpp-f-inl0-512z": {
-        "avg": 0.776214,
-        "median": 0.776214,
-        "min": 0.776214,
-        "max": 0.776214,
+        "avg": 0.781307,
+        "median": 0.781307,
+        "min": 0.781307,
+        "max": 0.781307,
         "count": 1
       },
       "ggtt-sa-cpp-f-inl1-512z": {
-        "avg": 0.563786,
-        "median": 0.563786,
-        "min": 0.563786,
-        "max": 0.563786,
+        "avg": 0.564741,
+        "median": 0.564741,
+        "min": 0.564741,
+        "max": 0.564741,
         "count": 1
       },
       "ggttg-sa-cuda-d-inl0": {
-        "avg": 13.42965,
-        "median": 13.42965,
-        "min": 13.42965,
-        "max": 13.42965,
+        "avg": 0.818309,
+        "median": 0.818309,
+        "min": 0.818309,
+        "max": 0.818309,
         "count": 1
       },
       "ggttg-sa-cuda-d-inl1": {
-        "avg": 13.42074,
-        "median": 13.42074,
-        "min": 13.42074,
-        "max": 13.42074,
+        "avg": 0.818317,
+        "median": 0.818317,
+        "min": 0.818317,
+        "max": 0.818317,
         "count": 1
       },
       "ggttg-sa-cuda-f-inl0": {
-        "avg": 45.87926,
-        "median": 45.87926,
-        "min": 45.87926,
-        "max": 45.87926,
+        "avg": 18.42414,
+        "median": 18.42414,
+        "min": 18.42414,
+        "max": 18.42414,
         "count": 1
       },
       "ggttg-sa-cuda-f-inl1": {
-        "avg": 45.53218,
-        "median": 45.53218,
-        "min": 45.53218,
-        "max": 45.53218,
+        "avg": 18.37018,
+        "median": 18.37018,
+        "min": 18.37018,
+        "max": 18.37018,
         "count": 1
       },
       "ggttg-sa-cpp-d-inl0-best": {
-        "avg": 0.100039,
-        "median": 0.100039,
-        "min": 0.100039,
-        "max": 0.100039,
+        "avg": 0.100087,
+        "median": 0.100087,
+        "min": 0.100087,
+        "max": 0.100087,
         "count": 1
       },
       "ggttg-sa-cpp-d-inl0-none": {
-        "avg": 0.02382,
-        "median": 0.02382,
-        "min": 0.02382,
-        "max": 0.02382,
+        "avg": 0.023867,
+        "median": 0.023867,
+        "min": 0.023867,
+        "max": 0.023867,
         "count": 1
       },
       "ggttg-sa-cpp-d-inl1-best": {
-        "avg": 0.088939,
-        "median": 0.088939,
-        "min": 0.088939,
-        "max": 0.088939,
+        "avg": 0.089018,
+        "median": 0.089018,
+        "min": 0.089018,
+        "max": 0.089018,
         "count": 1
       },
       "ggttg-sa-cpp-d-inl1-none": {
-        "avg": 0.006257,
-        "median": 0.006257,
-        "min": 0.006257,
-        "max": 0.006257,
+        "avg": 0.006266,
+        "median": 0.006266,
+        "min": 0.006266,
+        "max": 0.006266,
         "count": 1
       },
       "ggttg-sa-cpp-f-inl0-best": {
-        "avg": 0.19736,
-        "median": 0.19736,
-        "min": 0.19736,
-        "max": 0.19736,
+        "avg": 0.197983,
+        "median": 0.197983,
+        "min": 0.197983,
+        "max": 0.197983,
         "count": 1
       },
       "ggttg-sa-cpp-f-inl0-none": {
-        "avg": 0.024398,
-        "median": 0.024398,
-        "min": 0.024398,
-        "max": 0.024398,
+        "avg": 0.024443,
+        "median": 0.024443,
+        "min": 0.024443,
+        "max": 0.024443,
         "count": 1
       },
       "ggttg-sa-cpp-f-inl1-best": {
-        "avg": 0.155494,
-        "median": 0.155494,
-        "min": 0.155494,
-        "max": 0.155494,
+        "avg": 0.155876,
+        "median": 0.155876,
+        "min": 0.155876,
+        "max": 0.155876,
         "count": 1
       },
       "ggttg-sa-cpp-f-inl1-none": {
-        "avg": 0.010191,
-        "median": 0.010191,
-        "min": 0.010191,
-        "max": 0.010191,
+        "avg": 0.010211,
+        "median": 0.010211,
+        "min": 0.010211,
+        "max": 0.010211,
         "count": 1
       },
       "ggttg-sa-cpp-d-inl0-sse4": {
-        "avg": 0.044798,
-        "median": 0.044798,
-        "min": 0.044798,
-        "max": 0.044798,
+        "avg": 0.044909,
+        "median": 0.044909,
+        "min": 0.044909,
+        "max": 0.044909,
         "count": 1
       },
       "ggttg-sa-cpp-d-inl1-sse4": {
-        "avg": 0.041744,
-        "median": 0.041744,
-        "min": 0.041744,
-        "max": 0.041744,
+        "avg": 0.041899,
+        "median": 0.041899,
+        "min": 0.041899,
+        "max": 0.041899,
         "count": 1
       },
       "ggttg-sa-cpp-f-inl0-sse4": {
-        "avg": 0.081961,
-        "median": 0.081961,
-        "min": 0.081961,
-        "max": 0.081961,
+        "avg": 0.082025,
+        "median": 0.082025,
+        "min": 0.082025,
+        "max": 0.082025,
         "count": 1
       },
       "ggttg-sa-cpp-f-inl1-sse4": {
-        "avg": 0.087043,
-        "median": 0.087043,
-        "min": 0.087043,
-        "max": 0.087043,
+        "avg": 0.087215,
+        "median": 0.087215,
+        "min": 0.087215,
+        "max": 0.087215,
         "count": 1
       },
       "ggttg-sa-cpp-d-inl0-avx2": {
-        "avg": 0.087299,
-        "median": 0.087299,
-        "min": 0.087299,
-        "max": 0.087299,
+        "avg": 0.087359,
+        "median": 0.087359,
+        "min": 0.087359,
+        "max": 0.087359,
         "count": 1
       },
       "ggttg-sa-cpp-d-inl1-avx2": {
-        "avg": 0.080643,
-        "median": 0.080643,
-        "min": 0.080643,
-        "max": 0.080643,
+        "avg": 0.08088,
+        "median": 0.08088,
+        "min": 0.08088,
+        "max": 0.08088,
         "count": 1
       },
       "ggttg-sa-cpp-f-inl0-avx2": {
-        "avg": 0.174154,
-        "median": 0.174154,
-        "min": 0.174154,
-        "max": 0.174154,
+        "avg": 0.174366,
+        "median": 0.174366,
+        "min": 0.174366,
+        "max": 0.174366,
         "count": 1
       },
       "ggttg-sa-cpp-f-inl1-avx2": {
-        "avg": 0.140233,
-        "median": 0.140233,
-        "min": 0.140233,
-        "max": 0.140233,
+        "avg": 0.140372,
+        "median": 0.140372,
+        "min": 0.140372,
+        "max": 0.140372,
         "count": 1
       },
       "ggttg-sa-cpp-d-inl0-512y": {
-        "avg": 0.100039,
-        "median": 0.100039,
-        "min": 0.100039,
-        "max": 0.100039,
+        "avg": 0.100087,
+        "median": 0.100087,
+        "min": 0.100087,
+        "max": 0.100087,
         "count": 1
       },
       "ggttg-sa-cpp-d-inl1-512y": {
-        "avg": 0.088939,
-        "median": 0.088939,
-        "min": 0.088939,
-        "max": 0.088939,
+        "avg": 0.089018,
+        "median": 0.089018,
+        "min": 0.089018,
+        "max": 0.089018,
         "count": 1
       },
       "ggttg-sa-cpp-f-inl0-512y": {
-        "avg": 0.19736,
-        "median": 0.19736,
-        "min": 0.19736,
-        "max": 0.19736,
+        "avg": 0.197983,
+        "median": 0.197983,
+        "min": 0.197983,
+        "max": 0.197983,
         "count": 1
       },
       "ggttg-sa-cpp-f-inl1-512y": {
-        "avg": 0.155494,
-        "median": 0.155494,
-        "min": 0.155494,
-        "max": 0.155494,
+        "avg": 0.155876,
+        "median": 0.155876,
+        "min": 0.155876,
+        "max": 0.155876,
         "count": 1
       },
       "ggttg-sa-cpp-d-inl0-512z": {
-        "avg": 0.072167,
-        "median": 0.072167,
-        "min": 0.072167,
-        "max": 0.072167,
+        "avg": 0.072352,
+        "median": 0.072352,
+        "min": 0.072352,
+        "max": 0.072352,
         "count": 1
       },
       "ggttg-sa-cpp-d-inl1-512z": {
-        "avg": 0.064795,
-        "median": 0.064795,
-        "min": 0.064795,
-        "max": 0.064795,
+        "avg": 0.064912,
+        "median": 0.064912,
+        "min": 0.064912,
+        "max": 0.064912,
         "count": 1
       },
       "ggttg-sa-cpp-f-inl0-512z": {
-        "avg": 0.150164,
-        "median": 0.150164,
-        "min": 0.150164,
-        "max": 0.150164,
+        "avg": 0.150358,
+        "median": 0.150358,
+        "min": 0.150358,
+        "max": 0.150358,
         "count": 1
       },
       "ggttg-sa-cpp-f-inl1-512z": {
-        "avg": 0.11501,
-        "median": 0.11501,
-        "min": 0.11501,
-        "max": 0.11501,
+        "avg": 0.115493,
+        "median": 0.115493,
+        "min": 0.115493,
+        "max": 0.115493,
         "count": 1
       },
       "ggttgg-sa-cuda-d-inl0": {
-        "avg": 0.420085,
-        "median": 0.420085,
-        "min": 0.420085,
-        "max": 0.420085,
+        "avg": 0.055489,
+        "median": 0.055489,
+        "min": 0.055489,
+        "max": 0.055489,
         "count": 1
       },
       "ggttgg-sa-cuda-d-inl1": {
-        "avg": 0.386847,
-        "median": 0.386847,
-        "min": 0.386847,
-        "max": 0.386847,
+        "avg": 0.062788,
+        "median": 0.062788,
+        "min": 0.062788,
+        "max": 0.062788,
         "count": 1
       },
       "ggttgg-sa-cuda-f-inl0": {
-        "avg": 0.868273,
-        "median": 0.868273,
-        "min": 0.868273,
-        "max": 0.868273,
+        "avg": 0.308794,
+        "median": 0.308794,
+        "min": 0.308794,
+        "max": 0.308794,
         "count": 1
       },
       "ggttgg-sa-cuda-f-inl1": {
-        "avg": 0.776756,
-        "median": 0.776756,
-        "min": 0.776756,
-        "max": 0.776756,
+        "avg": 0.263863,
+        "median": 0.263863,
+        "min": 0.263863,
+        "max": 0.263863,
         "count": 1
       },
       "ggttgg-sa-cpp-d-inl0-best": {
-        "avg": 0.007535,
-        "median": 0.007535,
-        "min": 0.007535,
-        "max": 0.007535,
+        "avg": 0.007537,
+        "median": 0.007537,
+        "min": 0.007537,
+        "max": 0.007537,
         "count": 1
       },
       "ggttgg-sa-cpp-d-inl0-none": {
-        "avg": 0.001741,
-        "median": 0.001741,
-        "min": 0.001741,
-        "max": 0.001741,
+        "avg": 0.001743,
+        "median": 0.001743,
+        "min": 0.001743,
+        "max": 0.001743,
         "count": 1
       },
       "ggttgg-sa-cpp-d-inl1-best": {
-        "avg": 0.006889,
-        "median": 0.006889,
-        "min": 0.006889,
-        "max": 0.006889,
+        "avg": 0.006903,
+        "median": 0.006903,
+        "min": 0.006903,
+        "max": 0.006903,
         "count": 1
       },
       "ggttgg-sa-cpp-d-inl1-none": {
@@ -766,24 +766,24 @@
         "count": 1
       },
       "ggttgg-sa-cpp-f-inl0-best": {
-        "avg": 0.014947,
-        "median": 0.014947,
-        "min": 0.014947,
-        "max": 0.014947,
+        "avg": 0.014863,
+        "median": 0.014863,
+        "min": 0.014863,
+        "max": 0.014863,
         "count": 1
       },
       "ggttgg-sa-cpp-f-inl0-none": {
-        "avg": 0.001824,
-        "median": 0.001824,
-        "min": 0.001824,
-        "max": 0.001824,
+        "avg": 0.001829,
+        "median": 0.001829,
+        "min": 0.001829,
+        "max": 0.001829,
         "count": 1
       },
       "ggttgg-sa-cpp-f-inl1-best": {
-        "avg": 0.013404,
-        "median": 0.013404,
-        "min": 0.013404,
-        "max": 0.013404,
+        "avg": 0.013425,
+        "median": 0.013425,
+        "min": 0.013425,
+        "max": 0.013425,
         "count": 1
       },
       "ggttgg-sa-cpp-f-inl1-none": {
@@ -794,126 +794,126 @@
         "count": 1
       },
       "ggttgg-sa-cpp-d-inl0-sse4": {
-        "avg": 0.003343,
-        "median": 0.003343,
-        "min": 0.003343,
-        "max": 0.003343,
+        "avg": 0.00335,
+        "median": 0.00335,
+        "min": 0.00335,
+        "max": 0.00335,
         "count": 1
       },
       "ggttgg-sa-cpp-d-inl1-sse4": {
-        "avg": 0.002787,
-        "median": 0.002787,
-        "min": 0.002787,
-        "max": 0.002787,
+        "avg": 0.002792,
+        "median": 0.002792,
+        "min": 0.002792,
+        "max": 0.002792,
         "count": 1
       },
       "ggttgg-sa-cpp-f-inl0-sse4": {
-        "avg": 0.006896,
-        "median": 0.006896,
-        "min": 0.006896,
-        "max": 0.006896,
+        "avg": 0.006907,
+        "median": 0.006907,
+        "min": 0.006907,
+        "max": 0.006907,
         "count": 1
       },
       "ggttgg-sa-cpp-f-inl1-sse4": {
-        "avg": 0.006075,
-        "median": 0.006075,
-        "min": 0.006075,
-        "max": 0.006075,
+        "avg": 0.006093,
+        "median": 0.006093,
+        "min": 0.006093,
+        "max": 0.006093,
         "count": 1
       },
       "ggttgg-sa-cpp-d-inl0-avx2": {
-        "avg": 0.006661,
-        "median": 0.006661,
-        "min": 0.006661,
-        "max": 0.006661,
+        "avg": 0.006673,
+        "median": 0.006673,
+        "min": 0.006673,
+        "max": 0.006673,
         "count": 1
       },
       "ggttgg-sa-cpp-d-inl1-avx2": {
-        "avg": 0.005439,
-        "median": 0.005439,
-        "min": 0.005439,
-        "max": 0.005439,
+        "avg": 0.00545,
+        "median": 0.00545,
+        "min": 0.00545,
+        "max": 0.00545,
         "count": 1
       },
       "ggttgg-sa-cpp-f-inl0-avx2": {
-        "avg": 0.013351,
-        "median": 0.013351,
-        "min": 0.013351,
-        "max": 0.013351,
+        "avg": 0.013348,
+        "median": 0.013348,
+        "min": 0.013348,
+        "max": 0.013348,
         "count": 1
       },
       "ggttgg-sa-cpp-f-inl1-avx2": {
-        "avg": 0.010642,
-        "median": 0.010642,
-        "min": 0.010642,
-        "max": 0.010642,
+        "avg": 0.010681,
+        "median": 0.010681,
+        "min": 0.010681,
+        "max": 0.010681,
         "count": 1
       },
       "ggttgg-sa-cpp-d-inl0-512y": {
-        "avg": 0.007535,
-        "median": 0.007535,
-        "min": 0.007535,
-        "max": 0.007535,
+        "avg": 0.007537,
+        "median": 0.007537,
+        "min": 0.007537,
+        "max": 0.007537,
         "count": 1
       },
       "ggttgg-sa-cpp-d-inl1-512y": {
-        "avg": 0.006889,
-        "median": 0.006889,
-        "min": 0.006889,
-        "max": 0.006889,
+        "avg": 0.006903,
+        "median": 0.006903,
+        "min": 0.006903,
+        "max": 0.006903,
         "count": 1
       },
       "ggttgg-sa-cpp-f-inl0-512y": {
-        "avg": 0.014947,
-        "median": 0.014947,
-        "min": 0.014947,
-        "max": 0.014947,
+        "avg": 0.014863,
+        "median": 0.014863,
+        "min": 0.014863,
+        "max": 0.014863,
         "count": 1
       },
       "ggttgg-sa-cpp-f-inl1-512y": {
-        "avg": 0.013404,
-        "median": 0.013404,
-        "min": 0.013404,
-        "max": 0.013404,
+        "avg": 0.013425,
+        "median": 0.013425,
+        "min": 0.013425,
+        "max": 0.013425,
         "count": 1
       },
       "ggttgg-sa-cpp-d-inl0-512z": {
-        "avg": 0.006467,
-        "median": 0.006467,
-        "min": 0.006467,
-        "max": 0.006467,
+        "avg": 0.006486,
+        "median": 0.006486,
+        "min": 0.006486,
+        "max": 0.006486,
         "count": 1
       },
       "ggttgg-sa-cpp-d-inl1-512z": {
-        "avg": 0.006525,
-        "median": 0.006525,
-        "min": 0.006525,
-        "max": 0.006525,
+        "avg": 0.006547,
+        "median": 0.006547,
+        "min": 0.006547,
+        "max": 0.006547,
         "count": 1
       },
       "ggttgg-sa-cpp-f-inl0-512z": {
-        "avg": 0.013052,
-        "median": 0.013052,
-        "min": 0.013052,
-        "max": 0.013052,
+        "avg": 0.013055,
+        "median": 0.013055,
+        "min": 0.013055,
+        "max": 0.013055,
         "count": 1
       },
       "ggttgg-sa-cpp-f-inl1-512z": {
-        "avg": 0.01263,
-        "median": 0.01263,
-        "min": 0.01263,
-        "max": 0.01263,
+        "avg": 0.012701,
+        "median": 0.012701,
+        "min": 0.012701,
+        "max": 0.012701,
         "count": 1
       }
     },
     "log": "ok"
   },
   "app": {
-    "version": "ci-v0.6",
+    "version": "ci-v0.7",
     "description": "Madgraph5_aMCatNLO madgraph4gpu benchmark (2022)",
-    "cvmfs_checksum": "05f5179a44c0e2051bbb092a63cf0daf",
-    "bmkdata_checksum": "4eb8273563af22b829ddbf985ae0b0a9",
-    "bmk_checksum": "9b7bedb12e18a214106591542f8b3093",
+    "cvmfs_checksum": "34ff738c57b9b7a8a398e4769cba101d",
+    "bmkdata_checksum": "d4c9152ed732e012ca54b6518bf3de93",
+    "bmk_checksum": "3c9f62f161ec52296be50b21648606b0",
     "containment": "docker"
   }
 }
diff --git a/mg5amc/madgraph4gpu-2022/mg5amc-madgraph4gpu-2022/jobs/good_1/proc_1/doOneWrapper_1.log b/mg5amc/madgraph4gpu-2022/mg5amc-madgraph4gpu-2022/jobs/good_1/proc_1/doOneWrapper_1.log
index 5bad4572820d113c49a30a8536ead9d2bbd4ec44..1dcac39b9256c0380f022417123fcab663ebfd78 100644
--- a/mg5amc/madgraph4gpu-2022/mg5amc-madgraph4gpu-2022/jobs/good_1/proc_1/doOneWrapper_1.log
+++ b/mg5amc/madgraph4gpu-2022/mg5amc-madgraph4gpu-2022/jobs/good_1/proc_1/doOneWrapper_1.log
@@ -1,17 +1,18 @@
-[doOneWrapper (1)] Wed Aug 31 20:55:19 CEST 2022 : process 1 configured
-[doOneWrapper (1)] HOME=/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/HOME
+[doOneWrapper (1)] Sat Sep 24 23:33:55 CEST 2022 : process 1 configured
+[doOneWrapper (1)] HOME=/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/HOME
 [doOneWrapper (1)] current process pid is 50
-[doOneWrapper (1)] run doOne as bmkuser in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
+[doOneWrapper (1)] run doOne as bmkuser in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
 
-[doOne (1)] Wed Aug 31 20:55:19 CEST 2022 starting in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1)] Wed Aug 31 20:55:19 CEST 2022 EXTRA_ARGS='--both -eemumu -ggtt -ggttg -ggttgg -dbl -flt -inl0 -inl1'
-[doOne (1)] Wed Aug 31 20:55:19 CEST 2022 From EXTRA_ARGS: cpuorgpus='--both'
-[doOne (1)] Wed Aug 31 20:55:19 CEST 2022 From EXTRA_ARGS: processes='-eemumu -ggtt -ggttg -ggttgg '
-[doOne (1)] Wed Aug 31 20:55:19 CEST 2022 From EXTRA_ARGS: flts='-dbl -flt '
-[doOne (1)] Wed Aug 31 20:55:19 CEST 2022 From EXTRA_ARGS: inls='-inl0 -inl1 '
-[doOne (1)] Wed Aug 31 20:55:19 CEST 2022 cpuorgpus=--both: run both CPU and GPU tests
-[doOne (1)] Wed Aug 31 20:55:19 CEST 2022 cpuorgpus=--both and a GPU is installed on this system (/dev/nvidia* found)
-Wed Aug 31 20:55:20 2022       
+[doOne (1)] Sat Sep 24 23:33:55 CEST 2022 starting in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1)] Sat Sep 24 23:33:55 CEST 2022 EXTRA_ARGS='--both -eemumu -ggtt -ggttg -ggttgg -dbl -flt -inl0 -inl1'
+[doOne (1)] Sat Sep 24 23:33:55 CEST 2022 From EXTRA_ARGS: cpuorgpus='--both'
+[doOne (1)] Sat Sep 24 23:33:55 CEST 2022 From EXTRA_ARGS: processes='-eemumu -ggtt -ggttg -ggttgg '
+[doOne (1)] Sat Sep 24 23:33:55 CEST 2022 From EXTRA_ARGS: flts='-dbl -flt '
+[doOne (1)] Sat Sep 24 23:33:55 CEST 2022 From EXTRA_ARGS: inls='-inl0 -inl1 '
+[doOne (1)] Sat Sep 24 23:33:55 CEST 2022 No -p<nblks>,<nthrs>,<niter> was specified in EXTRA_ARGS: use process-dependent predefined numbers of events and 'GPU grids'
+[doOne (1)] Sat Sep 24 23:33:55 CEST 2022 cpuorgpus=--both: run both CPU and GPU tests
+[doOne (1)] Sat Sep 24 23:33:55 CEST 2022 cpuorgpus=--both and a GPU is installed on this system (/dev/nvidia* found)
+Sat Sep 24 23:33:57 2022       
 +-----------------------------------------------------------------------------+
 | NVIDIA-SMI 515.65.01    Driver Version: 515.65.01    CUDA Version: 11.7     |
 |-------------------------------+----------------------+----------------------+
@@ -19,8 +20,8 @@ Wed Aug 31 20:55:20 2022
 | Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
 |                               |                      |               MIG M. |
 |===============================+======================+======================|
-|   0  Tesla V100S-PCI...  Off  | 00000000:00:09.0 Off |                    0 |
-| N/A   34C    P0    36W / 250W |      0MiB / 32768MiB |      0%      Default |
+|   0  Tesla T4            Off  | 00000000:00:08.0 Off |                    0 |
+| N/A   54C    P0    28W /  70W |      2MiB / 15360MiB |      5%      Default |
 |                               |                      |                  N/A |
 +-------------------------------+----------------------+----------------------+
                                                                                
@@ -31,21 +32,23 @@ Wed Aug 31 20:55:20 2022
 |=============================================================================|
 |  No running processes found                                                 |
 +-----------------------------------------------------------------------------+
-[doOne (1)] Wed Aug 31 20:55:20 CEST 2022 madgraph4gpu not found in /bmk/build/madgraph4gpu
-[doOne (1)] Wed Aug 31 20:55:20 CEST 2022 download madgraph4gpu from github into /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu
-Cloning into '/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu'...
-Checking out files:  34% (5225/15099)   
Checking out files:  35% (5285/15099)   
Checking out files:  36% (5436/15099)   
Checking out files:  37% (5587/15099)   
Checking out files:  38% (5738/15099)   
Checking out files:  39% (5889/15099)   
Checking out files:  40% (6040/15099)   
Checking out files:  41% (6191/15099)   
Checking out files:  42% (6342/15099)   
Checking out files:  43% (6493/15099)   
Checking out files:  44% (6644/15099)   
Checking out files:  45% (6795/15099)   
Checking out files:  46% (6946/15099)   
Checking out files:  47% (7097/15099)   
Checking out files:  48% (7248/15099)   
Checking out files:  49% (7399/15099)   
Checking out files:  50% (7550/15099)   
Checking out files:  51% (7701/15099)   
Checking out files:  52% (7852/15099)   
Checking out files:  53% (8003/15099)   
Checking out files:  54% (8154/15099)   
Checking out files:  55% (8305/15099)   
Checking out files:  56% (8456/15099)   
Checking out files:  57% (8607/15099)   
Checking out files:  58% (8758/15099)   
Checking out files:  59% (8909/15099)   
Checking out files:  60% (9060/15099)   
Checking out files:  61% (9211/15099)   
Checking out files:  62% (9362/15099)   
Checking out files:  63% (9513/15099)   
Checking out files:  64% (9664/15099)   
Checking out files:  65% (9815/15099)   
Checking out files:  66% (9966/15099)   
Checking out files:  67% (10117/15099)   
Checking out files:  68% (10268/15099)   
Checking out files:  69% (10419/15099)   
Checking out files:  70% (10570/15099)   
Checking out files:  71% (10721/15099)   
Checking out files:  72% (10872/15099)   
Checking out files:  73% (11023/15099)   
Checking out files:  74% (11174/15099)   
Checking out files:  75% (11325/15099)   
Checking out files:  76% (11476/15099)   
Checking out files:  76% (11616/15099)   
Checking out files:  77% (11627/15099)   
Checking out files:  78% (11778/15099)   
Checking out files:  79% (11929/15099)   
Checking out files:  80% (12080/15099)   
Checking out files:  81% (12231/15099)   
Checking out files:  82% (12382/15099)   
Checking out files:  83% (12533/15099)   
Checking out files:  84% (12684/15099)   
Checking out files:  85% (12835/15099)   
Checking out files:  86% (12986/15099)   
Checking out files:  87% (13137/15099)   
Checking out files:  88% (13288/15099)   
Checking out files:  89% (13439/15099)   
Checking out files:  90% (13590/15099)   
Checking out files:  91% (13741/15099)   
Checking out files:  92% (13892/15099)   
Checking out files:  93% (14043/15099)   
Checking out files:  94% (14194/15099)   
Checking out files:  95% (14345/15099)   
Checking out files:  96% (14496/15099)   
Checking out files:  97% (14647/15099)   
Checking out files:  98% (14798/15099)   
Checking out files:  99% (14949/15099)   
Checking out files: 100% (15099/15099)   
Checking out files: 100% (15099/15099), done.
-HEAD is now at 083b774 Merge pull request #525 from valassi/bmk
-[doOne (1)] Wed Aug 31 20:55:29 CEST 2022 Set $NEVENTS_THREAD=2 as a multiplier for a process-dependent predefined number of events
+[doOne (1)] Sat Sep 24 23:33:58 CEST 2022 madgraph4gpu not found in /bmk/build/madgraph4gpu
+[doOne (1)] Sat Sep 24 23:33:58 CEST 2022 download madgraph4gpu from github into /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu
+Cloning into '/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu'...
+Checking out files:  39% (6052/15414)   
Checking out files:  40% (6166/15414)   
Checking out files:  41% (6320/15414)   
Checking out files:  42% (6474/15414)   
Checking out files:  43% (6629/15414)   
Checking out files:  44% (6783/15414)   
Checking out files:  45% (6937/15414)   
Checking out files:  46% (7091/15414)   
Checking out files:  47% (7245/15414)   
Checking out files:  48% (7399/15414)   
Checking out files:  49% (7553/15414)   
Checking out files:  50% (7707/15414)   
Checking out files:  51% (7862/15414)   
Checking out files:  52% (8016/15414)   
Checking out files:  53% (8170/15414)   
Checking out files:  54% (8324/15414)   
Checking out files:  55% (8478/15414)   
Checking out files:  56% (8632/15414)   
Checking out files:  57% (8786/15414)   
Checking out files:  58% (8941/15414)   
Checking out files:  59% (9095/15414)   
Checking out files:  60% (9249/15414)   
Checking out files:  61% (9403/15414)   
Checking out files:  62% (9557/15414)   
Checking out files:  63% (9711/15414)   
Checking out files:  64% (9865/15414)   
Checking out files:  65% (10020/15414)   
Checking out files:  66% (10174/15414)   
Checking out files:  67% (10328/15414)   
Checking out files:  68% (10482/15414)   
Checking out files:  69% (10636/15414)   
Checking out files:  70% (10790/15414)   
Checking out files:  71% (10944/15414)   
Checking out files:  72% (11099/15414)   
Checking out files:  73% (11253/15414)   
Checking out files:  74% (11407/15414)   
Checking out files:  75% (11561/15414)   
Checking out files:  76% (11715/15414)   
Checking out files:  77% (11869/15414)   
Checking out files:  77% (12017/15414)   
Checking out files:  78% (12023/15414)   
Checking out files:  79% (12178/15414)   
Checking out files:  80% (12332/15414)   
Checking out files:  81% (12486/15414)   
Checking out files:  82% (12640/15414)   
Checking out files:  83% (12794/15414)   
Checking out files:  84% (12948/15414)   
Checking out files:  85% (13102/15414)   
Checking out files:  86% (13257/15414)   
Checking out files:  87% (13411/15414)   
Checking out files:  88% (13565/15414)   
Checking out files:  89% (13719/15414)   
Checking out files:  90% (13873/15414)   
Checking out files:  91% (14027/15414)   
Checking out files:  92% (14181/15414)   
Checking out files:  93% (14336/15414)   
Checking out files:  94% (14490/15414)   
Checking out files:  95% (14644/15414)   
Checking out files:  96% (14798/15414)   
Checking out files:  97% (14952/15414)   
Checking out files:  98% (15106/15414)   
Checking out files:  99% (15260/15414)   
Checking out files: 100% (15414/15414)   
Checking out files: 100% (15414/15414), done.
+HEAD is now at 4173921 [hack] in tput scripts, run longer tests: ggttggg by x2 (https://its.cern.ch/jira/browse/BMK-1056)
+[doOne (1)] Sat Sep 24 23:34:07 CEST 2022 Use $BMKEXEARGS (if set) to replace process-dependent predefined numbers of events and 'GPU grids'
+[doOne (1)] Sat Sep 24 23:34:07 CEST 2022 Reinterpret $NEVENTS_THREAD as a multiplier (BMKMULTIPLIER) for process-dependent predefined numbers of events
 Set cache size limit to 10.0 GB
 USECCACHE=1 CCACHE_DIR=/ccache
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:55:29.511311890 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:55:29.515583150 CEST semaphore starting: WAIT for the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:55:29.521955011 CEST 1 processes out of 1 are currently in the WAIT state
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:55:29.528873380 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:55:29.537196494 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.3228511 seconds)
-[doOne (1)] Wed Aug 31 20:55:29 CEST 2022 current status=0: execute next action '-eemumu -nocpp  '
-[doOne (1)] Wed Aug 31 20:55:29 CEST 2022 Will execute './throughputX.sh -makej -eemumu -nocpp  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:34:08 CEST 2022 Reinterpret $NEVENTS_THREAD=2 as a multiplier (BMKMULTIPLIER) for process-dependent predefined numbers of events
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:34:08.309144265 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:34:08.313258982 CEST semaphore initializing (no previous action was RUNNING): WAIT for the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:34:08.319442328 CEST 1 processes out of 1 are currently in the WAIT state
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:34:08.325909819 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:34:08.334363988 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.3292406 seconds)
+[doOne (1)] Sat Sep 24 23:34:08 CEST 2022 current status=0: execute next action '-eemumu -nocpp  '
+[doOne (1)] Sat Sep 24 23:34:08 CEST 2022 Will execute './throughputX.sh -makej -eemumu -nocpp  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 Note: checking out 'e2239ee6043f73722e7aa812a459f54a28552929'.
 
 You are in 'detached HEAD' state. You can look around, make experimental
@@ -57,682 +60,1074 @@ do so (now or later) by using -b with the checkout command again. Example:
 
   git checkout -b new_branch_name
 
-real	0m1.303s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:56:20.438794163 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:56:20.441596533 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:56:20.448955163 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:56:20.456802565 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2845926 seconds)
-[doOne (1)] Wed Aug 31 20:56:20 CEST 2022 current status=0: execute next action '-eemumu -nocpp  -inlonly'
-[doOne (1)] Wed Aug 31 20:56:20 CEST 2022 Will execute './throughputX.sh -makej -eemumu -nocpp  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m1.294s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:56:39.482500898 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:56:39.485387424 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:56:39.492867541 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:56:39.500678561 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2833149 seconds)
-[doOne (1)] Wed Aug 31 20:56:39 CEST 2022 current status=0: execute next action '-eemumu -nocpp -fltonly '
-[doOne (1)] Wed Aug 31 20:56:39 CEST 2022 Will execute './throughputX.sh -makej -eemumu -nocpp -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m1.071s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:57:06.878040668 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:57:06.880925760 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:57:06.888271646 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:57:06.896256359 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2899047 seconds)
-[doOne (1)] Wed Aug 31 20:57:06 CEST 2022 current status=0: execute next action '-eemumu -nocpp -fltonly -inlonly'
-[doOne (1)] Wed Aug 31 20:57:06 CEST 2022 Will execute './throughputX.sh -makej -eemumu -nocpp -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m1.071s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:57:25.017859872 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:57:25.020807516 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:57:25.028215384 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:57:25.036056398 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2838533 seconds)
-[doOne (1)] Wed Aug 31 20:57:25 CEST 2022 current status=0: execute next action '-eemumu -noneonly  '
-[doOne (1)] Wed Aug 31 20:57:25 CEST 2022 Will execute './throughputX.sh -makej -eemumu -noneonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m12.745s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:57:39.991605444 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:57:39.994419234 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:57:40.001817645 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:57:40.009647332 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2842594 seconds)
-[doOne (1)] Wed Aug 31 20:57:40 CEST 2022 current status=0: execute next action '-eemumu -noneonly  -inlonly'
-[doOne (1)] Wed Aug 31 20:57:40 CEST 2022 Will execute './throughputX.sh -makej -eemumu -noneonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m7.637s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:57:49.591023960 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:57:49.593920892 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:57:49.601380900 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:57:49.609322815 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2897407 seconds)
-[doOne (1)] Wed Aug 31 20:57:49 CEST 2022 current status=0: execute next action '-eemumu -noneonly -fltonly '
-[doOne (1)] Wed Aug 31 20:57:49 CEST 2022 Will execute './throughputX.sh -makej -eemumu -noneonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m11.541s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:58:03.105980920 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:58:03.108823585 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:58:03.116240587 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:58:03.124105724 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2877230 seconds)
-[doOne (1)] Wed Aug 31 20:58:03 CEST 2022 current status=0: execute next action '-eemumu -noneonly -fltonly -inlonly'
-[doOne (1)] Wed Aug 31 20:58:03 CEST 2022 Will execute './throughputX.sh -makej -eemumu -noneonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m6.489s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:58:11.795718758 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:58:11.798701380 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:58:11.806100524 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:58:11.814179623 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2882007 seconds)
-[doOne (1)] Wed Aug 31 20:58:11 CEST 2022 current status=0: execute next action '-eemumu -sse4only  '
-[doOne (1)] Wed Aug 31 20:58:11 CEST 2022 Will execute './throughputX.sh -makej -eemumu -sse4only  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m9.145s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:58:24.361449875 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:58:24.364237477 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:58:24.371428566 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:58:24.379273137 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2857402 seconds)
-[doOne (1)] Wed Aug 31 20:58:24 CEST 2022 current status=0: execute next action '-eemumu -sse4only  -inlonly'
-[doOne (1)] Wed Aug 31 20:58:24 CEST 2022 Will execute './throughputX.sh -makej -eemumu -sse4only  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m6.599s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:58:34.281809185 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:58:34.284637549 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:58:34.291956775 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:58:34.299751752 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2851413 seconds)
-[doOne (1)] Wed Aug 31 20:58:34 CEST 2022 current status=0: execute next action '-eemumu -sse4only -fltonly '
-[doOne (1)] Wed Aug 31 20:58:34 CEST 2022 Will execute './throughputX.sh -makej -eemumu -sse4only -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m6.123s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:58:43.747433657 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:58:43.750385611 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:58:43.757716038 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:58:43.765536231 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2823571 seconds)
-[doOne (1)] Wed Aug 31 20:58:43 CEST 2022 current status=0: execute next action '-eemumu -sse4only -fltonly -inlonly'
-[doOne (1)] Wed Aug 31 20:58:43 CEST 2022 Will execute './throughputX.sh -makej -eemumu -sse4only -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m4.933s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:58:52.118016105 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:58:52.120802193 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:58:52.128007079 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:58:52.135759067 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2801968 seconds)
-[doOne (1)] Wed Aug 31 20:58:52 CEST 2022 current status=0: execute next action '-eemumu -avx2only  '
-[doOne (1)] Wed Aug 31 20:58:52 CEST 2022 Will execute './throughputX.sh -makej -eemumu -avx2only  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m7.245s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:59:02.730954006 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:59:02.733835939 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:59:02.741122093 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:59:02.748909639 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2816497 seconds)
-[doOne (1)] Wed Aug 31 20:59:02 CEST 2022 current status=0: execute next action '-eemumu -avx2only  -inlonly'
-[doOne (1)] Wed Aug 31 20:59:02 CEST 2022 Will execute './throughputX.sh -makej -eemumu -avx2only  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m6.126s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:59:12.163305474 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:59:12.166141227 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:59:12.173408512 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:59:12.181241155 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2840062 seconds)
-[doOne (1)] Wed Aug 31 20:59:12 CEST 2022 current status=0: execute next action '-eemumu -avx2only -fltonly '
-[doOne (1)] Wed Aug 31 20:59:12 CEST 2022 Will execute './throughputX.sh -makej -eemumu -avx2only -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m5.155s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:59:20.645297870 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:59:20.648158732 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:59:20.655316661 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:59:20.663106927 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2813722 seconds)
-[doOne (1)] Wed Aug 31 20:59:20 CEST 2022 current status=0: execute next action '-eemumu -avx2only -fltonly -inlonly'
-[doOne (1)] Wed Aug 31 20:59:20 CEST 2022 Will execute './throughputX.sh -makej -eemumu -avx2only -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m4.492s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:59:28.627236108 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:59:28.630084343 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:59:28.637324197 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:59:28.645334165 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2854086 seconds)
-[doOne (1)] Wed Aug 31 20:59:28 CEST 2022 current status=0: execute next action '-eemumu -512yonly  '
-[doOne (1)] Wed Aug 31 20:59:28 CEST 2022 Will execute './throughputX.sh -makej -eemumu -512yonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m7.106s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:59:37.933812095 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:59:37.936628184 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:59:37.943914793 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:59:37.951817536 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2884230 seconds)
-[doOne (1)] Wed Aug 31 20:59:37 CEST 2022 current status=0: execute next action '-eemumu -512yonly  -inlonly'
-[doOne (1)] Wed Aug 31 20:59:37 CEST 2022 Will execute './throughputX.sh -makej -eemumu -512yonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m6.153s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:59:46.282242656 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:59:46.285061799 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:59:46.292359633 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:59:46.300147868 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2860240 seconds)
-[doOne (1)] Wed Aug 31 20:59:46 CEST 2022 current status=0: execute next action '-eemumu -512yonly -fltonly '
-[doOne (1)] Wed Aug 31 20:59:46 CEST 2022 Will execute './throughputX.sh -makej -eemumu -512yonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m5.016s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:59:53.507903422 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:59:53.510787792 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:59:53.518132697 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 20:59:53.525950905 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2796185 seconds)
-[doOne (1)] Wed Aug 31 20:59:53 CEST 2022 current status=0: execute next action '-eemumu -512yonly -fltonly -inlonly'
-[doOne (1)] Wed Aug 31 20:59:53 CEST 2022 Will execute './throughputX.sh -makej -eemumu -512yonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m4.481s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:00:00.201876554 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:00:00.204721535 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:00:00.212001361 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:00:00.219941078 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2858030 seconds)
-[doOne (1)] Wed Aug 31 21:00:00 CEST 2022 current status=0: execute next action '-eemumu -512zonly  '
-[doOne (1)] Wed Aug 31 21:00:00 CEST 2022 Will execute './throughputX.sh -makej -eemumu -512zonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m7.586s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:00:11.430736427 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:00:11.433657280 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:00:11.441013278 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:00:11.449132102 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2869066 seconds)
-[doOne (1)] Wed Aug 31 21:00:11 CEST 2022 current status=0: execute next action '-eemumu -512zonly  -inlonly'
-[doOne (1)] Wed Aug 31 21:00:11 CEST 2022 Will execute './throughputX.sh -makej -eemumu -512zonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m6.395s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:00:21.220822179 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:00:21.223635339 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:00:21.230877574 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:00:21.238747953 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2825745 seconds)
-[doOne (1)] Wed Aug 31 21:00:21 CEST 2022 current status=0: execute next action '-eemumu -512zonly -fltonly '
-[doOne (1)] Wed Aug 31 21:00:21 CEST 2022 Will execute './throughputX.sh -makej -eemumu -512zonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m5.265s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:00:29.862378372 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:00:29.865317988 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:00:29.872670643 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:00:29.880820456 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2943645 seconds)
-[doOne (1)] Wed Aug 31 21:00:29 CEST 2022 current status=0: execute next action '-eemumu -512zonly -fltonly -inlonly'
-[doOne (1)] Wed Aug 31 21:00:29 CEST 2022 Will execute './throughputX.sh -makej -eemumu -512zonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m4.655s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:00:37.813071461 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:00:37.815969302 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:00:37.823125843 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:00:37.830881734 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2810040 seconds)
-[doOne (1)] Wed Aug 31 21:00:37 CEST 2022 current status=0: execute next action '-ggtt -nocpp  '
-[doOne (1)] Wed Aug 31 21:00:37 CEST 2022 Will execute './throughputX.sh -makej -ggtt -nocpp  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m0.904s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:01:11.637587100 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:01:11.640398000 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:01:11.647877543 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:01:11.655787275 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2867428 seconds)
-[doOne (1)] Wed Aug 31 21:01:11 CEST 2022 current status=0: execute next action '-ggtt -nocpp  -inlonly'
-[doOne (1)] Wed Aug 31 21:01:11 CEST 2022 Will execute './throughputX.sh -makej -ggtt -nocpp  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m0.896s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:01:29.757241273 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:01:29.760144009 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:01:29.767554742 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:01:29.775412347 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2881637 seconds)
-[doOne (1)] Wed Aug 31 21:01:29 CEST 2022 current status=0: execute next action '-ggtt -nocpp -fltonly '
-[doOne (1)] Wed Aug 31 21:01:29 CEST 2022 Will execute './throughputX.sh -makej -ggtt -nocpp -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m0.838s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:01:56.847976196 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:01:56.850900635 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:01:56.858331205 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:01:56.866151641 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2871804 seconds)
-[doOne (1)] Wed Aug 31 21:01:56 CEST 2022 current status=0: execute next action '-ggtt -nocpp -fltonly -inlonly'
-[doOne (1)] Wed Aug 31 21:01:56 CEST 2022 Will execute './throughputX.sh -makej -ggtt -nocpp -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m0.833s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:02:14.195155036 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:02:14.198077286 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:02:14.205511345 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:02:14.214113652 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.3203461 seconds)
-[doOne (1)] Wed Aug 31 21:02:14 CEST 2022 current status=0: execute next action '-ggtt -noneonly  '
-[doOne (1)] Wed Aug 31 21:02:14 CEST 2022 Will execute './throughputX.sh -makej -ggtt -noneonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m5.982s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:02:22.376029225 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:02:22.378873587 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:02:22.386200208 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:02:22.394148624 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2858059 seconds)
-[doOne (1)] Wed Aug 31 21:02:22 CEST 2022 current status=0: execute next action '-ggtt -noneonly  -inlonly'
-[doOne (1)] Wed Aug 31 21:02:22 CEST 2022 Will execute './throughputX.sh -makej -ggtt -noneonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m4.989s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:02:29.572522836 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:02:29.575388063 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:02:29.582706676 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:02:29.590567022 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2889712 seconds)
-[doOne (1)] Wed Aug 31 21:02:29 CEST 2022 current status=0: execute next action '-ggtt -noneonly -fltonly '
-[doOne (1)] Wed Aug 31 21:02:29 CEST 2022 Will execute './throughputX.sh -makej -ggtt -noneonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m5.620s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:02:37.154078711 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:02:37.156858101 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:02:37.164106306 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:02:37.171947773 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2855787 seconds)
-[doOne (1)] Wed Aug 31 21:02:37 CEST 2022 current status=0: execute next action '-ggtt -noneonly -fltonly -inlonly'
-[doOne (1)] Wed Aug 31 21:02:37 CEST 2022 Will execute './throughputX.sh -makej -ggtt -noneonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m4.703s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:02:44.058875835 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:02:44.061742328 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:02:44.068926749 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:02:44.076806547 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2832053 seconds)
-[doOne (1)] Wed Aug 31 21:02:44 CEST 2022 current status=0: execute next action '-ggtt -sse4only  '
-[doOne (1)] Wed Aug 31 21:02:44 CEST 2022 Will execute './throughputX.sh -makej -ggtt -sse4only  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m3.778s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:02:51.265128010 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:02:51.268454151 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:02:51.276043665 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:02:51.284274586 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2984998 seconds)
-[doOne (1)] Wed Aug 31 21:02:51 CEST 2022 current status=0: execute next action '-ggtt -sse4only  -inlonly'
-[doOne (1)] Wed Aug 31 21:02:51 CEST 2022 Will execute './throughputX.sh -makej -ggtt -sse4only  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m4.299s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:02:59.088216795 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:02:59.091038815 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:02:59.098348400 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:02:59.106280812 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2884119 seconds)
-[doOne (1)] Wed Aug 31 21:02:59 CEST 2022 current status=0: execute next action '-ggtt -sse4only -fltonly '
-[doOne (1)] Wed Aug 31 21:02:59 CEST 2022 Will execute './throughputX.sh -makej -ggtt -sse4only -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m2.588s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:05.106234335 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:05.109060903 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:05.116319763 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:05.124085315 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2811907 seconds)
-[doOne (1)] Wed Aug 31 21:03:05 CEST 2022 current status=0: execute next action '-ggtt -sse4only -fltonly -inlonly'
-[doOne (1)] Wed Aug 31 21:03:05 CEST 2022 Will execute './throughputX.sh -makej -ggtt -sse4only -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m2.257s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:10.645621124 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:10.648438267 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:10.655710754 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:10.663591887 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2882217 seconds)
-[doOne (1)] Wed Aug 31 21:03:10 CEST 2022 current status=0: execute next action '-ggtt -avx2only  '
-[doOne (1)] Wed Aug 31 21:03:10 CEST 2022 Will execute './throughputX.sh -makej -ggtt -avx2only  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m2.379s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:16.386362272 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:16.389221477 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:16.396749953 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:16.404640064 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2873645 seconds)
-[doOne (1)] Wed Aug 31 21:03:16 CEST 2022 current status=0: execute next action '-ggtt -avx2only  -inlonly'
-[doOne (1)] Wed Aug 31 21:03:16 CEST 2022 Will execute './throughputX.sh -makej -ggtt -avx2only  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m2.781s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:22.457668178 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:22.460519045 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:22.467877249 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:22.475798287 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2891104 seconds)
-[doOne (1)] Wed Aug 31 21:03:22 CEST 2022 current status=0: execute next action '-ggtt -avx2only -fltonly '
-[doOne (1)] Wed Aug 31 21:03:22 CEST 2022 Will execute './throughputX.sh -makej -ggtt -avx2only -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m1.394s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:27.196608244 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:27.199462363 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:27.206717085 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:27.214525151 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2855763 seconds)
-[doOne (1)] Wed Aug 31 21:03:27 CEST 2022 current status=0: execute next action '-ggtt -avx2only -fltonly -inlonly'
-[doOne (1)] Wed Aug 31 21:03:27 CEST 2022 Will execute './throughputX.sh -makej -ggtt -avx2only -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m1.881s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:32.529952909 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:32.532944634 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:32.540274575 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:32.548260948 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2865348 seconds)
-[doOne (1)] Wed Aug 31 21:03:32 CEST 2022 current status=0: execute next action '-ggtt -512yonly  '
-[doOne (1)] Wed Aug 31 21:03:32 CEST 2022 Will execute './throughputX.sh -makej -ggtt -512yonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m2.188s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:36.949776532 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:36.952788174 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:36.960443066 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:36.968740319 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2974743 seconds)
-[doOne (1)] Wed Aug 31 21:03:36 CEST 2022 current status=0: execute next action '-ggtt -512yonly  -inlonly'
-[doOne (1)] Wed Aug 31 21:03:36 CEST 2022 Will execute './throughputX.sh -makej -ggtt -512yonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m2.705s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:41.877306953 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:41.880250582 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:41.887629636 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:41.895816303 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2875809 seconds)
-[doOne (1)] Wed Aug 31 21:03:41 CEST 2022 current status=0: execute next action '-ggtt -512yonly -fltonly '
-[doOne (1)] Wed Aug 31 21:03:41 CEST 2022 Will execute './throughputX.sh -makej -ggtt -512yonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m1.324s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:45.449470871 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:45.452450204 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:45.459795842 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:45.468025291 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2917173 seconds)
-[doOne (1)] Wed Aug 31 21:03:45 CEST 2022 current status=0: execute next action '-ggtt -512yonly -fltonly -inlonly'
-[doOne (1)] Wed Aug 31 21:03:45 CEST 2022 Will execute './throughputX.sh -makej -ggtt -512yonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m1.860s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:49.546799823 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:49.549719345 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:49.556938681 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:49.564924343 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2834815 seconds)
-[doOne (1)] Wed Aug 31 21:03:49 CEST 2022 current status=0: execute next action '-ggtt -512zonly  '
-[doOne (1)] Wed Aug 31 21:03:49 CEST 2022 Will execute './throughputX.sh -makej -ggtt -512zonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m3.311s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:56.387251011 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:56.390202823 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:56.397558579 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:03:56.405572774 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2851562 seconds)
-[doOne (1)] Wed Aug 31 21:03:56 CEST 2022 current status=0: execute next action '-ggtt -512zonly  -inlonly'
-[doOne (1)] Wed Aug 31 21:03:56 CEST 2022 Will execute './throughputX.sh -makej -ggtt -512zonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m3.552s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:04:03.427170523 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:04:03.429985277 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:04:03.437316000 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:04:03.445132769 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2847847 seconds)
-[doOne (1)] Wed Aug 31 21:04:03 CEST 2022 current status=0: execute next action '-ggtt -512zonly -fltonly '
-[doOne (1)] Wed Aug 31 21:04:03 CEST 2022 Will execute './throughputX.sh -makej -ggtt -512zonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m1.730s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:04:08.474646409 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:04:08.477447824 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:04:08.484670988 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:04:08.492496391 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2845571 seconds)
-[doOne (1)] Wed Aug 31 21:04:08 CEST 2022 current status=0: execute next action '-ggtt -512zonly -fltonly -inlonly'
-[doOne (1)] Wed Aug 31 21:04:08 CEST 2022 Will execute './throughputX.sh -makej -ggtt -512zonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m2.238s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:04:13.820840659 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:04:13.823657562 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:04:13.830915999 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:04:13.838781189 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2879744 seconds)
-[doOne (1)] Wed Aug 31 21:04:13 CEST 2022 current status=0: execute next action '-ggttg -nocpp  '
-[doOne (1)] Wed Aug 31 21:04:13 CEST 2022 Will execute './throughputX.sh -makej -ggttg -nocpp  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m0.796s
-real	0m1.033s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:04:48.997802630 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:04:49.000738254 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:04:49.008112308 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:04:49.016076050 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2877143 seconds)
-[doOne (1)] Wed Aug 31 21:04:49 CEST 2022 current status=0: execute next action '-ggttg -nocpp  -inlonly'
-[doOne (1)] Wed Aug 31 21:04:49 CEST 2022 Will execute './throughputX.sh -makej -ggttg -nocpp  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m0.784s
-real	0m1.033s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:05:08.102523602 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:05:08.105431013 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:05:08.113021741 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:05:08.120919629 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2868035 seconds)
-[doOne (1)] Wed Aug 31 21:05:08 CEST 2022 current status=0: execute next action '-ggttg -nocpp -fltonly '
-[doOne (1)] Wed Aug 31 21:05:08 CEST 2022 Will execute './throughputX.sh -makej -ggttg -nocpp -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m0.980s
-real	0m0.874s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:05:36.892918022 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:05:36.895822872 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:05:36.903262530 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:05:36.911144485 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2877324 seconds)
-[doOne (1)] Wed Aug 31 21:05:36 CEST 2022 current status=0: execute next action '-ggttg -nocpp -fltonly -inlonly'
-[doOne (1)] Wed Aug 31 21:05:36 CEST 2022 Will execute './throughputX.sh -makej -ggttg -nocpp -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m0.772s
-real	0m0.872s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:05:55.060302138 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:05:55.063273704 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:05:55.070660509 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:05:55.078551105 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2862453 seconds)
-[doOne (1)] Wed Aug 31 21:05:55 CEST 2022 current status=0: execute next action '-ggttg -noneonly  '
-[doOne (1)] Wed Aug 31 21:05:55 CEST 2022 Will execute './throughputX.sh -makej -ggttg -noneonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m1.407s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:05:58.723289365 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:05:58.726131112 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:05:58.733322228 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:05:58.741095739 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2812984 seconds)
-[doOne (1)] Wed Aug 31 21:05:58 CEST 2022 current status=0: execute next action '-ggttg -noneonly  -inlonly'
-[doOne (1)] Wed Aug 31 21:05:58 CEST 2022 Will execute './throughputX.sh -makej -ggttg -noneonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m5.271s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:06.353181893 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:06.356020592 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:06.363910476 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:06.371854293 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2854228 seconds)
-[doOne (1)] Wed Aug 31 21:06:06 CEST 2022 current status=0: execute next action '-ggttg -noneonly -fltonly '
-[doOne (1)] Wed Aug 31 21:06:06 CEST 2022 Will execute './throughputX.sh -makej -ggttg -noneonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m1.369s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:10.049330976 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:10.052200158 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:10.059540648 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:10.067513958 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2906139 seconds)
-[doOne (1)] Wed Aug 31 21:06:10 CEST 2022 current status=0: execute next action '-ggttg -noneonly -fltonly -inlonly'
-[doOne (1)] Wed Aug 31 21:06:10 CEST 2022 Will execute './throughputX.sh -makej -ggttg -noneonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m3.243s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:15.410296147 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:15.413152719 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:15.420458542 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:15.428369145 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2882158 seconds)
-[doOne (1)] Wed Aug 31 21:06:15 CEST 2022 current status=0: execute next action '-ggttg -sse4only  '
-[doOne (1)] Wed Aug 31 21:06:15 CEST 2022 Will execute './throughputX.sh -makej -ggttg -sse4only  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m0.763s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:19.532564627 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:19.535420004 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:19.542721128 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:19.550482473 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2832538 seconds)
-[doOne (1)] Wed Aug 31 21:06:19 CEST 2022 current status=0: execute next action '-ggttg -sse4only  -inlonly'
-[doOne (1)] Wed Aug 31 21:06:19 CEST 2022 Will execute './throughputX.sh -makej -ggttg -sse4only  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m0.816s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:23.692357308 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:23.695167215 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:23.702374604 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:23.710199516 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2848056 seconds)
-[doOne (1)] Wed Aug 31 21:06:23 CEST 2022 current status=0: execute next action '-ggttg -sse4only -fltonly '
-[doOne (1)] Wed Aug 31 21:06:23 CEST 2022 Will execute './throughputX.sh -makej -ggttg -sse4only -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m0.425s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:27.448874911 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:27.451729358 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:27.458971120 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:27.466789931 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2839236 seconds)
-[doOne (1)] Wed Aug 31 21:06:27 CEST 2022 current status=0: execute next action '-ggttg -sse4only -fltonly -inlonly'
-[doOne (1)] Wed Aug 31 21:06:27 CEST 2022 Will execute './throughputX.sh -makej -ggttg -sse4only -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m0.402s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:31.182343754 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:31.185150142 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:31.192380203 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:31.200146285 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2805251 seconds)
-[doOne (1)] Wed Aug 31 21:06:31 CEST 2022 current status=0: execute next action '-ggttg -avx2only  '
-[doOne (1)] Wed Aug 31 21:06:31 CEST 2022 Will execute './throughputX.sh -makej -ggttg -avx2only  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m0.406s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:35.808176453 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:35.810994463 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:35.818276800 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:35.826127984 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2898078 seconds)
-[doOne (1)] Wed Aug 31 21:06:35 CEST 2022 current status=0: execute next action '-ggttg -avx2only  -inlonly'
-[doOne (1)] Wed Aug 31 21:06:35 CEST 2022 Will execute './throughputX.sh -makej -ggttg -avx2only  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m0.437s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:39.656265144 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:39.659087728 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:39.666470419 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:39.674321149 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2849093 seconds)
-[doOne (1)] Wed Aug 31 21:06:39 CEST 2022 current status=0: execute next action '-ggttg -avx2only -fltonly '
-[doOne (1)] Wed Aug 31 21:06:39 CEST 2022 Will execute './throughputX.sh -makej -ggttg -avx2only -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m0.214s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:43.419809900 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:43.422614070 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:43.429889890 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:43.437740136 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2826802 seconds)
-[doOne (1)] Wed Aug 31 21:06:43 CEST 2022 current status=0: execute next action '-ggttg -avx2only -fltonly -inlonly'
-[doOne (1)] Wed Aug 31 21:06:43 CEST 2022 Will execute './throughputX.sh -makej -ggttg -avx2only -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m0.259s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:47.123940333 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:47.126762806 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:47.133955963 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:47.141768061 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2814227 seconds)
-[doOne (1)] Wed Aug 31 21:06:47 CEST 2022 current status=0: execute next action '-ggttg -512yonly  '
-[doOne (1)] Wed Aug 31 21:06:47 CEST 2022 Will execute './throughputX.sh -makej -ggttg -512yonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m0.358s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:49.707248079 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:49.710093726 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:49.717380883 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:49.725144420 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2834385 seconds)
-[doOne (1)] Wed Aug 31 21:06:49 CEST 2022 current status=0: execute next action '-ggttg -512yonly  -inlonly'
-[doOne (1)] Wed Aug 31 21:06:49 CEST 2022 Will execute './throughputX.sh -makej -ggttg -512yonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m0.399s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:52.312837492 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:52.315640632 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:52.323027542 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:52.330844838 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2855793 seconds)
-[doOne (1)] Wed Aug 31 21:06:52 CEST 2022 current status=0: execute next action '-ggttg -512yonly -fltonly '
-[doOne (1)] Wed Aug 31 21:06:52 CEST 2022 Will execute './throughputX.sh -makej -ggttg -512yonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m0.192s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:54.702457677 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:54.705322797 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:54.712531596 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:54.720430565 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2894329 seconds)
-[doOne (1)] Wed Aug 31 21:06:54 CEST 2022 current status=0: execute next action '-ggttg -512yonly -fltonly -inlonly'
-[doOne (1)] Wed Aug 31 21:06:54 CEST 2022 Will execute './throughputX.sh -makej -ggttg -512yonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m0.236s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:57.304940758 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:57.307772451 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:57.315008216 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:06:57.322864467 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2790101 seconds)
-[doOne (1)] Wed Aug 31 21:06:57 CEST 2022 current status=0: execute next action '-ggttg -512zonly  '
-[doOne (1)] Wed Aug 31 21:06:57 CEST 2022 Will execute './throughputX.sh -makej -ggttg -512zonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m0.485s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:07:01.106345140 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:07:01.109147714 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:07:01.116342155 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:07:01.124201211 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2835285 seconds)
-[doOne (1)] Wed Aug 31 21:07:01 CEST 2022 current status=0: execute next action '-ggttg -512zonly  -inlonly'
-[doOne (1)] Wed Aug 31 21:07:01 CEST 2022 Will execute './throughputX.sh -makej -ggttg -512zonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m0.536s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:07:05.045711639 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:07:05.048503108 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:07:05.055759338 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:07:05.063555876 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2822331 seconds)
-[doOne (1)] Wed Aug 31 21:07:05 CEST 2022 current status=0: execute next action '-ggttg -512zonly -fltonly '
-[doOne (1)] Wed Aug 31 21:07:05 CEST 2022 Will execute './throughputX.sh -makej -ggttg -512zonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m0.244s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:07:08.626657661 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:07:08.629479086 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:07:08.636703259 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:07:08.644537473 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2853969 seconds)
-[doOne (1)] Wed Aug 31 21:07:08 CEST 2022 current status=0: execute next action '-ggttg -512zonly -fltonly -inlonly'
-[doOne (1)] Wed Aug 31 21:07:08 CEST 2022 Will execute './throughputX.sh -makej -ggttg -512zonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m0.311s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:07:14.210389827 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:07:14.213323642 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:07:14.220791518 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:07:14.228818431 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2870445 seconds)
-[doOne (1)] Wed Aug 31 21:07:14 CEST 2022 current status=0: execute next action '-ggttgg -nocpp  '
-[doOne (1)] Wed Aug 31 21:07:14 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -nocpp  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m0.938s
-real	0m4.727s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:08:01.943083742 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:08:01.946033993 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:08:01.953381875 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:08:01.961255524 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2819127 seconds)
-[doOne (1)] Wed Aug 31 21:08:01 CEST 2022 current status=0: execute next action '-ggttgg -nocpp  -inlonly'
-[doOne (1)] Wed Aug 31 21:08:01 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -nocpp  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m0.939s
+real	0m3.742s
+[doOne (1)] Sat Sep 24 23:35:33 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_d_inl0_hrd0/gcheck.exe -p 2048 256 24 OMP=
+[doOne (1)] Sat Sep 24 23:35:40 CEST 2022 current status=0: completed action '-eemumu -nocpp  '
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:35:40.713590648 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:35:40.716525956 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:35:40.723729041 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:35:40.731697469 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2881743 seconds)
+[doOne (1)] Sat Sep 24 23:35:40 CEST 2022 current status=0: execute next action '-eemumu -nocpp  -inlonly'
+[doOne (1)] Sat Sep 24 23:35:40 CEST 2022 Will execute './throughputX.sh -makej -eemumu -nocpp  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m3.688s
+[doOne (1)] Sat Sep 24 23:36:24 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_d_inl1_hrd0/gcheck.exe -p 2048 256 24 OMP=
+[doOne (1)] Sat Sep 24 23:36:31 CEST 2022 current status=0: completed action '-eemumu -nocpp  -inlonly'
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:36:31.450505139 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:36:31.453348572 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:36:31.461016314 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:36:31.468867217 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2867377 seconds)
+[doOne (1)] Sat Sep 24 23:36:31 CEST 2022 current status=0: execute next action '-eemumu -nocpp -fltonly '
+[doOne (1)] Sat Sep 24 23:36:31 CEST 2022 Will execute './throughputX.sh -makej -eemumu -nocpp -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m3.182s
+[doOne (1)] Sat Sep 24 23:37:31 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_f_inl0_hrd0/gcheck.exe -p 2048 256 24 OMP=
+[doOne (1)] Sat Sep 24 23:37:39 CEST 2022 current status=0: completed action '-eemumu -nocpp -fltonly '
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:37:39.349669370 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:37:39.352593233 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:37:39.360250897 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:37:39.368050668 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2847377 seconds)
+[doOne (1)] Sat Sep 24 23:37:39 CEST 2022 current status=0: execute next action '-eemumu -nocpp -fltonly -inlonly'
+[doOne (1)] Sat Sep 24 23:37:39 CEST 2022 Will execute './throughputX.sh -makej -eemumu -nocpp -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m3.132s
+[doOne (1)] Sat Sep 24 23:38:22 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_f_inl1_hrd0/gcheck.exe -p 2048 256 24 OMP=
+[doOne (1)] Sat Sep 24 23:38:30 CEST 2022 current status=0: completed action '-eemumu -nocpp -fltonly -inlonly'
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:38:30.076140937 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:38:30.078894767 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:38:30.086259400 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:38:30.094197168 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2885985 seconds)
+[doOne (1)] Sat Sep 24 23:38:30 CEST 2022 current status=0: execute next action '-eemumu -noneonly  '
+[doOne (1)] Sat Sep 24 23:38:30 CEST 2022 Will execute './throughputX.sh -makej -eemumu -noneonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m12.689s
+[doOne (1)] Sat Sep 24 23:38:50 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_d_inl0_hrd0/check.exe -p 2048 256 24 OMP=
+[doOne (1)] Sat Sep 24 23:38:57 CEST 2022 current status=0: completed action '-eemumu -noneonly  '
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:38:57.985687572 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:38:57.988629596 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:38:57.996178006 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:38:58.004097304 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2876465 seconds)
+[doOne (1)] Sat Sep 24 23:38:58 CEST 2022 current status=0: execute next action '-eemumu -noneonly  -inlonly'
+[doOne (1)] Sat Sep 24 23:38:58 CEST 2022 Will execute './throughputX.sh -makej -eemumu -noneonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m7.538s
+[doOne (1)] Sat Sep 24 23:39:13 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_d_inl1_hrd0/check.exe -p 2048 256 24 OMP=
+[doOne (1)] Sat Sep 24 23:39:20 CEST 2022 current status=0: completed action '-eemumu -noneonly  -inlonly'
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:39:20.797214937 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:39:20.800042147 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:39:20.807313141 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:39:20.815170361 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2862991 seconds)
+[doOne (1)] Sat Sep 24 23:39:20 CEST 2022 current status=0: execute next action '-eemumu -noneonly -fltonly '
+[doOne (1)] Sat Sep 24 23:39:20 CEST 2022 Will execute './throughputX.sh -makej -eemumu -noneonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m11.487s
+[doOne (1)] Sat Sep 24 23:39:40 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_f_inl0_hrd0/check.exe -p 2048 256 24 OMP=
+[doOne (1)] Sat Sep 24 23:39:47 CEST 2022 current status=0: completed action '-eemumu -noneonly -fltonly '
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:39:47.509025314 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:39:47.511859683 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:39:47.519231268 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:39:47.527116145 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2865831 seconds)
+[doOne (1)] Sat Sep 24 23:39:47 CEST 2022 current status=0: execute next action '-eemumu -noneonly -fltonly -inlonly'
+[doOne (1)] Sat Sep 24 23:39:47 CEST 2022 Will execute './throughputX.sh -makej -eemumu -noneonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m6.462s
+[doOne (1)] Sat Sep 24 23:40:01 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_f_inl1_hrd0/check.exe -p 2048 256 24 OMP=
+[doOne (1)] Sat Sep 24 23:40:09 CEST 2022 current status=0: completed action '-eemumu -noneonly -fltonly -inlonly'
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:40:09.233611718 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:40:09.236412401 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:40:09.243988926 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:40:09.251824609 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2854578 seconds)
+[doOne (1)] Sat Sep 24 23:40:09 CEST 2022 current status=0: execute next action '-eemumu -sse4only  '
+[doOne (1)] Sat Sep 24 23:40:09 CEST 2022 Will execute './throughputX.sh -makej -eemumu -sse4only  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m9.060s
+[doOne (1)] Sat Sep 24 23:40:35 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.sse4_d_inl0_hrd0/check.exe -p 2048 256 24 OMP=
+[doOne (1)] Sat Sep 24 23:40:42 CEST 2022 current status=0: completed action '-eemumu -sse4only  '
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:40:42.924013044 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:40:42.926888547 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:40:42.934286448 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:40:42.942187240 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2862076 seconds)
+[doOne (1)] Sat Sep 24 23:40:42 CEST 2022 current status=0: execute next action '-eemumu -sse4only  -inlonly'
+[doOne (1)] Sat Sep 24 23:40:42 CEST 2022 Will execute './throughputX.sh -makej -eemumu -sse4only  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m6.506s
+[doOne (1)] Sat Sep 24 23:41:03 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.sse4_d_inl1_hrd0/check.exe -p 2048 256 24 OMP=
+[doOne (1)] Sat Sep 24 23:41:11 CEST 2022 current status=0: completed action '-eemumu -sse4only  -inlonly'
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:41:11.380913893 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:41:11.383786134 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:41:11.391285552 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:41:11.399114529 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2816263 seconds)
+[doOne (1)] Sat Sep 24 23:41:11 CEST 2022 current status=0: execute next action '-eemumu -sse4only -fltonly '
+[doOne (1)] Sat Sep 24 23:41:11 CEST 2022 Will execute './throughputX.sh -makej -eemumu -sse4only -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m6.073s
+[doOne (1)] Sat Sep 24 23:41:34 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.sse4_f_inl0_hrd0/check.exe -p 2048 256 24 OMP=
+[doOne (1)] Sat Sep 24 23:41:41 CEST 2022 current status=0: completed action '-eemumu -sse4only -fltonly '
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:41:41.957387510 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:41:41.960257133 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:41:41.967607878 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:41:41.975534184 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2874318 seconds)
+[doOne (1)] Sat Sep 24 23:41:41 CEST 2022 current status=0: execute next action '-eemumu -sse4only -fltonly -inlonly'
+[doOne (1)] Sat Sep 24 23:41:41 CEST 2022 Will execute './throughputX.sh -makej -eemumu -sse4only -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m4.866s
+[doOne (1)] Sat Sep 24 23:42:01 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.sse4_f_inl1_hrd0/check.exe -p 2048 256 24 OMP=
+[doOne (1)] Sat Sep 24 23:42:08 CEST 2022 current status=0: completed action '-eemumu -sse4only -fltonly -inlonly'
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:42:08.755645711 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:42:08.758592276 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:42:08.766252853 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:42:08.774201356 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2877983 seconds)
+[doOne (1)] Sat Sep 24 23:42:08 CEST 2022 current status=0: execute next action '-eemumu -avx2only  '
+[doOne (1)] Sat Sep 24 23:42:08 CEST 2022 Will execute './throughputX.sh -makej -eemumu -avx2only  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m7.151s
+[doOne (1)] Sat Sep 24 23:42:33 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.avx2_d_inl0_hrd0/check.exe -p 2048 256 24 OMP=
+[doOne (1)] Sat Sep 24 23:42:40 CEST 2022 current status=0: completed action '-eemumu -avx2only  '
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:42:40.574875074 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:42:40.577776031 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:42:40.585316375 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:42:40.593262202 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2857308 seconds)
+[doOne (1)] Sat Sep 24 23:42:40 CEST 2022 current status=0: execute next action '-eemumu -avx2only  -inlonly'
+[doOne (1)] Sat Sep 24 23:42:40 CEST 2022 Will execute './throughputX.sh -makej -eemumu -avx2only  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m6.030s
+[doOne (1)] Sat Sep 24 23:43:01 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.avx2_d_inl1_hrd0/check.exe -p 2048 256 24 OMP=
+[doOne (1)] Sat Sep 24 23:43:08 CEST 2022 current status=0: completed action '-eemumu -avx2only  -inlonly'
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:43:08.874748873 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:43:08.877602658 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:43:08.885235814 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:43:08.893105266 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2868016 seconds)
+[doOne (1)] Sat Sep 24 23:43:08 CEST 2022 current status=0: execute next action '-eemumu -avx2only -fltonly '
+[doOne (1)] Sat Sep 24 23:43:08 CEST 2022 Will execute './throughputX.sh -makej -eemumu -avx2only -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 real	0m5.048s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:08:51.957963829 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:08:51.960960663 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:08:51.968518796 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:08:51.976384220 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2878634 seconds)
-[doOne (1)] Wed Aug 31 21:08:51 CEST 2022 current status=0: execute next action '-ggttgg -nocpp -fltonly '
-[doOne (1)] Wed Aug 31 21:08:51 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -nocpp -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m0.827s
-real	0m2.694s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:09:28.452185453 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:09:28.455070478 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:09:28.462379673 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:09:28.470315457 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2870514 seconds)
-[doOne (1)] Wed Aug 31 21:09:28 CEST 2022 current status=0: execute next action '-ggttgg -nocpp -fltonly -inlonly'
-[doOne (1)] Wed Aug 31 21:09:28 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -nocpp -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m0.877s
-real	0m2.904s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:10:29.826720988 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:10:29.829595422 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:10:29.836990769 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:10:29.844910598 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2825634 seconds)
-[doOne (1)] Wed Aug 31 21:10:29 CEST 2022 current status=0: execute next action '-ggttgg -noneonly  '
-[doOne (1)] Wed Aug 31 21:10:29 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -noneonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m18.867s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:10:51.085395977 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:10:51.088219841 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:10:51.095478578 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:10:51.103258176 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2839226 seconds)
-[doOne (1)] Wed Aug 31 21:10:51 CEST 2022 current status=0: execute next action '-ggttgg -noneonly  -inlonly'
-[doOne (1)] Wed Aug 31 21:10:51 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -noneonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	1m24.975s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:12:20.502119759 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:12:20.505055458 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:12:20.512495868 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:12:20.520320601 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2855417 seconds)
-[doOne (1)] Wed Aug 31 21:12:20 CEST 2022 current status=0: execute next action '-ggttgg -noneonly -fltonly '
-[doOne (1)] Wed Aug 31 21:12:20 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -noneonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m18.006s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:12:41.048989091 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:12:41.051900945 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:12:41.059318225 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:12:41.067155878 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2888403 seconds)
-[doOne (1)] Wed Aug 31 21:12:41 CEST 2022 current status=0: execute next action '-ggttgg -noneonly -fltonly -inlonly'
-[doOne (1)] Wed Aug 31 21:12:41 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -noneonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	1m5.747s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:13:52.021274126 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:13:52.024204994 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:13:52.031666181 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:13:52.039435491 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2831688 seconds)
-[doOne (1)] Wed Aug 31 21:13:52 CEST 2022 current status=0: execute next action '-ggttgg -sse4only  '
-[doOne (1)] Wed Aug 31 21:13:52 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -sse4only  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m9.843s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:14:05.492492294 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:14:05.495351452 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:14:05.502748198 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:14:05.510581819 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2833760 seconds)
-[doOne (1)] Wed Aug 31 21:14:05 CEST 2022 current status=0: execute next action '-ggttgg -sse4only  -inlonly'
-[doOne (1)] Wed Aug 31 21:14:05 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -sse4only  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m11.799s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:14:23.098765086 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:14:23.101651763 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:14:23.108940001 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:14:23.116765132 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2838394 seconds)
-[doOne (1)] Wed Aug 31 21:14:23 CEST 2022 current status=0: execute next action '-ggttgg -sse4only -fltonly '
-[doOne (1)] Wed Aug 31 21:14:23 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -sse4only -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m4.784s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:14:31.373246073 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:14:31.376174009 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:14:31.383508650 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:14:31.391616118 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2879050 seconds)
-[doOne (1)] Wed Aug 31 21:14:31 CEST 2022 current status=0: execute next action '-ggttgg -sse4only -fltonly -inlonly'
-[doOne (1)] Wed Aug 31 21:14:31 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -sse4only -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m5.427s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:14:42.606674282 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:14:42.609536465 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:14:42.616867059 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:14:42.624757237 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2858182 seconds)
-[doOne (1)] Wed Aug 31 21:14:42 CEST 2022 current status=0: execute next action '-ggttgg -avx2only  '
-[doOne (1)] Wed Aug 31 21:14:42 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -avx2only  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m4.958s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:14:51.083084227 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:14:51.085998981 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:14:51.093382153 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:14:51.101194448 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2831402 seconds)
-[doOne (1)] Wed Aug 31 21:14:51 CEST 2022 current status=0: execute next action '-ggttgg -avx2only  -inlonly'
-[doOne (1)] Wed Aug 31 21:14:51 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -avx2only  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m6.065s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:15:04.323043158 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:15:04.325908922 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:15:04.333381711 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:15:04.341238053 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2850028 seconds)
-[doOne (1)] Wed Aug 31 21:15:04 CEST 2022 current status=0: execute next action '-ggttgg -avx2only -fltonly '
-[doOne (1)] Wed Aug 31 21:15:04 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -avx2only -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:43:31 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.avx2_f_inl0_hrd0/check.exe -p 2048 256 24 OMP=
+[doOne (1)] Sat Sep 24 23:43:38 CEST 2022 current status=0: completed action '-eemumu -avx2only -fltonly '
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:43:38.565728053 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:43:38.568612255 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:43:38.575915423 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:43:38.583804893 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2874550 seconds)
+[doOne (1)] Sat Sep 24 23:43:38 CEST 2022 current status=0: execute next action '-eemumu -avx2only -fltonly -inlonly'
+[doOne (1)] Sat Sep 24 23:43:38 CEST 2022 Will execute './throughputX.sh -makej -eemumu -avx2only -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m4.391s
+[doOne (1)] Sat Sep 24 23:43:58 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.avx2_f_inl1_hrd0/check.exe -p 2048 256 24 OMP=
+[doOne (1)] Sat Sep 24 23:44:05 CEST 2022 current status=0: completed action '-eemumu -avx2only -fltonly -inlonly'
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:44:05.587568292 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:44:05.590551073 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:44:05.597957641 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:44:05.605921817 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2865280 seconds)
+[doOne (1)] Sat Sep 24 23:44:05 CEST 2022 current status=0: execute next action '-eemumu -512yonly  '
+[doOne (1)] Sat Sep 24 23:44:05 CEST 2022 Will execute './throughputX.sh -makej -eemumu -512yonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m7.009s
+[doOne (1)] Sat Sep 24 23:44:20 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512y_d_inl0_hrd0/check.exe -p 2048 256 24 OMP=
+[doOne (1)] Sat Sep 24 23:44:27 CEST 2022 current status=0: completed action '-eemumu -512yonly  '
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:44:27.909234561 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:44:27.912151704 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:44:27.919547358 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:44:27.927447685 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2855560 seconds)
+[doOne (1)] Sat Sep 24 23:44:27 CEST 2022 current status=0: execute next action '-eemumu -512yonly  -inlonly'
+[doOne (1)] Sat Sep 24 23:44:27 CEST 2022 Will execute './throughputX.sh -makej -eemumu -512yonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m6.042s
+[doOne (1)] Sat Sep 24 23:44:41 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512y_d_inl1_hrd0/check.exe -p 2048 256 24 OMP=
+[doOne (1)] Sat Sep 24 23:44:49 CEST 2022 current status=0: completed action '-eemumu -512yonly  -inlonly'
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:44:49.227145746 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:44:49.229980275 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:44:49.237269064 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:44:49.245124408 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2857204 seconds)
+[doOne (1)] Sat Sep 24 23:44:49 CEST 2022 current status=0: execute next action '-eemumu -512yonly -fltonly '
+[doOne (1)] Sat Sep 24 23:44:49 CEST 2022 Will execute './throughputX.sh -makej -eemumu -512yonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m4.997s
+[doOne (1)] Sat Sep 24 23:45:02 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512y_f_inl0_hrd0/check.exe -p 2048 256 24 OMP=
+[doOne (1)] Sat Sep 24 23:45:09 CEST 2022 current status=0: completed action '-eemumu -512yonly -fltonly '
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:45:09.568227827 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:45:09.571095764 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:45:09.578483975 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:45:09.586492246 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2888694 seconds)
+[doOne (1)] Sat Sep 24 23:45:09 CEST 2022 current status=0: execute next action '-eemumu -512yonly -fltonly -inlonly'
+[doOne (1)] Sat Sep 24 23:45:09 CEST 2022 Will execute './throughputX.sh -makej -eemumu -512yonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m4.387s
+[doOne (1)] Sat Sep 24 23:45:21 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512y_f_inl1_hrd0/check.exe -p 2048 256 24 OMP=
+[doOne (1)] Sat Sep 24 23:45:29 CEST 2022 current status=0: completed action '-eemumu -512yonly -fltonly -inlonly'
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:45:29.253057892 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:45:29.255967451 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:45:29.263284367 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:45:29.271218478 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2882243 seconds)
+[doOne (1)] Sat Sep 24 23:45:29 CEST 2022 current status=0: execute next action '-eemumu -512zonly  '
+[doOne (1)] Sat Sep 24 23:45:29 CEST 2022 Will execute './throughputX.sh -makej -eemumu -512zonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m7.426s
+[doOne (1)] Sat Sep 24 23:45:53 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512z_d_inl0_hrd0/check.exe -p 2048 256 24 OMP=
+[doOne (1)] Sat Sep 24 23:46:00 CEST 2022 current status=0: completed action '-eemumu -512zonly  '
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:46:00.966775281 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:46:00.969692339 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:46:00.977043037 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:46:00.984906543 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2875820 seconds)
+[doOne (1)] Sat Sep 24 23:46:00 CEST 2022 current status=0: execute next action '-eemumu -512zonly  -inlonly'
+[doOne (1)] Sat Sep 24 23:46:00 CEST 2022 Will execute './throughputX.sh -makej -eemumu -512zonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m6.243s
+[doOne (1)] Sat Sep 24 23:46:22 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512z_d_inl1_hrd0/check.exe -p 2048 256 24 OMP=
+[doOne (1)] Sat Sep 24 23:46:30 CEST 2022 current status=0: completed action '-eemumu -512zonly  -inlonly'
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:46:30.064733890 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:46:30.067648513 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:46:30.075174279 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:46:30.083030498 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2860934 seconds)
+[doOne (1)] Sat Sep 24 23:46:30 CEST 2022 current status=0: execute next action '-eemumu -512zonly -fltonly '
+[doOne (1)] Sat Sep 24 23:46:30 CEST 2022 Will execute './throughputX.sh -makej -eemumu -512zonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m5.172s
+[doOne (1)] Sat Sep 24 23:46:52 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512z_f_inl0_hrd0/check.exe -p 2048 256 24 OMP=
+[doOne (1)] Sat Sep 24 23:46:59 CEST 2022 current status=0: completed action '-eemumu -512zonly -fltonly '
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:46:59.831260959 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:46:59.834208829 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:46:59.841558502 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:46:59.849465178 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2860815 seconds)
+[doOne (1)] Sat Sep 24 23:46:59 CEST 2022 current status=0: execute next action '-eemumu -512zonly -fltonly -inlonly'
+[doOne (1)] Sat Sep 24 23:46:59 CEST 2022 Will execute './throughputX.sh -makej -eemumu -512zonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m4.584s
+[doOne (1)] Sat Sep 24 23:47:21 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512z_f_inl1_hrd0/check.exe -p 2048 256 24 OMP=
+[doOne (1)] Sat Sep 24 23:47:28 CEST 2022 current status=0: completed action '-eemumu -512zonly -fltonly -inlonly'
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:47:28.867837184 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:47:28.870758981 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:47:28.878476271 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:47:28.886284163 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2844569 seconds)
+[doOne (1)] Sat Sep 24 23:47:28 CEST 2022 current status=0: execute next action '-ggtt -nocpp  '
+[doOne (1)] Sat Sep 24 23:47:28 CEST 2022 Will execute './throughputX.sh -makej -ggtt -nocpp  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m3.444s
+[doOne (1)] Sat Sep 24 23:48:34 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/gcheck.exe -p 2048 256 4 OMP=
+[doOne (1)] Sat Sep 24 23:48:42 CEST 2022 current status=0: completed action '-ggtt -nocpp  '
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:48:42.215248823 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:48:42.218038092 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:48:42.225810005 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:48:42.233684758 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2831180 seconds)
+[doOne (1)] Sat Sep 24 23:48:42 CEST 2022 current status=0: execute next action '-ggtt -nocpp  -inlonly'
+[doOne (1)] Sat Sep 24 23:48:42 CEST 2022 Will execute './throughputX.sh -makej -ggtt -nocpp  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m3.409s
+[doOne (1)] Sat Sep 24 23:49:25 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl1_hrd0/gcheck.exe -p 2048 256 4 OMP=
+[doOne (1)] Sat Sep 24 23:49:33 CEST 2022 current status=0: completed action '-ggtt -nocpp  -inlonly'
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:49:33.278894545 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:49:33.281743671 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:49:33.289283957 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:49:33.297171291 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2844970 seconds)
+[doOne (1)] Sat Sep 24 23:49:33 CEST 2022 current status=0: execute next action '-ggtt -nocpp -fltonly '
+[doOne (1)] Sat Sep 24 23:49:33 CEST 2022 Will execute './throughputX.sh -makej -ggtt -nocpp -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m2.986s
+[doOne (1)] Sat Sep 24 23:50:33 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/gcheck.exe -p 2048 256 4 OMP=
+[doOne (1)] Sat Sep 24 23:50:41 CEST 2022 current status=0: completed action '-ggtt -nocpp -fltonly '
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:50:41.212645834 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:50:41.215636164 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:50:41.223006177 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:50:41.230845110 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2837696 seconds)
+[doOne (1)] Sat Sep 24 23:50:41 CEST 2022 current status=0: execute next action '-ggtt -nocpp -fltonly -inlonly'
+[doOne (1)] Sat Sep 24 23:50:41 CEST 2022 Will execute './throughputX.sh -makej -ggtt -nocpp -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m2.932s
+[doOne (1)] Sat Sep 24 23:51:24 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl1_hrd0/gcheck.exe -p 2048 256 4 OMP=
+[doOne (1)] Sat Sep 24 23:51:31 CEST 2022 current status=0: completed action '-ggtt -nocpp -fltonly -inlonly'
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:51:31.741741154 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:51:31.744664046 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:51:31.752304207 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:51:31.760236324 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2876996 seconds)
+[doOne (1)] Sat Sep 24 23:51:31 CEST 2022 current status=0: execute next action '-ggtt -noneonly  '
+[doOne (1)] Sat Sep 24 23:51:31 CEST 2022 Will execute './throughputX.sh -makej -ggtt -noneonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m11.830s
+[doOne (1)] Sat Sep 24 23:51:51 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/check.exe -p 2048 256 4 OMP=
+[doOne (1)] Sat Sep 24 23:51:58 CEST 2022 current status=0: completed action '-ggtt -noneonly  '
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:51:58.713941822 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:51:58.716908972 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:51:58.724394570 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:51:58.732310732 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2889858 seconds)
+[doOne (1)] Sat Sep 24 23:51:58 CEST 2022 current status=0: execute next action '-ggtt -noneonly  -inlonly'
+[doOne (1)] Sat Sep 24 23:51:58 CEST 2022 Will execute './throughputX.sh -makej -ggtt -noneonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m9.857s
+[doOne (1)] Sat Sep 24 23:52:16 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl1_hrd0/check.exe -p 2048 256 4 OMP=
+[doOne (1)] Sat Sep 24 23:52:23 CEST 2022 current status=0: completed action '-ggtt -noneonly  -inlonly'
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:52:23.811293644 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:52:23.814120081 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:52:23.821434898 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:52:23.829287721 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2817458 seconds)
+[doOne (1)] Sat Sep 24 23:52:23 CEST 2022 current status=0: execute next action '-ggtt -noneonly -fltonly '
+[doOne (1)] Sat Sep 24 23:52:23 CEST 2022 Will execute './throughputX.sh -makej -ggtt -noneonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m11.150s
+[doOne (1)] Sat Sep 24 23:52:42 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/check.exe -p 2048 256 4 OMP=
+[doOne (1)] Sat Sep 24 23:52:50 CEST 2022 current status=0: completed action '-ggtt -noneonly -fltonly '
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:52:50.289725921 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:52:50.292598924 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:52:50.299977625 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:52:50.307908072 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2876618 seconds)
+[doOne (1)] Sat Sep 24 23:52:50 CEST 2022 current status=0: execute next action '-ggtt -noneonly -fltonly -inlonly'
+[doOne (1)] Sat Sep 24 23:52:50 CEST 2022 Will execute './throughputX.sh -makej -ggtt -noneonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m9.316s
+[doOne (1)] Sat Sep 24 23:53:07 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl1_hrd0/check.exe -p 2048 256 4 OMP=
+[doOne (1)] Sat Sep 24 23:53:14 CEST 2022 current status=0: completed action '-ggtt -noneonly -fltonly -inlonly'
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:53:14.825198971 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:53:14.828117500 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:53:14.835601130 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:53:14.843451923 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2841818 seconds)
+[doOne (1)] Sat Sep 24 23:53:14 CEST 2022 current status=0: execute next action '-ggtt -sse4only  '
+[doOne (1)] Sat Sep 24 23:53:14 CEST 2022 Will execute './throughputX.sh -makej -ggtt -sse4only  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m7.417s
+[doOne (1)] Sat Sep 24 23:53:39 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/check.exe -p 2048 256 4 OMP=
+[doOne (1)] Sat Sep 24 23:53:46 CEST 2022 current status=0: completed action '-ggtt -sse4only  '
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:53:46.837222969 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:53:46.840030861 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:53:46.847571475 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:53:46.855357040 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2835683 seconds)
+[doOne (1)] Sat Sep 24 23:53:46 CEST 2022 current status=0: execute next action '-ggtt -sse4only  -inlonly'
+[doOne (1)] Sat Sep 24 23:53:46 CEST 2022 Will execute './throughputX.sh -makej -ggtt -sse4only  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m8.443s
+[doOne (1)] Sat Sep 24 23:54:09 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl1_hrd0/check.exe -p 2048 256 4 OMP=
+[doOne (1)] Sat Sep 24 23:54:17 CEST 2022 current status=0: completed action '-ggtt -sse4only  -inlonly'
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:54:17.147132747 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:54:17.149974683 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:54:17.157357161 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:54:17.165279539 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2859620 seconds)
+[doOne (1)] Sat Sep 24 23:54:17 CEST 2022 current status=0: execute next action '-ggtt -sse4only -fltonly '
+[doOne (1)] Sat Sep 24 23:54:17 CEST 2022 Will execute './throughputX.sh -makej -ggtt -sse4only -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m5.102s
+[doOne (1)] Sat Sep 24 23:54:39 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/check.exe -p 2048 256 4 OMP=
+[doOne (1)] Sat Sep 24 23:54:47 CEST 2022 current status=0: completed action '-ggtt -sse4only -fltonly '
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:54:47.184909918 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:54:47.187833239 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:54:47.195350755 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:54:47.203246502 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2858833 seconds)
+[doOne (1)] Sat Sep 24 23:54:47 CEST 2022 current status=0: execute next action '-ggtt -sse4only -fltonly -inlonly'
+[doOne (1)] Sat Sep 24 23:54:47 CEST 2022 Will execute './throughputX.sh -makej -ggtt -sse4only -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m4.445s
+[doOne (1)] Sat Sep 24 23:55:06 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl1_hrd0/check.exe -p 2048 256 4 OMP=
+[doOne (1)] Sat Sep 24 23:55:13 CEST 2022 current status=0: completed action '-ggtt -sse4only -fltonly -inlonly'
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:55:13.536846269 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:55:13.539847736 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:55:13.547262247 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:55:13.555201862 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2867011 seconds)
+[doOne (1)] Sat Sep 24 23:55:13 CEST 2022 current status=0: execute next action '-ggtt -avx2only  '
+[doOne (1)] Sat Sep 24 23:55:13 CEST 2022 Will execute './throughputX.sh -makej -ggtt -avx2only  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m4.643s
+[doOne (1)] Sat Sep 24 23:55:36 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/check.exe -p 2048 256 4 OMP=
+[doOne (1)] Sat Sep 24 23:55:43 CEST 2022 current status=0: completed action '-ggtt -avx2only  '
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:55:43.548669328 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:55:43.551562379 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:55:43.559215246 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:55:43.567112363 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2849352 seconds)
+[doOne (1)] Sat Sep 24 23:55:43 CEST 2022 current status=0: execute next action '-ggtt -avx2only  -inlonly'
+[doOne (1)] Sat Sep 24 23:55:43 CEST 2022 Will execute './throughputX.sh -makej -ggtt -avx2only  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m5.440s
+[doOne (1)] Sat Sep 24 23:56:03 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl1_hrd0/check.exe -p 2048 256 4 OMP=
+[doOne (1)] Sat Sep 24 23:56:11 CEST 2022 current status=0: completed action '-ggtt -avx2only  -inlonly'
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:56:11.159449152 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:56:11.162374751 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:56:11.169704829 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:56:11.177553625 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2853732 seconds)
+[doOne (1)] Sat Sep 24 23:56:11 CEST 2022 current status=0: execute next action '-ggtt -avx2only -fltonly '
+[doOne (1)] Sat Sep 24 23:56:11 CEST 2022 Will execute './throughputX.sh -makej -ggtt -avx2only -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m2.726s
+[doOne (1)] Sat Sep 24 23:56:31 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/check.exe -p 2048 256 4 OMP=
+[doOne (1)] Sat Sep 24 23:56:38 CEST 2022 current status=0: completed action '-ggtt -avx2only -fltonly '
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:56:38.714579555 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:56:38.717531599 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:56:38.724868687 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:56:38.732811063 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2891519 seconds)
+[doOne (1)] Sat Sep 24 23:56:38 CEST 2022 current status=0: execute next action '-ggtt -avx2only -fltonly -inlonly'
+[doOne (1)] Sat Sep 24 23:56:38 CEST 2022 Will execute './throughputX.sh -makej -ggtt -avx2only -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m3.636s
+[doOne (1)] Sat Sep 24 23:56:57 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl1_hrd0/check.exe -p 2048 256 4 OMP=
+[doOne (1)] Sat Sep 24 23:57:05 CEST 2022 current status=0: completed action '-ggtt -avx2only -fltonly -inlonly'
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:57:05.223447944 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:57:05.226349817 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:57:05.234120891 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:57:05.241940315 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2844798 seconds)
+[doOne (1)] Sat Sep 24 23:57:05 CEST 2022 current status=0: execute next action '-ggtt -512yonly  '
+[doOne (1)] Sat Sep 24 23:57:05 CEST 2022 Will execute './throughputX.sh -makej -ggtt -512yonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m4.248s
+[doOne (1)] Sat Sep 24 23:57:17 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/check.exe -p 2048 256 4 OMP=
+[doOne (1)] Sat Sep 24 23:57:24 CEST 2022 current status=0: completed action '-ggtt -512yonly  '
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:57:24.752470351 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:57:24.755403394 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:57:24.762739848 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:57:24.770636710 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2862891 seconds)
+[doOne (1)] Sat Sep 24 23:57:24 CEST 2022 current status=0: execute next action '-ggtt -512yonly  -inlonly'
+[doOne (1)] Sat Sep 24 23:57:24 CEST 2022 Will execute './throughputX.sh -makej -ggtt -512yonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m5.253s
+[doOne (1)] Sat Sep 24 23:57:37 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl1_hrd0/check.exe -p 2048 256 4 OMP=
+[doOne (1)] Sat Sep 24 23:57:45 CEST 2022 current status=0: completed action '-ggtt -512yonly  -inlonly'
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:57:45.257903376 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:57:45.260810679 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:57:45.268125388 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:57:45.276064237 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2908865 seconds)
+[doOne (1)] Sat Sep 24 23:57:45 CEST 2022 current status=0: execute next action '-ggtt -512yonly -fltonly '
+[doOne (1)] Sat Sep 24 23:57:45 CEST 2022 Will execute './throughputX.sh -makej -ggtt -512yonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m2.587s
+[doOne (1)] Sat Sep 24 23:57:55 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/check.exe -p 2048 256 4 OMP=
+[doOne (1)] Sat Sep 24 23:58:03 CEST 2022 current status=0: completed action '-ggtt -512yonly -fltonly '
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:58:03.055331977 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:58:03.058166792 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:58:03.065663467 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:58:03.073627401 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2883116 seconds)
+[doOne (1)] Sat Sep 24 23:58:03 CEST 2022 current status=0: execute next action '-ggtt -512yonly -fltonly -inlonly'
+[doOne (1)] Sat Sep 24 23:58:03 CEST 2022 Will execute './throughputX.sh -makej -ggtt -512yonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m3.629s
+[doOne (1)] Sat Sep 24 23:58:14 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl1_hrd0/check.exe -p 2048 256 4 OMP=
+[doOne (1)] Sat Sep 24 23:58:21 CEST 2022 current status=0: completed action '-ggtt -512yonly -fltonly -inlonly'
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:58:21.930725832 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:58:21.933639593 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:58:21.941192967 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:58:21.949100495 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2888290 seconds)
+[doOne (1)] Sat Sep 24 23:58:21 CEST 2022 current status=0: execute next action '-ggtt -512zonly  '
+[doOne (1)] Sat Sep 24 23:58:21 CEST 2022 Will execute './throughputX.sh -makej -ggtt -512zonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m6.498s
+[doOne (1)] Sat Sep 24 23:58:45 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/check.exe -p 2048 256 4 OMP=
+[doOne (1)] Sat Sep 24 23:58:53 CEST 2022 current status=0: completed action '-ggtt -512zonly  '
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:58:53.469255131 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:58:53.472114753 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:58:53.479489333 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:58:53.487354202 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2824893 seconds)
+[doOne (1)] Sat Sep 24 23:58:53 CEST 2022 current status=0: execute next action '-ggtt -512zonly  -inlonly'
+[doOne (1)] Sat Sep 24 23:58:53 CEST 2022 Will execute './throughputX.sh -makej -ggtt -512zonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m6.938s
+[doOne (1)] Sat Sep 24 23:59:15 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl1_hrd0/check.exe -p 2048 256 4 OMP=
+[doOne (1)] Sat Sep 24 23:59:23 CEST 2022 current status=0: completed action '-ggtt -512zonly  -inlonly'
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:59:23.255427793 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:59:23.258260931 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:59:23.265768002 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:59:23.273701980 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2884102 seconds)
+[doOne (1)] Sat Sep 24 23:59:23 CEST 2022 current status=0: execute next action '-ggtt -512zonly -fltonly '
+[doOne (1)] Sat Sep 24 23:59:23 CEST 2022 Will execute './throughputX.sh -makej -ggtt -512zonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m3.385s
+[doOne (1)] Sat Sep 24 23:59:44 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/check.exe -p 2048 256 4 OMP=
+[doOne (1)] Sat Sep 24 23:59:51 CEST 2022 current status=0: completed action '-ggtt -512zonly -fltonly '
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:59:51.554884721 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:59:51.557761545 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:59:51.565113583 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sat 24 Sep 2022 23:59:51.572982803 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2853745 seconds)
+[doOne (1)] Sat Sep 24 23:59:51 CEST 2022 current status=0: execute next action '-ggtt -512zonly -fltonly -inlonly'
+[doOne (1)] Sat Sep 24 23:59:51 CEST 2022 Will execute './throughputX.sh -makej -ggtt -512zonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m4.416s
+[doOne (1)] Sun Sep 25 00:00:13 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl1_hrd0/check.exe -p 2048 256 4 OMP=
+[doOne (1)] Sun Sep 25 00:00:20 CEST 2022 current status=0: completed action '-ggtt -512zonly -fltonly -inlonly'
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:00:20.378419927 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:00:20.381301147 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:00:20.389049760 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:00:20.396892933 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2839343 seconds)
+[doOne (1)] Sun Sep 25 00:00:20 CEST 2022 current status=0: execute next action '-ggttg -nocpp  '
+[doOne (1)] Sun Sep 25 00:00:20 CEST 2022 Will execute './throughputX.sh -makej -ggttg -nocpp  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m3.426s
+real	0m4.926s
+[doOne (1)] Sun Sep 25 00:01:32 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl0_hrd0/gcheck.exe -p 64 256 20 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl0_hrd0/gcheck.exe -p 2048 256 2 OMP=
+[doOne (1)] Sun Sep 25 00:01:40 CEST 2022 current status=0: completed action '-ggttg -nocpp  '
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:01:40.111657938 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:01:40.114484537 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:01:40.122275789 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:01:40.130119639 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2842344 seconds)
+[doOne (1)] Sun Sep 25 00:01:40 CEST 2022 current status=0: execute next action '-ggttg -nocpp  -inlonly'
+[doOne (1)] Sun Sep 25 00:01:40 CEST 2022 Will execute './throughputX.sh -makej -ggttg -nocpp  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m3.392s
+real	0m4.911s
+[doOne (1)] Sun Sep 25 00:02:30 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl1_hrd0/gcheck.exe -p 64 256 20 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl1_hrd0/gcheck.exe -p 2048 256 2 OMP=
+[doOne (1)] Sun Sep 25 00:02:38 CEST 2022 current status=0: completed action '-ggttg -nocpp  -inlonly'
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:02:38.032154582 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:02:38.034996809 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:02:38.042409410 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:02:38.050233150 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2846883 seconds)
+[doOne (1)] Sun Sep 25 00:02:38 CEST 2022 current status=0: execute next action '-ggttg -nocpp -fltonly '
+[doOne (1)] Sun Sep 25 00:02:38 CEST 2022 Will execute './throughputX.sh -makej -ggttg -nocpp -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m2.945s
+real	0m2.972s
+[doOne (1)] Sun Sep 25 00:03:42 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl0_hrd0/gcheck.exe -p 64 256 20 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl0_hrd0/gcheck.exe -p 2048 256 2 OMP=
+[doOne (1)] Sun Sep 25 00:03:50 CEST 2022 current status=0: completed action '-ggttg -nocpp -fltonly '
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:03:50.203634692 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:03:50.206516632 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:03:50.213963354 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:03:50.221914757 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2888283 seconds)
+[doOne (1)] Sun Sep 25 00:03:50 CEST 2022 current status=0: execute next action '-ggttg -nocpp -fltonly -inlonly'
+[doOne (1)] Sun Sep 25 00:03:50 CEST 2022 Will execute './throughputX.sh -makej -ggttg -nocpp -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m2.902s
+real	0m2.957s
+[doOne (1)] Sun Sep 25 00:04:39 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl1_hrd0/gcheck.exe -p 64 256 20 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl1_hrd0/gcheck.exe -p 2048 256 2 OMP=
+[doOne (1)] Sun Sep 25 00:04:46 CEST 2022 current status=0: completed action '-ggttg -nocpp -fltonly -inlonly'
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:04:46.473351617 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:04:46.476260653 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:04:46.483834774 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:04:46.491763816 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2868683 seconds)
+[doOne (1)] Sun Sep 25 00:04:46 CEST 2022 current status=0: execute next action '-ggttg -noneonly  '
+[doOne (1)] Sun Sep 25 00:04:46 CEST 2022 Will execute './throughputX.sh -makej -ggttg -noneonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m13.930s
+[doOne (1)] Sun Sep 25 00:05:08 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl0_hrd0/check.exe -p 64 256 20 OMP=
+[doOne (1)] Sun Sep 25 00:05:15 CEST 2022 current status=0: completed action '-ggttg -noneonly  '
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:05:15.678306397 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:05:15.681185996 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:05:15.688833005 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:05:15.696896195 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2981445 seconds)
+[doOne (1)] Sun Sep 25 00:05:15 CEST 2022 current status=0: execute next action '-ggttg -noneonly  -inlonly'
+[doOne (1)] Sun Sep 25 00:05:15 CEST 2022 Will execute './throughputX.sh -makej -ggttg -noneonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m52.500s
+[doOne (1)] Sun Sep 25 00:06:16 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl1_hrd0/check.exe -p 64 256 20 OMP=
+[doOne (1)] Sun Sep 25 00:06:23 CEST 2022 current status=0: completed action '-ggttg -noneonly  -inlonly'
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:06:23.509954369 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:06:23.512833630 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:06:23.520320042 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:06:23.528235252 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2861284 seconds)
+[doOne (1)] Sun Sep 25 00:06:23 CEST 2022 current status=0: execute next action '-ggttg -noneonly -fltonly '
+[doOne (1)] Sun Sep 25 00:06:23 CEST 2022 Will execute './throughputX.sh -makej -ggttg -noneonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m13.572s
+[doOne (1)] Sun Sep 25 00:06:44 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl0_hrd0/check.exe -p 64 256 20 OMP=
+[doOne (1)] Sun Sep 25 00:06:52 CEST 2022 current status=0: completed action '-ggttg -noneonly -fltonly '
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:06:52.340845722 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:06:52.343726262 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:06:52.350995037 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:06:52.359030815 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2888175 seconds)
+[doOne (1)] Sun Sep 25 00:06:52 CEST 2022 current status=0: execute next action '-ggttg -noneonly -fltonly -inlonly'
+[doOne (1)] Sun Sep 25 00:06:52 CEST 2022 Will execute './throughputX.sh -makej -ggttg -noneonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m32.258s
+[doOne (1)] Sun Sep 25 00:07:32 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl1_hrd0/check.exe -p 64 256 20 OMP=
+[doOne (1)] Sun Sep 25 00:07:40 CEST 2022 current status=0: completed action '-ggttg -noneonly -fltonly -inlonly'
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:07:40.041508115 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:07:40.044456865 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:07:40.052017838 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:07:40.059868790 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2833696 seconds)
+[doOne (1)] Sun Sep 25 00:07:40 CEST 2022 current status=0: execute next action '-ggttg -sse4only  '
+[doOne (1)] Sun Sep 25 00:07:40 CEST 2022 Will execute './throughputX.sh -makej -ggttg -sse4only  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m7.493s
+[doOne (1)] Sun Sep 25 00:08:04 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_d_inl0_hrd0/check.exe -p 64 256 20 OMP=
+[doOne (1)] Sun Sep 25 00:08:12 CEST 2022 current status=0: completed action '-ggttg -sse4only  '
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:08:12.189988744 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:08:12.192941875 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:08:12.200287275 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:08:12.208224236 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2894750 seconds)
+[doOne (1)] Sun Sep 25 00:08:12 CEST 2022 current status=0: execute next action '-ggttg -sse4only  -inlonly'
+[doOne (1)] Sun Sep 25 00:08:12 CEST 2022 Will execute './throughputX.sh -makej -ggttg -sse4only  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m8.017s
+[doOne (1)] Sun Sep 25 00:08:34 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_d_inl1_hrd0/check.exe -p 64 256 20 OMP=
+[doOne (1)] Sun Sep 25 00:08:42 CEST 2022 current status=0: completed action '-ggttg -sse4only  -inlonly'
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:08:42.298662151 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:08:42.301456095 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:08:42.308957422 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:08:42.316843881 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2869685 seconds)
+[doOne (1)] Sun Sep 25 00:08:42 CEST 2022 current status=0: execute next action '-ggttg -sse4only -fltonly '
+[doOne (1)] Sun Sep 25 00:08:42 CEST 2022 Will execute './throughputX.sh -makej -ggttg -sse4only -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m4.162s
+[doOne (1)] Sun Sep 25 00:09:03 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_f_inl0_hrd0/check.exe -p 64 256 20 OMP=
+[doOne (1)] Sun Sep 25 00:09:11 CEST 2022 current status=0: completed action '-ggttg -sse4only -fltonly '
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:09:11.104556512 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:09:11.107436079 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:09:11.114834458 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:09:11.122764112 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2889705 seconds)
+[doOne (1)] Sun Sep 25 00:09:11 CEST 2022 current status=0: execute next action '-ggttg -sse4only -fltonly -inlonly'
+[doOne (1)] Sun Sep 25 00:09:11 CEST 2022 Will execute './throughputX.sh -makej -ggttg -sse4only -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m3.924s
+[doOne (1)] Sun Sep 25 00:09:29 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_f_inl1_hrd0/check.exe -p 64 256 20 OMP=
+[doOne (1)] Sun Sep 25 00:09:37 CEST 2022 current status=0: completed action '-ggttg -sse4only -fltonly -inlonly'
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:09:37.226308137 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:09:37.229307461 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:09:37.236954680 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:09:37.244918168 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2873997 seconds)
+[doOne (1)] Sun Sep 25 00:09:37 CEST 2022 current status=0: execute next action '-ggttg -avx2only  '
+[doOne (1)] Sun Sep 25 00:09:37 CEST 2022 Will execute './throughputX.sh -makej -ggttg -avx2only  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m3.949s
+[doOne (1)] Sun Sep 25 00:09:58 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_d_inl0_hrd0/check.exe -p 64 256 20 OMP=
+[doOne (1)] Sun Sep 25 00:10:06 CEST 2022 current status=0: completed action '-ggttg -avx2only  '
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:10:06.249300480 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:10:06.252146561 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:10:06.259671566 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:10:06.267568063 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2861471 seconds)
+[doOne (1)] Sun Sep 25 00:10:06 CEST 2022 current status=0: execute next action '-ggttg -avx2only  -inlonly'
+[doOne (1)] Sun Sep 25 00:10:06 CEST 2022 Will execute './throughputX.sh -makej -ggttg -avx2only  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m4.249s
+[doOne (1)] Sun Sep 25 00:10:25 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_d_inl1_hrd0/check.exe -p 64 256 20 OMP=
+[doOne (1)] Sun Sep 25 00:10:32 CEST 2022 current status=0: completed action '-ggttg -avx2only  -inlonly'
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:10:32.756160229 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:10:32.758976225 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:10:32.766267872 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:10:32.774047678 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2840298 seconds)
+[doOne (1)] Sun Sep 25 00:10:32 CEST 2022 current status=0: execute next action '-ggttg -avx2only -fltonly '
+[doOne (1)] Sun Sep 25 00:10:32 CEST 2022 Will execute './throughputX.sh -makej -ggttg -avx2only -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m2.046s
+[doOne (1)] Sun Sep 25 00:10:52 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_f_inl0_hrd0/check.exe -p 64 256 20 OMP=
+[doOne (1)] Sun Sep 25 00:11:00 CEST 2022 current status=0: completed action '-ggttg -avx2only -fltonly '
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:11:00.190151958 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:11:00.193004452 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:11:00.200500436 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:11:00.208385215 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2855082 seconds)
+[doOne (1)] Sun Sep 25 00:11:00 CEST 2022 current status=0: execute next action '-ggttg -avx2only -fltonly -inlonly'
+[doOne (1)] Sun Sep 25 00:11:00 CEST 2022 Will execute './throughputX.sh -makej -ggttg -avx2only -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m2.501s
+[doOne (1)] Sun Sep 25 00:11:17 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_f_inl1_hrd0/check.exe -p 64 256 20 OMP=
+[doOne (1)] Sun Sep 25 00:11:25 CEST 2022 current status=0: completed action '-ggttg -avx2only -fltonly -inlonly'
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:11:25.387592022 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:11:25.390556240 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:11:25.398139355 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:11:25.406000109 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2860661 seconds)
+[doOne (1)] Sun Sep 25 00:11:25 CEST 2022 current status=0: execute next action '-ggttg -512yonly  '
+[doOne (1)] Sun Sep 25 00:11:25 CEST 2022 Will execute './throughputX.sh -makej -ggttg -512yonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m3.471s
+[doOne (1)] Sun Sep 25 00:11:36 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_d_inl0_hrd0/check.exe -p 64 256 20 OMP=
+[doOne (1)] Sun Sep 25 00:11:44 CEST 2022 current status=0: completed action '-ggttg -512yonly  '
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:11:44.113972620 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:11:44.116853338 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:11:44.124242842 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:11:44.132171432 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2882814 seconds)
+[doOne (1)] Sun Sep 25 00:11:44 CEST 2022 current status=0: execute next action '-ggttg -512yonly  -inlonly'
+[doOne (1)] Sun Sep 25 00:11:44 CEST 2022 Will execute './throughputX.sh -makej -ggttg -512yonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m3.878s
+[doOne (1)] Sun Sep 25 00:11:55 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_d_inl1_hrd0/check.exe -p 64 256 20 OMP=
+[doOne (1)] Sun Sep 25 00:12:03 CEST 2022 current status=0: completed action '-ggttg -512yonly  -inlonly'
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:12:03.305381356 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:12:03.308288823 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:12:03.315618960 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:12:03.323551780 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2879511 seconds)
+[doOne (1)] Sun Sep 25 00:12:03 CEST 2022 current status=0: execute next action '-ggttg -512yonly -fltonly '
+[doOne (1)] Sun Sep 25 00:12:03 CEST 2022 Will execute './throughputX.sh -makej -ggttg -512yonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m1.822s
+[doOne (1)] Sun Sep 25 00:12:13 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_f_inl0_hrd0/check.exe -p 64 256 20 OMP=
+[doOne (1)] Sun Sep 25 00:12:20 CEST 2022 current status=0: completed action '-ggttg -512yonly -fltonly '
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:12:20.409956412 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:12:20.412889585 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:12:20.420206296 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:12:20.428057455 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2842344 seconds)
+[doOne (1)] Sun Sep 25 00:12:20 CEST 2022 current status=0: execute next action '-ggttg -512yonly -fltonly -inlonly'
+[doOne (1)] Sun Sep 25 00:12:20 CEST 2022 Will execute './throughputX.sh -makej -ggttg -512yonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m2.269s
+[doOne (1)] Sun Sep 25 00:12:30 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_f_inl1_hrd0/check.exe -p 64 256 20 OMP=
+[doOne (1)] Sun Sep 25 00:12:37 CEST 2022 current status=0: completed action '-ggttg -512yonly -fltonly -inlonly'
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:12:37.969594226 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:12:37.972468375 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:12:37.979968758 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:12:37.987797921 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2828983 seconds)
+[doOne (1)] Sun Sep 25 00:12:37 CEST 2022 current status=0: execute next action '-ggttg -512zonly  '
+[doOne (1)] Sun Sep 25 00:12:37 CEST 2022 Will execute './throughputX.sh -makej -ggttg -512zonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m4.732s
+[doOne (1)] Sun Sep 25 00:13:00 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_d_inl0_hrd0/check.exe -p 64 256 20 OMP=
+[doOne (1)] Sun Sep 25 00:13:07 CEST 2022 current status=0: completed action '-ggttg -512zonly  '
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:13:07.618451070 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:13:07.621327511 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:13:07.628762690 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:13:07.636630824 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2852102 seconds)
+[doOne (1)] Sun Sep 25 00:13:07 CEST 2022 current status=0: execute next action '-ggttg -512zonly  -inlonly'
+[doOne (1)] Sun Sep 25 00:13:07 CEST 2022 Will execute './throughputX.sh -makej -ggttg -512zonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m5.248s
+[doOne (1)] Sun Sep 25 00:13:28 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_d_inl1_hrd0/check.exe -p 64 256 20 OMP=
+[doOne (1)] Sun Sep 25 00:13:35 CEST 2022 current status=0: completed action '-ggttg -512zonly  -inlonly'
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:13:35.879195527 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:13:35.882087132 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:13:35.889402300 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:13:35.897259191 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2818839 seconds)
+[doOne (1)] Sun Sep 25 00:13:35 CEST 2022 current status=0: execute next action '-ggttg -512zonly -fltonly '
+[doOne (1)] Sun Sep 25 00:13:35 CEST 2022 Will execute './throughputX.sh -makej -ggttg -512zonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m2.355s
+[doOne (1)] Sun Sep 25 00:13:55 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_f_inl0_hrd0/check.exe -p 64 256 20 OMP=
+[doOne (1)] Sun Sep 25 00:14:03 CEST 2022 current status=0: completed action '-ggttg -512zonly -fltonly '
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:14:03.325956741 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:14:03.328829103 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:14:03.336665380 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:14:03.344541860 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2854780 seconds)
+[doOne (1)] Sun Sep 25 00:14:03 CEST 2022 current status=0: execute next action '-ggttg -512zonly -fltonly -inlonly'
+[doOne (1)] Sun Sep 25 00:14:03 CEST 2022 Will execute './throughputX.sh -makej -ggttg -512zonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m3.010s
+[doOne (1)] Sun Sep 25 00:14:23 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_f_inl1_hrd0/check.exe -p 64 256 20 OMP=
+[doOne (1)] Sun Sep 25 00:14:31 CEST 2022 current status=0: completed action '-ggttg -512zonly -fltonly -inlonly'
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:14:31.055472683 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:14:31.058373771 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:14:31.065794487 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:14:31.073727197 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2885522 seconds)
+[doOne (1)] Sun Sep 25 00:14:31 CEST 2022 current status=0: execute next action '-ggttgg -nocpp  '
+[doOne (1)] Sun Sep 25 00:14:31 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -nocpp  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m3.905s
+real	0m31.223s
+[doOne (1)] Sun Sep 25 00:16:39 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/gcheck.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/gcheck.exe -p 2048 256 2 OMP=
+[doOne (1)] Sun Sep 25 00:16:46 CEST 2022 current status=0: completed action '-ggttgg -nocpp  '
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:16:46.921859973 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:16:46.924733119 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:16:46.932182361 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:16:46.940014503 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2864968 seconds)
+[doOne (1)] Sun Sep 25 00:16:46 CEST 2022 current status=0: execute next action '-ggttgg -nocpp  -inlonly'
+[doOne (1)] Sun Sep 25 00:16:46 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -nocpp  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m3.744s
+real	0m27.929s
+[doOne (1)] Sun Sep 25 00:20:12 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl1_hrd0/gcheck.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl1_hrd0/gcheck.exe -p 2048 256 2 OMP=
+[doOne (1)] Sun Sep 25 00:20:20 CEST 2022 current status=0: completed action '-ggttgg -nocpp  -inlonly'
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:20:20.283905118 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:20:20.286777642 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:20:20.294177303 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:20:20.302142853 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2865061 seconds)
+[doOne (1)] Sun Sep 25 00:20:20 CEST 2022 current status=0: execute next action '-ggttgg -nocpp -fltonly '
+[doOne (1)] Sun Sep 25 00:20:20 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -nocpp -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m3.027s
+real	0m7.956s
+[doOne (1)] Sun Sep 25 00:21:55 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/gcheck.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/gcheck.exe -p 2048 256 2 OMP=
+[doOne (1)] Sun Sep 25 00:22:02 CEST 2022 current status=0: completed action '-ggttgg -nocpp -fltonly '
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:22:02.792317691 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:22:02.795352466 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:22:02.802885735 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:22:02.810914997 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2933220 seconds)
+[doOne (1)] Sun Sep 25 00:22:02 CEST 2022 current status=0: execute next action '-ggttgg -nocpp -fltonly -inlonly'
+[doOne (1)] Sun Sep 25 00:22:02 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -nocpp -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m3.013s
+real	0m8.837s
+[doOne (1)] Sun Sep 25 00:25:52 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl1_hrd0/gcheck.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl1_hrd0/gcheck.exe -p 2048 256 2 OMP=
+[doOne (1)] Sun Sep 25 00:25:59 CEST 2022 current status=0: completed action '-ggttgg -nocpp -fltonly -inlonly'
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:25:59.802449994 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:25:59.807314111 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:25:59.814690079 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:25:59.822563950 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2878221 seconds)
+[doOne (1)] Sun Sep 25 00:25:59 CEST 2022 current status=0: execute next action '-ggttgg -noneonly  '
+[doOne (1)] Sun Sep 25 00:25:59 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -noneonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m18.851s
+[doOne (1)] Sun Sep 25 00:26:26 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/check.exe -p 64 256 2 OMP=
+[doOne (1)] Sun Sep 25 00:26:34 CEST 2022 current status=0: completed action '-ggttgg -noneonly  '
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:26:34.365227411 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:26:34.368129549 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:26:34.375423354 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:26:34.383283479 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2833513 seconds)
+[doOne (1)] Sun Sep 25 00:26:34 CEST 2022 current status=0: execute next action '-ggttgg -noneonly  -inlonly'
+[doOne (1)] Sun Sep 25 00:26:34 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -noneonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	1m25.094s
+[doOne (1)] Sun Sep 25 00:28:08 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl1_hrd0/check.exe -p 64 256 2 OMP=
+[doOne (1)] Sun Sep 25 00:28:16 CEST 2022 current status=0: completed action '-ggttgg -noneonly  -inlonly'
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:28:16.407193709 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:28:16.410101986 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:28:16.417624581 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:28:16.425588425 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2931514 seconds)
+[doOne (1)] Sun Sep 25 00:28:16 CEST 2022 current status=0: execute next action '-ggttgg -noneonly -fltonly '
+[doOne (1)] Sun Sep 25 00:28:16 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -noneonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m17.958s
+[doOne (1)] Sun Sep 25 00:28:42 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/check.exe -p 64 256 2 OMP=
+[doOne (1)] Sun Sep 25 00:28:50 CEST 2022 current status=0: completed action '-ggttgg -noneonly -fltonly '
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:28:50.100835183 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:28:50.103703633 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:28:50.111007731 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:28:50.118880934 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2858770 seconds)
+[doOne (1)] Sun Sep 25 00:28:50 CEST 2022 current status=0: execute next action '-ggttgg -noneonly -fltonly -inlonly'
+[doOne (1)] Sun Sep 25 00:28:50 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -noneonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	1m5.700s
+[doOne (1)] Sun Sep 25 00:30:04 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl1_hrd0/check.exe -p 64 256 2 OMP=
+[doOne (1)] Sun Sep 25 00:30:12 CEST 2022 current status=0: completed action '-ggttgg -noneonly -fltonly -inlonly'
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:30:12.341670322 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:30:12.344480327 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:30:12.352062519 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:30:12.359881032 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2872304 seconds)
+[doOne (1)] Sun Sep 25 00:30:12 CEST 2022 current status=0: execute next action '-ggttgg -sse4only  '
+[doOne (1)] Sun Sep 25 00:30:12 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -sse4only  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m9.823s
+[doOne (1)] Sun Sep 25 00:30:39 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/check.exe -p 64 256 2 OMP=
+[doOne (1)] Sun Sep 25 00:30:47 CEST 2022 current status=0: completed action '-ggttgg -sse4only  '
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:30:47.141776660 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:30:47.144715582 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:30:47.152118617 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:30:47.160083810 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2929029 seconds)
+[doOne (1)] Sun Sep 25 00:30:47 CEST 2022 current status=0: execute next action '-ggttgg -sse4only  -inlonly'
+[doOne (1)] Sun Sep 25 00:30:47 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -sse4only  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m11.778s
+[doOne (1)] Sun Sep 25 00:32:05 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl1_hrd0/check.exe -p 64 256 2 OMP=
+[doOne (1)] Sun Sep 25 00:32:12 CEST 2022 current status=0: completed action '-ggttgg -sse4only  -inlonly'
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:32:12.449599979 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:32:12.452501783 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:32:12.459994592 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:32:12.467982895 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2883851 seconds)
+[doOne (1)] Sun Sep 25 00:32:12 CEST 2022 current status=0: execute next action '-ggttgg -sse4only -fltonly '
+[doOne (1)] Sun Sep 25 00:32:12 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -sse4only -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m4.776s
+[doOne (1)] Sun Sep 25 00:32:34 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/check.exe -p 64 256 2 OMP=
+[doOne (1)] Sun Sep 25 00:32:42 CEST 2022 current status=0: completed action '-ggttgg -sse4only -fltonly '
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:32:42.250601800 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:32:42.253525785 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:32:42.260856251 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:32:42.268917176 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2907940 seconds)
+[doOne (1)] Sun Sep 25 00:32:42 CEST 2022 current status=0: execute next action '-ggttgg -sse4only -fltonly -inlonly'
+[doOne (1)] Sun Sep 25 00:32:42 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -sse4only -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m5.411s
+[doOne (1)] Sun Sep 25 00:33:56 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl1_hrd0/check.exe -p 64 256 2 OMP=
+[doOne (1)] Sun Sep 25 00:34:04 CEST 2022 current status=0: completed action '-ggttgg -sse4only -fltonly -inlonly'
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:34:04.007827467 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:34:04.010717585 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:34:04.018255586 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:34:04.026158579 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2871472 seconds)
+[doOne (1)] Sun Sep 25 00:34:04 CEST 2022 current status=0: execute next action '-ggttgg -avx2only  '
+[doOne (1)] Sun Sep 25 00:34:04 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -avx2only  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m4.949s
+[doOne (1)] Sun Sep 25 00:34:26 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/check.exe -p 64 256 2 OMP=
+[doOne (1)] Sun Sep 25 00:34:33 CEST 2022 current status=0: completed action '-ggttgg -avx2only  '
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:34:33.961711276 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:34:33.964614916 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:34:33.971984098 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:34:33.979955552 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2896472 seconds)
+[doOne (1)] Sun Sep 25 00:34:33 CEST 2022 current status=0: execute next action '-ggttgg -avx2only  -inlonly'
+[doOne (1)] Sun Sep 25 00:34:33 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -avx2only  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m6.051s
+[doOne (1)] Sun Sep 25 00:35:51 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl1_hrd0/check.exe -p 64 256 2 OMP=
+[doOne (1)] Sun Sep 25 00:35:58 CEST 2022 current status=0: completed action '-ggttgg -avx2only  -inlonly'
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:35:58.724372583 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:35:58.727262066 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:35:58.734856686 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:35:58.742727024 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2852716 seconds)
+[doOne (1)] Sun Sep 25 00:35:58 CEST 2022 current status=0: execute next action '-ggttgg -avx2only -fltonly '
+[doOne (1)] Sun Sep 25 00:35:58 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -avx2only -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 real	0m2.486s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:15:10.400995762 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:15:10.403810947 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:15:10.411100630 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:15:10.419031500 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2876637 seconds)
-[doOne (1)] Wed Aug 31 21:15:10 CEST 2022 current status=0: execute next action '-ggttgg -avx2only -fltonly -inlonly'
-[doOne (1)] Wed Aug 31 21:15:10 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -avx2only -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m3.111s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:15:19.291752504 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:15:19.294664814 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:15:19.302166396 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:15:19.310133979 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2918798 seconds)
-[doOne (1)] Wed Aug 31 21:15:19 CEST 2022 current status=0: execute next action '-ggttgg -512yonly  '
-[doOne (1)] Wed Aug 31 21:15:19 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -512yonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m4.388s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:15:26.486285739 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:15:26.489073607 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:15:26.496362066 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:15:26.504232163 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2856081 seconds)
-[doOne (1)] Wed Aug 31 21:15:26 CEST 2022 current status=0: execute next action '-ggttgg -512yonly  -inlonly'
-[doOne (1)] Wed Aug 31 21:15:26 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -512yonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m4.795s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:15:35.596822674 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:15:35.599636712 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:15:35.607055180 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:15:35.614924859 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2824557 seconds)
-[doOne (1)] Wed Aug 31 21:15:35 CEST 2022 current status=0: execute next action '-ggttgg -512yonly -fltonly '
-[doOne (1)] Wed Aug 31 21:15:35 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -512yonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m2.224s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:15:40.094175055 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:15:40.097092019 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:15:40.104560479 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:15:40.112514756 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2894463 seconds)
-[doOne (1)] Wed Aug 31 21:15:40 CEST 2022 current status=0: execute next action '-ggttgg -512yonly -fltonly -inlonly'
-[doOne (1)] Wed Aug 31 21:15:40 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -512yonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m2.476s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:15:45.081034955 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:15:45.083881830 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:15:45.091259897 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:15:45.099310554 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2878204 seconds)
-[doOne (1)] Wed Aug 31 21:15:45 CEST 2022 current status=0: execute next action '-ggttgg -512zonly  '
-[doOne (1)] Wed Aug 31 21:15:45 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -512zonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m5.106s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:15:53.673103698 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:15:53.676011953 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:15:53.683244982 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:15:53.691110054 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2888857 seconds)
-[doOne (1)] Wed Aug 31 21:15:53 CEST 2022 current status=0: execute next action '-ggttgg -512zonly  -inlonly'
-[doOne (1)] Wed Aug 31 21:15:53 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -512zonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m5.061s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:16:02.361785647 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:16:02.364589326 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:16:02.371949609 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:16:02.379786524 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2903909 seconds)
-[doOne (1)] Wed Aug 31 21:16:02 CEST 2022 current status=0: execute next action '-ggttgg -512zonly -fltonly '
-[doOne (1)] Wed Aug 31 21:16:02 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -512zonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m2.543s
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:16:09.227186341 CEST semaphore initializing in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:16:09.229978427 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:16:09.237293372 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
-[doOne (1): syncprocesses] Wed 31 Aug 2022 21:16:09.245097561 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2816408 seconds)
-[doOne (1)] Wed Aug 31 21:16:09 CEST 2022 current status=0: execute next action '-ggttgg -512zonly -fltonly -inlonly'
-[doOne (1)] Wed Aug 31 21:16:09 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -512zonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
-real	0m2.626s
-[doOne (1)] Wed Aug 31 21:16:15 CEST 2022 copy /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu to /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/build/madgraph4gpu
-[doOne (1)] Wed Aug 31 21:16:28 CEST 2022 completed (status=0)
+[doOne (1)] Sun Sep 25 00:36:18 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/check.exe -p 64 256 2 OMP=
+[doOne (1)] Sun Sep 25 00:36:25 CEST 2022 current status=0: completed action '-ggttgg -avx2only -fltonly '
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:36:25.982214412 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:36:25.985005623 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:36:25.992359847 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:36:26.000282827 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2844604 seconds)
+[doOne (1)] Sun Sep 25 00:36:26 CEST 2022 current status=0: execute next action '-ggttgg -avx2only -fltonly -inlonly'
+[doOne (1)] Sun Sep 25 00:36:26 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -avx2only -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m3.099s
+[doOne (1)] Sun Sep 25 00:37:41 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl1_hrd0/check.exe -p 64 256 2 OMP=
+[doOne (1)] Sun Sep 25 00:37:48 CEST 2022 current status=0: completed action '-ggttgg -avx2only -fltonly -inlonly'
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:37:48.789968996 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:37:48.792788772 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:37:48.800341251 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:37:48.808201583 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2837060 seconds)
+[doOne (1)] Sun Sep 25 00:37:48 CEST 2022 current status=0: execute next action '-ggttgg -512yonly  '
+[doOne (1)] Sun Sep 25 00:37:48 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -512yonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m4.386s
+[doOne (1)] Sun Sep 25 00:38:01 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/check.exe -p 64 256 2 OMP=
+[doOne (1)] Sun Sep 25 00:38:08 CEST 2022 current status=0: completed action '-ggttgg -512yonly  '
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:38:08.557371886 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:38:08.560265180 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:38:08.567548299 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:38:08.575448250 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2870998 seconds)
+[doOne (1)] Sun Sep 25 00:38:08 CEST 2022 current status=0: execute next action '-ggttgg -512yonly  -inlonly'
+[doOne (1)] Sun Sep 25 00:38:08 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -512yonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m4.785s
+[doOne (1)] Sun Sep 25 00:38:21 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl1_hrd0/check.exe -p 64 256 2 OMP=
+[doOne (1)] Sun Sep 25 00:38:28 CEST 2022 current status=0: completed action '-ggttgg -512yonly  -inlonly'
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:38:28.888250148 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:38:28.891099185 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:38:28.898388501 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:38:28.906280379 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2858813 seconds)
+[doOne (1)] Sun Sep 25 00:38:28 CEST 2022 current status=0: execute next action '-ggttgg -512yonly -fltonly '
+[doOne (1)] Sun Sep 25 00:38:28 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -512yonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m2.236s
+[doOne (1)] Sun Sep 25 00:38:39 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/check.exe -p 64 256 2 OMP=
+[doOne (1)] Sun Sep 25 00:38:46 CEST 2022 current status=0: completed action '-ggttgg -512yonly -fltonly '
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:38:46.367946703 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:38:46.370934969 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:38:46.378616349 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:38:46.386494153 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2844901 seconds)
+[doOne (1)] Sun Sep 25 00:38:46 CEST 2022 current status=0: execute next action '-ggttgg -512yonly -fltonly -inlonly'
+[doOne (1)] Sun Sep 25 00:38:46 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -512yonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m2.472s
+[doOne (1)] Sun Sep 25 00:38:56 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl1_hrd0/check.exe -p 64 256 2 OMP=
+[doOne (1)] Sun Sep 25 00:39:04 CEST 2022 current status=0: completed action '-ggttgg -512yonly -fltonly -inlonly'
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:39:04.404153150 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:39:04.407009580 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:39:04.414666037 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:39:04.422554948 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2868415 seconds)
+[doOne (1)] Sun Sep 25 00:39:04 CEST 2022 current status=0: execute next action '-ggttgg -512zonly  '
+[doOne (1)] Sun Sep 25 00:39:04 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -512zonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m5.093s
+[doOne (1)] Sun Sep 25 00:39:27 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/check.exe -p 64 256 2 OMP=
+[doOne (1)] Sun Sep 25 00:39:34 CEST 2022 current status=0: completed action '-ggttgg -512zonly  '
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:39:34.452784937 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:39:34.455673167 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:39:34.463005804 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:39:34.470848694 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2835479 seconds)
+[doOne (1)] Sun Sep 25 00:39:34 CEST 2022 current status=0: execute next action '-ggttgg -512zonly  -inlonly'
+[doOne (1)] Sun Sep 25 00:39:34 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -512zonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m5.044s
+[doOne (1)] Sun Sep 25 00:40:51 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl1_hrd0/check.exe -p 64 256 2 OMP=
+[doOne (1)] Sun Sep 25 00:40:58 CEST 2022 current status=0: completed action '-ggttgg -512zonly  -inlonly'
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:40:58.572296143 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:40:58.575191595 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:40:58.582794928 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:40:58.590755098 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2888427 seconds)
+[doOne (1)] Sun Sep 25 00:40:58 CEST 2022 current status=0: execute next action '-ggttgg -512zonly -fltonly '
+[doOne (1)] Sun Sep 25 00:40:58 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -512zonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m2.542s
+[doOne (1)] Sun Sep 25 00:41:18 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/check.exe -p 64 256 2 OMP=
+[doOne (1)] Sun Sep 25 00:41:25 CEST 2022 current status=0: completed action '-ggttgg -512zonly -fltonly '
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:41:25.921547831 CEST semaphore invoked for a new action in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:41:25.924341530 CEST semaphore.RUNNING: previous action has successfully completed, now WAIT
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:41:25.931709671 CEST semaphore master: all 1 processes are in the WAIT state, send the GO signal
+[doOne (1): syncprocesses] Sun 25 Sep 2022 00:41:25.939582893 CEST semaphore.GO: start RUNNING a new action (delay from GO: 0.2874803 seconds)
+[doOne (1)] Sun Sep 25 00:41:25 CEST 2022 current status=0: execute next action '-ggttgg -512zonly -fltonly -inlonly'
+[doOne (1)] Sun Sep 25 00:41:25 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -512zonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
+real	0m2.612s
+[doOne (1)] Sun Sep 25 00:42:38 CEST 2022 Have executed these runExe:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl1_hrd0/check.exe -p 64 256 2 OMP=
+[doOne (1)] Sun Sep 25 00:42:45 CEST 2022 current status=0: completed action '-ggttgg -512zonly -fltonly -inlonly'
+[doOne (1)] Sun Sep 25 00:42:45 CEST 2022 copy /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu to /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/build/madgraph4gpu
+[doOne (1)] Sun Sep 25 00:43:19 CEST 2022 completed (status=0)
 
-[doOneWrapper (1)] Wed Aug 31 21:16:28 CEST 2022 : process 1 (pid=50) completed ok
+[doOneWrapper (1)] Sun Sep 25 00:43:19 CEST 2022 : process 1 (pid=50) completed ok
 
diff --git a/mg5amc/madgraph4gpu-2022/mg5amc-madgraph4gpu-2022/jobs/good_1/proc_1/out_1.log b/mg5amc/madgraph4gpu-2022/mg5amc-madgraph4gpu-2022/jobs/good_1/proc_1/out_1.log
index 6275e108cbecf842a7b59b4839bfb6a4528153c5..07a0d51244effc54fd62c63baf5c6cb453164a63 100644
--- a/mg5amc/madgraph4gpu-2022/mg5amc-madgraph4gpu-2022/jobs/good_1/proc_1/out_1.log
+++ b/mg5amc/madgraph4gpu-2022/mg5amc-madgraph4gpu-2022/jobs/good_1/proc_1/out_1.log
@@ -1,6 +1,6 @@
-[doOne (1)] Wed Aug 31 20:55:29 CEST 2022 Will execute './throughputX.sh -makej -eemumu -nocpp  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:34:08 CEST 2022 Will execute './throughputX.sh -makej -eemumu -nocpp  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 git clone https://github.com/google/googletest.git -b release-1.11.0 googletest
 Cloning into 'googletest'...
 Note: checking out 'e2239ee6043f73722e7aa812a459f54a28552929'.
@@ -40,30 +40,30 @@ cd googletest/build && cmake -DBUILD_GMOCK=OFF ../
 -- Found Threads: TRUE  
 -- Configuring done
 -- Generating done
--- Build files have been written to: /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test/googletest/build
+-- Build files have been written to: /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test/googletest/build
 make -C googletest/build
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test/googletest/build'
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test/googletest/build'
-make[3]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test/googletest/build'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test/googletest/build'
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test/googletest/build'
+make[3]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test/googletest/build'
 Scanning dependencies of target gtest
-make[3]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test/googletest/build'
-make[3]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test/googletest/build'
+make[3]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test/googletest/build'
+make[3]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test/googletest/build'
 [ 25%] Building CXX object googletest/CMakeFiles/gtest.dir/src/gtest-all.cc.o
 [ 50%] Linking CXX static library ../lib/libgtest.a
-make[3]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test/googletest/build'
+make[3]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test/googletest/build'
 [ 50%] Built target gtest
-make[3]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test/googletest/build'
+make[3]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test/googletest/build'
 Scanning dependencies of target gtest_main
-make[3]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test/googletest/build'
-make[3]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test/googletest/build'
+make[3]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test/googletest/build'
+make[3]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test/googletest/build'
 [ 75%] Building CXX object googletest/CMakeFiles/gtest_main.dir/src/gtest_main.cc.o
 [100%] Linking CXX static library ../lib/libgtest_main.a
-make[3]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test/googletest/build'
+make[3]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test/googletest/build'
 [100%] Built target gtest_main
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test/googletest/build'
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test/googletest/build'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test/googletest/build'
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test/googletest/build'
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
 CUDACPP_BUILDDIR='build.none_d_inl0_hrd0'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -w -cpp  -c myamp.f -I../../Source/ -fopenmp -o myamp.o
 cd ../../Source; make
@@ -82,7 +82,7 @@ ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfort
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -std=c++11 -Wall -Wshadow -Wextra -c counters.cpp -o counters.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -w -cpp  -c -DMG5AMC_MEEXPORTER_CUDACPP auto_dsig1.f -I../../Source/ -fopenmp -o auto_dsig1_cudacpp.o
 make -f cudacpp.mk
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/Source'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/Source'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o StringCast.o StringCast.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o ranmar.o ranmar.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o alfas_functions.o alfas_functions.f
@@ -106,126 +106,127 @@ cd PDF; make
 cd MODEL; make    
 cd CERNLIB; make
 cd BIAS/dummy; make
-OMPFLAGS=
-AVX=none
-FPTYPE=d
-HELINL=0
-HRDCOD=0
-RNDGEN=hasCurand
-Building in BUILDDIR=build.none_d_inl0_hrd0 for tag=none_d_inl0_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/Source/BIAS/dummy'
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/Source/BIAS/dummy'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o dummy.o dummy.f
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/Source/CERNLIB'
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o abend.o abend.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o dlsqp2.o dlsqp2.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o lenocc.o lenocc.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o mtlprt.o mtlprt.f
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/Source/DHELAS'
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o aloha_functions.o aloha_functions.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o mtlset.o mtlset.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o FFV2_0.o FFV2_0.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o FFV2_3.o FFV2_3.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o radmul.o radmul.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o FFV1P0_3.o FFV1P0_3.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o FFV1_0.o FFV1_0.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o FFV4_3.o FFV4_3.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o FFV4_0.o FFV4_0.f
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/Source/PDF'
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/Source/MODEL'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o couplings.o couplings.f
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/Source/PDF'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o Ctq6Pdf.o Ctq6Pdf.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o lha_read.o lha_read.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o pdfwrap.o pdfwrap.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o printout.o printout.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o opendata.o opendata.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I.. -c -o rw_para.o rw_para.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o model_functions.o model_functions.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o pdf.o pdf.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o couplings1.o couplings1.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o PhotonFlux.o PhotonFlux.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o couplings2.o couplings2.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o pdg2pdf.o pdg2pdf.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o NNPDFDriver.o NNPDFDriver.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o eepdf.o eepdf.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o gridpdfaux.o gridpdfaux.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o dfint.o dfint.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o kerset.o kerset.f
+OMPFLAGS=
+AVX=none
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/Source/CERNLIB'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o abend.o abend.f
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/Source/DHELAS'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o aloha_functions.o aloha_functions.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o ElectroweakFluxDriver.o ElectroweakFluxDriver.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o dlsqp2.o dlsqp2.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o lenocc.o lenocc.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o ElectroweakFlux.o ElectroweakFlux.f
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/Source/MODEL'
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o couplings.o couplings.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o lha_read.o lha_read.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o printout.o printout.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I.. -c -o rw_para.o rw_para.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o model_functions.o model_functions.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o couplings1.o couplings1.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o couplings2.o couplings2.f
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o FFV2_0.o FFV2_0.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o mtlprt.o mtlprt.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o FFV2_3.o FFV2_3.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o mtlset.o mtlset.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o FFV1P0_3.o FFV1P0_3.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o radmul.o radmul.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o FFV1_0.o FFV1_0.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o FFV4_3.o FFV4_3.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o FFV4_0.o FFV4_0.f
+FPTYPE=d
+HELINL=0
+HRDCOD=0
+RNDGEN=hasCurand
+Building in BUILDDIR=build.none_d_inl0_hrd0 for tag=none_d_inl0_hrd0_hasCurand (USEBUILDDIR is set = 1)
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.none_d_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gcheck_sa.cu -o build.none_d_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gcheck_sa.cu -o build.none_d_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gCPPProcess.cu -o build.none_d_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.none_d_inl0_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gBridgeKernels.cu -o build.none_d_inl0_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.none_d_inl0_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fbridge.cc -o build.none_d_inl0_hrd0/fbridge_cu.o
 AVX=none
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gCPPProcess.cu -o build.none_d_inl0_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.none_d_inl0_hrd0/gMatrixElementKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gBridgeKernels.cu -o build.none_d_inl0_hrd0/gBridgeKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -c Parameters_sm.cc -o build.none_d_inl0_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -c read_slha.cc -o build.none_d_inl0_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.none_d_inl0_hrd0/gCrossSectionKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fbridge.cc -o build.none_d_inl0_hrd0/fbridge_cu.o
-mkdir -p ../lib/build.none_d_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.none_d_inl0_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.none_d_inl0_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.none_d_inl0_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.none_d_inl0_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.none_d_inl0_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.none_d_inl0_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.none_d_inl0_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.none_d_inl0_hrd0/BridgeKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.none_d_inl0_hrd0/CrossSectionKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.none_d_inl0_hrd0/fbridge.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.none_d_inl0_hrd0/RandomNumberKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -c Parameters_sm.cc -o build.none_d_inl0_hrd0/Parameters_sm.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -c read_slha.cc -o build.none_d_inl0_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.none_d_inl0_hrd0/RamboSamplingKernels.o
+mkdir -p ../lib/build.none_d_inl0_hrd0
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.none_d_inl0_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testxxx.cc -o build.none_d_inl0_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testxxx.cc -o build.none_d_inl0_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.none_d_inl0_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testmisc.cc -o build.none_d_inl0_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testmisc.cc -o build.none_d_inl0_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.none_d_inl0_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu runTest.cc -o build.none_d_inl0_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu runTest.cc -o build.none_d_inl0_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.none_d_inl0_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fsampler.cc -o build.none_d_inl0_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fsampler.cc -o build.none_d_inl0_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.none_d_inl0_hrd0/fsampler.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.none_d_inl0_hrd0/libmg5amc_common.so build.none_d_inl0_hrd0/Parameters_sm.o build.none_d_inl0_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.none_d_inl0_hrd0/libmg5amc_ll_ll_cpp.so build.none_d_inl0_hrd0/CPPProcess.o build.none_d_inl0_hrd0/MatrixElementKernels.o build.none_d_inl0_hrd0/BridgeKernels.o build.none_d_inl0_hrd0/CrossSectionKernels.o build.none_d_inl0_hrd0/fbridge.o -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_d_inl0_hrd0/check.exe build.none_d_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_ll_ll_cpp build.none_d_inl0_hrd0/RandomNumberKernels.o build.none_d_inl0_hrd0/RamboSamplingKernels.o
 ar cru  ../../../lib/libbias.a  dummy.o
 ranlib  ../../../lib/libbias.a
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/Source/BIAS/dummy'
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_d_inl0_hrd0/fcheck.exe build.none_d_inl0_hrd0/fcheck_sa.o build.none_d_inl0_hrd0/fsampler.o -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_ll_ll_cpp build.none_d_inl0_hrd0/RandomNumberKernels.o build.none_d_inl0_hrd0/RamboSamplingKernels.o
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/Source/BIAS/dummy'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.none_d_inl0_hrd0/libmg5amc_common.so build.none_d_inl0_hrd0/Parameters_sm.o build.none_d_inl0_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o DiscreteSampler.o DiscreteSampler.f
 ar cru  ../../lib/libcernlib.a  abend.o dlsqp2.o lenocc.o mtlprt.o mtlset.o radmul.o
 ranlib  ../../lib/libcernlib.a
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/Source/CERNLIB'
 ar cru  ../../lib/libpdf.a  Ctq6Pdf.o pdfwrap.o opendata.o pdf.o PhotonFlux.o pdg2pdf.o NNPDFDriver.o eepdf.o gridpdfaux.o dfint.o kerset.o ElectroweakFluxDriver.o ElectroweakFlux.o
-ar cru  ../../lib/libmodel.a  couplings.o lha_read.o printout.o rw_para.o model_functions.o couplings1.o couplings2.o
 ranlib  ../../lib/libpdf.a
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/Source/PDF'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/Source/CERNLIB'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/Source/PDF'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.none_d_inl0_hrd0/libmg5amc_ll_ll_cpp.so build.none_d_inl0_hrd0/CPPProcess.o build.none_d_inl0_hrd0/MatrixElementKernels.o build.none_d_inl0_hrd0/BridgeKernels.o build.none_d_inl0_hrd0/CrossSectionKernels.o build.none_d_inl0_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_d_inl0_hrd0/check.exe build.none_d_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_d_inl0_hrd0'  -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_ll_ll_cpp build.none_d_inl0_hrd0/RandomNumberKernels.o build.none_d_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_d_inl0_hrd0/fcheck.exe build.none_d_inl0_hrd0/fcheck_sa.o build.none_d_inl0_hrd0/fsampler.o -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_d_inl0_hrd0'  -lgfortran -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_ll_ll_cpp build.none_d_inl0_hrd0/RandomNumberKernels.o build.none_d_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ar cru  ../../lib/libmodel.a  couplings.o lha_read.o printout.o rw_para.o model_functions.o couplings1.o couplings2.o
 ranlib  ../../lib/libmodel.a
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/Source/MODEL'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/Source/MODEL'
 ar cru  ../lib/libgeneric.a  alfas_functions.o transpole.o invarients.o hfill.o pawgraphs.o ran1.o rw_events.o rw_routines.o kin_functions.o open_file.o basecode.o setrun.o run_printout.o dgauss.o readgrid.o getissud.o
 ranlib  ../lib/libgeneric.a
 ar cru  ../../lib/libdhelas.a  aloha_functions.o FFV2_0.o FFV2_3.o FFV1P0_3.o FFV1_0.o FFV4_3.o FFV4_0.o
 ranlib  ../../lib/libdhelas.a
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/Source/DHELAS'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/Source/DHELAS'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o dsample.o dsample.f
 ar cru  ../lib/libdsample.a  dsample.o ranmar.o DiscreteSampler.o StringCast.o
 ranlib  ../lib/libdsample.a
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/Source'
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/Source'
 touch .libs
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -w -cpp  -c genps.f -I../../Source/ -fopenmp -o genps.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -w -cpp  -c driver.f -I../../Source/ -fopenmp -o driver.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -w -cpp  -c auto_dsig.f -I../../Source/ -fopenmp -o auto_dsig.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -w -cpp   -c matrix1.f -I../../Source/ -fopenmp
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -w -cpp  -c -DMG5AMC_MEEXPORTER_CUDACPP driver.f -I../../Source/ -fopenmp -o driver_cudacpp.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o madevent myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver.o  auto_dsig1.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.none_d_inl0_hrd0/libmg5amc_ll_ll_cuda.so build.none_d_inl0_hrd0/gCPPProcess.o build.none_d_inl0_hrd0/gMatrixElementKernels.o build.none_d_inl0_hrd0/gBridgeKernels.o build.none_d_inl0_hrd0/gCrossSectionKernels.o build.none_d_inl0_hrd0/fbridge_cu.o -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl0_hrd0/fgcheck.exe build.none_d_inl0_hrd0/fcheck_sa.o build.none_d_inl0_hrd0/fsampler_cu.o -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_ll_ll_cuda build.none_d_inl0_hrd0/gRandomNumberKernels.o build.none_d_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl0_hrd0/gcheck.exe build.none_d_inl0_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_ll_ll_cuda build.none_d_inl0_hrd0/gRandomNumberKernels.o build.none_d_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl0_hrd0/runTest.exe build.none_d_inl0_hrd0/CPPProcess.o build.none_d_inl0_hrd0/MatrixElementKernels.o build.none_d_inl0_hrd0/BridgeKernels.o build.none_d_inl0_hrd0/CrossSectionKernels.o build.none_d_inl0_hrd0/RandomNumberKernels.o build.none_d_inl0_hrd0/RamboSamplingKernels.o build.none_d_inl0_hrd0/testxxx.o  build.none_d_inl0_hrd0/testmisc.o  build.none_d_inl0_hrd0/runTest.o build.none_d_inl0_hrd0/gCPPProcess.o build.none_d_inl0_hrd0/gMatrixElementKernels.o build.none_d_inl0_hrd0/gBridgeKernels.o build.none_d_inl0_hrd0/gCrossSectionKernels.o build.none_d_inl0_hrd0/gRandomNumberKernels.o build.none_d_inl0_hrd0/gRamboSamplingKernels.o build.none_d_inl0_hrd0/testxxx_cu.o  build.none_d_inl0_hrd0/testmisc_cu.o  build.none_d_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o madevent myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver.o  auto_dsig1.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -lstdc++  -Wl,--no-relax 
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.none_d_inl0_hrd0/libmg5amc_ll_ll_cuda.so build.none_d_inl0_hrd0/gCPPProcess.o build.none_d_inl0_hrd0/gMatrixElementKernels.o build.none_d_inl0_hrd0/gBridgeKernels.o build.none_d_inl0_hrd0/gCrossSectionKernels.o build.none_d_inl0_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl0_hrd0/fgcheck.exe build.none_d_inl0_hrd0/fcheck_sa.o build.none_d_inl0_hrd0/fsampler_cu.o -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl0_hrd0'  -lgfortran -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_ll_ll_cuda build.none_d_inl0_hrd0/gRandomNumberKernels.o build.none_d_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl0_hrd0/gcheck.exe build.none_d_inl0_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl0_hrd0'  -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_ll_ll_cuda build.none_d_inl0_hrd0/gRandomNumberKernels.o build.none_d_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl0_hrd0/runTest.exe build.none_d_inl0_hrd0/CPPProcess.o build.none_d_inl0_hrd0/MatrixElementKernels.o build.none_d_inl0_hrd0/BridgeKernels.o build.none_d_inl0_hrd0/CrossSectionKernels.o build.none_d_inl0_hrd0/RandomNumberKernels.o build.none_d_inl0_hrd0/RamboSamplingKernels.o build.none_d_inl0_hrd0/testxxx.o  build.none_d_inl0_hrd0/testmisc.o  build.none_d_inl0_hrd0/runTest.o build.none_d_inl0_hrd0/gCPPProcess.o build.none_d_inl0_hrd0/gMatrixElementKernels.o build.none_d_inl0_hrd0/gBridgeKernels.o build.none_d_inl0_hrd0/gCrossSectionKernels.o build.none_d_inl0_hrd0/gRandomNumberKernels.o build.none_d_inl0_hrd0/gRamboSamplingKernels.o build.none_d_inl0_hrd0/testxxx_cu.o  build.none_d_inl0_hrd0/testmisc_cu.o  build.none_d_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl0_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
 touch build.none_d_inl0_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_d_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.none_d_inl0_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.none_d_inl0_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_d_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.none_d_inl0_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.none_d_inl0_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.none_d_inl0_hrd0/libmg5amc_ll_ll_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_d_inl0_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.none_d_inl0_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.none_d_inl0_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
 CUDACPP_BUILDDIR='build.512y_d_inl0_hrd0'
 make -f cudacpp.mk
@@ -236,71 +237,72 @@ HELINL=0
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.512y_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.512y_d_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gcheck_sa.cu -o build.512y_d_inl0_hrd0/gcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gCPPProcess.cu -o build.512y_d_inl0_hrd0/gCPPProcess.o
-AVX=512y
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512y_d_inl0_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512y_d_inl0_hrd0/gBridgeKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512y_d_inl0_hrd0/gCrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -c Parameters_sm.cc -o build.512y_d_inl0_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -c read_slha.cc -o build.512y_d_inl0_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512y_d_inl0_hrd0/fbridge_cu.o
-mkdir -p ../lib/build.512y_d_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512y_d_inl0_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512y_d_inl0_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gcheck_sa.cu -o build.512y_d_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gCPPProcess.cu -o build.512y_d_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512y_d_inl0_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512y_d_inl0_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512y_d_inl0_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512y_d_inl0_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512y_d_inl0_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512y_d_inl0_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.512y_d_inl0_hrd0/check_sa.o
+AVX=512y
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.512y_d_inl0_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.512y_d_inl0_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.512y_d_inl0_hrd0/BridgeKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.512y_d_inl0_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.512y_d_inl0_hrd0/fbridge.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.512y_d_inl0_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.512y_d_inl0_hrd0/RandomNumberKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.512y_d_inl0_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.512y_d_inl0_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512y_d_inl0_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512y_d_inl0_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.512y_d_inl0_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512y_d_inl0_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512y_d_inl0_hrd0/testmisc_cu.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.512y_d_inl0_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu runTest.cc -o build.512y_d_inl0_hrd0/runTest_cu.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -c read_slha.cc -o build.512y_d_inl0_hrd0/read_slha.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu runTest.cc -o build.512y_d_inl0_hrd0/runTest_cu.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -c Parameters_sm.cc -o build.512y_d_inl0_hrd0/Parameters_sm.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.512y_d_inl0_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512y_d_inl0_hrd0/fsampler_cu.o
+mkdir -p ../lib/build.512y_d_inl0_hrd0
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512y_d_inl0_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.512y_d_inl0_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.512y_d_inl0_hrd0/libmg5amc_common.so build.512y_d_inl0_hrd0/Parameters_sm.o build.512y_d_inl0_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512y_d_inl0_hrd0/libmg5amc_ll_ll_cuda.so build.512y_d_inl0_hrd0/gCPPProcess.o build.512y_d_inl0_hrd0/gMatrixElementKernels.o build.512y_d_inl0_hrd0/gBridgeKernels.o build.512y_d_inl0_hrd0/gCrossSectionKernels.o build.512y_d_inl0_hrd0/fbridge_cu.o -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512y_d_inl0_hrd0/libmg5amc_ll_ll_cpp.so build.512y_d_inl0_hrd0/CPPProcess.o build.512y_d_inl0_hrd0/MatrixElementKernels.o build.512y_d_inl0_hrd0/BridgeKernels.o build.512y_d_inl0_hrd0/CrossSectionKernels.o build.512y_d_inl0_hrd0/fbridge.o -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl0_hrd0/runTest.exe build.512y_d_inl0_hrd0/CPPProcess.o build.512y_d_inl0_hrd0/MatrixElementKernels.o build.512y_d_inl0_hrd0/BridgeKernels.o build.512y_d_inl0_hrd0/CrossSectionKernels.o build.512y_d_inl0_hrd0/RandomNumberKernels.o build.512y_d_inl0_hrd0/RamboSamplingKernels.o build.512y_d_inl0_hrd0/testxxx.o  build.512y_d_inl0_hrd0/testmisc.o  build.512y_d_inl0_hrd0/runTest.o build.512y_d_inl0_hrd0/gCPPProcess.o build.512y_d_inl0_hrd0/gMatrixElementKernels.o build.512y_d_inl0_hrd0/gBridgeKernels.o build.512y_d_inl0_hrd0/gCrossSectionKernels.o build.512y_d_inl0_hrd0/gRandomNumberKernels.o build.512y_d_inl0_hrd0/gRamboSamplingKernels.o build.512y_d_inl0_hrd0/testxxx_cu.o  build.512y_d_inl0_hrd0/testmisc_cu.o  build.512y_d_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_d_inl0_hrd0/check.exe build.512y_d_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_ll_ll_cpp build.512y_d_inl0_hrd0/RandomNumberKernels.o build.512y_d_inl0_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_d_inl0_hrd0/fcheck.exe build.512y_d_inl0_hrd0/fcheck_sa.o build.512y_d_inl0_hrd0/fsampler.o -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_ll_ll_cpp build.512y_d_inl0_hrd0/RandomNumberKernels.o build.512y_d_inl0_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl0_hrd0/gcheck.exe build.512y_d_inl0_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_ll_ll_cuda build.512y_d_inl0_hrd0/gRandomNumberKernels.o build.512y_d_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl0_hrd0/fgcheck.exe build.512y_d_inl0_hrd0/fcheck_sa.o build.512y_d_inl0_hrd0/fsampler_cu.o -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_ll_ll_cuda build.512y_d_inl0_hrd0/gRandomNumberKernels.o build.512y_d_inl0_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512y_d_inl0_hrd0/libmg5amc_ll_ll_cuda.so build.512y_d_inl0_hrd0/gCPPProcess.o build.512y_d_inl0_hrd0/gMatrixElementKernels.o build.512y_d_inl0_hrd0/gBridgeKernels.o build.512y_d_inl0_hrd0/gCrossSectionKernels.o build.512y_d_inl0_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512y_d_inl0_hrd0/libmg5amc_ll_ll_cpp.so build.512y_d_inl0_hrd0/CPPProcess.o build.512y_d_inl0_hrd0/MatrixElementKernels.o build.512y_d_inl0_hrd0/BridgeKernels.o build.512y_d_inl0_hrd0/CrossSectionKernels.o build.512y_d_inl0_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_d_inl0_hrd0/fcheck.exe build.512y_d_inl0_hrd0/fcheck_sa.o build.512y_d_inl0_hrd0/fsampler.o -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_d_inl0_hrd0'  -lgfortran -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_ll_ll_cpp build.512y_d_inl0_hrd0/RandomNumberKernels.o build.512y_d_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl0_hrd0/gcheck.exe build.512y_d_inl0_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl0_hrd0'  -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_ll_ll_cuda build.512y_d_inl0_hrd0/gRandomNumberKernels.o build.512y_d_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl0_hrd0/fgcheck.exe build.512y_d_inl0_hrd0/fcheck_sa.o build.512y_d_inl0_hrd0/fsampler_cu.o -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl0_hrd0'  -lgfortran -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_ll_ll_cuda build.512y_d_inl0_hrd0/gRandomNumberKernels.o build.512y_d_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_d_inl0_hrd0/check.exe build.512y_d_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_d_inl0_hrd0'  -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_ll_ll_cpp build.512y_d_inl0_hrd0/RandomNumberKernels.o build.512y_d_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl0_hrd0/runTest.exe build.512y_d_inl0_hrd0/CPPProcess.o build.512y_d_inl0_hrd0/MatrixElementKernels.o build.512y_d_inl0_hrd0/BridgeKernels.o build.512y_d_inl0_hrd0/CrossSectionKernels.o build.512y_d_inl0_hrd0/RandomNumberKernels.o build.512y_d_inl0_hrd0/RamboSamplingKernels.o build.512y_d_inl0_hrd0/testxxx.o  build.512y_d_inl0_hrd0/testmisc.o  build.512y_d_inl0_hrd0/runTest.o build.512y_d_inl0_hrd0/gCPPProcess.o build.512y_d_inl0_hrd0/gMatrixElementKernels.o build.512y_d_inl0_hrd0/gBridgeKernels.o build.512y_d_inl0_hrd0/gCrossSectionKernels.o build.512y_d_inl0_hrd0/gRandomNumberKernels.o build.512y_d_inl0_hrd0/gRamboSamplingKernels.o build.512y_d_inl0_hrd0/testxxx_cu.o  build.512y_d_inl0_hrd0/testmisc_cu.o  build.512y_d_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl0_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
 touch build.512y_d_inl0_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_d_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.512y_d_inl0_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_d_inl0_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_d_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512y_d_inl0_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_d_inl0_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.512y_d_inl0_hrd0/libmg5amc_ll_ll_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_d_inl0_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512y_d_inl0_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_d_inl0_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_20:56:10
+DATE: 2022-09-24_23:35:11
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_d_inl0_hrd0/gcheck.exe -p 2048 256 24 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_d_inl0_hrd0/gcheck.exe -p 2048 256 24 OMP=
 Process                     = SIGMA_SM_EPEM_MUPMUM_CUDA [nvcc 11.7.99 (gcc 11.2.0)] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
-EvtsPerSec[Rmb+ME]     (23) = ( 5.534655e+07                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 5.450773e+08                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 1.130432e+09                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 2.279185e+07                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 4.663382e+07                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 4.879672e+07                 )  sec^-1
 MeanMatrixElemValue         = ( 1.371952e-02 +- 2.312385e-06 )  GeV^0
-TOTAL       :     0.993012 sec
-real	0m1.303s
-==PROF== Profiling "sigmaKin": launch__registers_per_thread 142
-==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100%
+TOTAL       :     3.261580 sec
+real	0m3.742s
+   launch__registers_per_thread N/A
+   sm__sass_average_branch_targets_threads_uniform.pct N/A
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_d_inl0_hrd0/gcheck.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_d_inl0_hrd0/fgcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_d_inl0_hrd0/gcheck.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_d_inl0_hrd0/fgcheck.exe 2 64 2
 Avg ME (C++/CUDA)   = 1.282804e-02
 Avg ME (F77/CUDA)   = 1.2828039868165201E-002
 Relative difference = 1.0277080522138477e-08
@@ -308,12 +310,12 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 20:56:20 CEST 2022 Will execute './throughputX.sh -makej -eemumu -nocpp  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:35:40 CEST 2022 Will execute './throughputX.sh -makej -eemumu -nocpp  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
 CUDACPP_BUILDDIR='build.none_d_inl1_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -323,22 +325,18 @@ HELINL=1
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.none_d_inl1_hrd0 for tag=none_d_inl1_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.none_d_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.none_d_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.none_d_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.none_d_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.none_d_inl1_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.none_d_inl1_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.none_d_inl1_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.none_d_inl1_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.none_d_inl1_hrd0/gRandomNumberKernels.o
 AVX=none
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.none_d_inl1_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.none_d_inl1_hrd0/gMatrixElementKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.none_d_inl1_hrd0/gBridgeKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.none_d_inl1_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.none_d_inl1_hrd0/read_slha.o
-mkdir -p ../lib/build.none_d_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.none_d_inl1_hrd0/gCrossSectionKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.none_d_inl1_hrd0/fbridge_cu.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.none_d_inl1_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.none_d_inl1_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.none_d_inl1_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.none_d_inl1_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.none_d_inl1_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.none_d_inl1_hrd0/MatrixElementKernels.o
@@ -348,26 +346,31 @@ ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.none_d_inl1_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.none_d_inl1_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.none_d_inl1_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.none_d_inl1_hrd0/testxxx_cu.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.none_d_inl1_hrd0/Parameters_sm.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.none_d_inl1_hrd0/testxxx_cu.o
+mkdir -p ../lib/build.none_d_inl1_hrd0
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.none_d_inl1_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.none_d_inl1_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.none_d_inl1_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.none_d_inl1_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.none_d_inl1_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.none_d_inl1_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.none_d_inl1_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.none_d_inl1_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.none_d_inl1_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.none_d_inl1_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.none_d_inl1_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.none_d_inl1_hrd0/libmg5amc_common.so build.none_d_inl1_hrd0/Parameters_sm.o build.none_d_inl1_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.none_d_inl1_hrd0/libmg5amc_ll_ll_cpp.so build.none_d_inl1_hrd0/CPPProcess.o build.none_d_inl1_hrd0/MatrixElementKernels.o build.none_d_inl1_hrd0/BridgeKernels.o build.none_d_inl1_hrd0/CrossSectionKernels.o build.none_d_inl1_hrd0/fbridge.o -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_d_inl1_hrd0/check.exe build.none_d_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_ll_ll_cpp build.none_d_inl1_hrd0/RandomNumberKernels.o build.none_d_inl1_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_d_inl1_hrd0/fcheck.exe build.none_d_inl1_hrd0/fcheck_sa.o build.none_d_inl1_hrd0/fsampler.o -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_ll_ll_cpp build.none_d_inl1_hrd0/RandomNumberKernels.o build.none_d_inl1_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.none_d_inl1_hrd0/libmg5amc_ll_ll_cuda.so build.none_d_inl1_hrd0/gCPPProcess.o build.none_d_inl1_hrd0/gMatrixElementKernels.o build.none_d_inl1_hrd0/gBridgeKernels.o build.none_d_inl1_hrd0/gCrossSectionKernels.o build.none_d_inl1_hrd0/fbridge_cu.o -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl1_hrd0/fgcheck.exe build.none_d_inl1_hrd0/fcheck_sa.o build.none_d_inl1_hrd0/fsampler_cu.o -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_ll_ll_cuda build.none_d_inl1_hrd0/gRandomNumberKernels.o build.none_d_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl1_hrd0/gcheck.exe build.none_d_inl1_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_ll_ll_cuda build.none_d_inl1_hrd0/gRandomNumberKernels.o build.none_d_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl1_hrd0/runTest.exe build.none_d_inl1_hrd0/CPPProcess.o build.none_d_inl1_hrd0/MatrixElementKernels.o build.none_d_inl1_hrd0/BridgeKernels.o build.none_d_inl1_hrd0/CrossSectionKernels.o build.none_d_inl1_hrd0/RandomNumberKernels.o build.none_d_inl1_hrd0/RamboSamplingKernels.o build.none_d_inl1_hrd0/testxxx.o  build.none_d_inl1_hrd0/testmisc.o  build.none_d_inl1_hrd0/runTest.o build.none_d_inl1_hrd0/gCPPProcess.o build.none_d_inl1_hrd0/gMatrixElementKernels.o build.none_d_inl1_hrd0/gBridgeKernels.o build.none_d_inl1_hrd0/gCrossSectionKernels.o build.none_d_inl1_hrd0/gRandomNumberKernels.o build.none_d_inl1_hrd0/gRamboSamplingKernels.o build.none_d_inl1_hrd0/testxxx_cu.o  build.none_d_inl1_hrd0/testmisc_cu.o  build.none_d_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.none_d_inl1_hrd0/libmg5amc_ll_ll_cpp.so build.none_d_inl1_hrd0/CPPProcess.o build.none_d_inl1_hrd0/MatrixElementKernels.o build.none_d_inl1_hrd0/BridgeKernels.o build.none_d_inl1_hrd0/CrossSectionKernels.o build.none_d_inl1_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_d_inl1_hrd0/check.exe build.none_d_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_d_inl1_hrd0'  -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_ll_ll_cpp build.none_d_inl1_hrd0/RandomNumberKernels.o build.none_d_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_d_inl1_hrd0/fcheck.exe build.none_d_inl1_hrd0/fcheck_sa.o build.none_d_inl1_hrd0/fsampler.o -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_d_inl1_hrd0'  -lgfortran -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_ll_ll_cpp build.none_d_inl1_hrd0/RandomNumberKernels.o build.none_d_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.none_d_inl1_hrd0/libmg5amc_ll_ll_cuda.so build.none_d_inl1_hrd0/gCPPProcess.o build.none_d_inl1_hrd0/gMatrixElementKernels.o build.none_d_inl1_hrd0/gBridgeKernels.o build.none_d_inl1_hrd0/gCrossSectionKernels.o build.none_d_inl1_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl1_hrd0/fgcheck.exe build.none_d_inl1_hrd0/fcheck_sa.o build.none_d_inl1_hrd0/fsampler_cu.o -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl1_hrd0'  -lgfortran -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_ll_ll_cuda build.none_d_inl1_hrd0/gRandomNumberKernels.o build.none_d_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl1_hrd0/gcheck.exe build.none_d_inl1_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl1_hrd0'  -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_ll_ll_cuda build.none_d_inl1_hrd0/gRandomNumberKernels.o build.none_d_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl1_hrd0/runTest.exe build.none_d_inl1_hrd0/CPPProcess.o build.none_d_inl1_hrd0/MatrixElementKernels.o build.none_d_inl1_hrd0/BridgeKernels.o build.none_d_inl1_hrd0/CrossSectionKernels.o build.none_d_inl1_hrd0/RandomNumberKernels.o build.none_d_inl1_hrd0/RamboSamplingKernels.o build.none_d_inl1_hrd0/testxxx.o  build.none_d_inl1_hrd0/testmisc.o  build.none_d_inl1_hrd0/runTest.o build.none_d_inl1_hrd0/gCPPProcess.o build.none_d_inl1_hrd0/gMatrixElementKernels.o build.none_d_inl1_hrd0/gBridgeKernels.o build.none_d_inl1_hrd0/gCrossSectionKernels.o build.none_d_inl1_hrd0/gRandomNumberKernels.o build.none_d_inl1_hrd0/gRamboSamplingKernels.o build.none_d_inl1_hrd0/testxxx_cu.o  build.none_d_inl1_hrd0/testmisc_cu.o  build.none_d_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl1_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
 touch build.none_d_inl1_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_d_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.none_d_inl1_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.none_d_inl1_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_d_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.none_d_inl1_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.none_d_inl1_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.none_d_inl1_hrd0/libmg5amc_ll_ll_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_d_inl1_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.none_d_inl1_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.none_d_inl1_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
 CUDACPP_BUILDDIR='build.512y_d_inl1_hrd0'
 make -f cudacpp.mk
@@ -378,22 +381,18 @@ HELINL=1
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.512y_d_inl1_hrd0 for tag=512y_d_inl1_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.512y_d_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.512y_d_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.512y_d_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.512y_d_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512y_d_inl1_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512y_d_inl1_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512y_d_inl1_hrd0/gCrossSectionKernels.o
 AVX=512y
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.512y_d_inl1_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512y_d_inl1_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512y_d_inl1_hrd0/gBridgeKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512y_d_inl1_hrd0/gCrossSectionKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512y_d_inl1_hrd0/fbridge_cu.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.512y_d_inl1_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.512y_d_inl1_hrd0/read_slha.o
-mkdir -p ../lib/build.512y_d_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512y_d_inl1_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512y_d_inl1_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512y_d_inl1_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512y_d_inl1_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512y_d_inl1_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.512y_d_inl1_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.512y_d_inl1_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.512y_d_inl1_hrd0/MatrixElementKernels.o
@@ -403,46 +402,51 @@ ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.512y_d_inl1_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.512y_d_inl1_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.512y_d_inl1_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512y_d_inl1_hrd0/testxxx_cu.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512y_d_inl1_hrd0/testxxx_cu.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.512y_d_inl1_hrd0/read_slha.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.512y_d_inl1_hrd0/Parameters_sm.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.512y_d_inl1_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512y_d_inl1_hrd0/testmisc_cu.o
+mkdir -p ../lib/build.512y_d_inl1_hrd0
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512y_d_inl1_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.512y_d_inl1_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.512y_d_inl1_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.512y_d_inl1_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.512y_d_inl1_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512y_d_inl1_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512y_d_inl1_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.512y_d_inl1_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.512y_d_inl1_hrd0/libmg5amc_common.so build.512y_d_inl1_hrd0/Parameters_sm.o build.512y_d_inl1_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512y_d_inl1_hrd0/libmg5amc_ll_ll_cuda.so build.512y_d_inl1_hrd0/gCPPProcess.o build.512y_d_inl1_hrd0/gMatrixElementKernels.o build.512y_d_inl1_hrd0/gBridgeKernels.o build.512y_d_inl1_hrd0/gCrossSectionKernels.o build.512y_d_inl1_hrd0/fbridge_cu.o -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512y_d_inl1_hrd0/libmg5amc_ll_ll_cpp.so build.512y_d_inl1_hrd0/CPPProcess.o build.512y_d_inl1_hrd0/MatrixElementKernels.o build.512y_d_inl1_hrd0/BridgeKernels.o build.512y_d_inl1_hrd0/CrossSectionKernels.o build.512y_d_inl1_hrd0/fbridge.o -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl1_hrd0/runTest.exe build.512y_d_inl1_hrd0/CPPProcess.o build.512y_d_inl1_hrd0/MatrixElementKernels.o build.512y_d_inl1_hrd0/BridgeKernels.o build.512y_d_inl1_hrd0/CrossSectionKernels.o build.512y_d_inl1_hrd0/RandomNumberKernels.o build.512y_d_inl1_hrd0/RamboSamplingKernels.o build.512y_d_inl1_hrd0/testxxx.o  build.512y_d_inl1_hrd0/testmisc.o  build.512y_d_inl1_hrd0/runTest.o build.512y_d_inl1_hrd0/gCPPProcess.o build.512y_d_inl1_hrd0/gMatrixElementKernels.o build.512y_d_inl1_hrd0/gBridgeKernels.o build.512y_d_inl1_hrd0/gCrossSectionKernels.o build.512y_d_inl1_hrd0/gRandomNumberKernels.o build.512y_d_inl1_hrd0/gRamboSamplingKernels.o build.512y_d_inl1_hrd0/testxxx_cu.o  build.512y_d_inl1_hrd0/testmisc_cu.o  build.512y_d_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_d_inl1_hrd0/check.exe build.512y_d_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_ll_ll_cpp build.512y_d_inl1_hrd0/RandomNumberKernels.o build.512y_d_inl1_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_d_inl1_hrd0/fcheck.exe build.512y_d_inl1_hrd0/fcheck_sa.o build.512y_d_inl1_hrd0/fsampler.o -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_ll_ll_cpp build.512y_d_inl1_hrd0/RandomNumberKernels.o build.512y_d_inl1_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl1_hrd0/gcheck.exe build.512y_d_inl1_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_ll_ll_cuda build.512y_d_inl1_hrd0/gRandomNumberKernels.o build.512y_d_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl1_hrd0/fgcheck.exe build.512y_d_inl1_hrd0/fcheck_sa.o build.512y_d_inl1_hrd0/fsampler_cu.o -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_ll_ll_cuda build.512y_d_inl1_hrd0/gRandomNumberKernels.o build.512y_d_inl1_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512y_d_inl1_hrd0/libmg5amc_ll_ll_cuda.so build.512y_d_inl1_hrd0/gCPPProcess.o build.512y_d_inl1_hrd0/gMatrixElementKernels.o build.512y_d_inl1_hrd0/gBridgeKernels.o build.512y_d_inl1_hrd0/gCrossSectionKernels.o build.512y_d_inl1_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl1_hrd0/gcheck.exe build.512y_d_inl1_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl1_hrd0'  -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_ll_ll_cuda build.512y_d_inl1_hrd0/gRandomNumberKernels.o build.512y_d_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl1_hrd0/fgcheck.exe build.512y_d_inl1_hrd0/fcheck_sa.o build.512y_d_inl1_hrd0/fsampler_cu.o -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl1_hrd0'  -lgfortran -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_ll_ll_cuda build.512y_d_inl1_hrd0/gRandomNumberKernels.o build.512y_d_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512y_d_inl1_hrd0/libmg5amc_ll_ll_cpp.so build.512y_d_inl1_hrd0/CPPProcess.o build.512y_d_inl1_hrd0/MatrixElementKernels.o build.512y_d_inl1_hrd0/BridgeKernels.o build.512y_d_inl1_hrd0/CrossSectionKernels.o build.512y_d_inl1_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_d_inl1_hrd0/fcheck.exe build.512y_d_inl1_hrd0/fcheck_sa.o build.512y_d_inl1_hrd0/fsampler.o -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_d_inl1_hrd0'  -lgfortran -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_ll_ll_cpp build.512y_d_inl1_hrd0/RandomNumberKernels.o build.512y_d_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_d_inl1_hrd0/check.exe build.512y_d_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_d_inl1_hrd0'  -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_ll_ll_cpp build.512y_d_inl1_hrd0/RandomNumberKernels.o build.512y_d_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl1_hrd0/runTest.exe build.512y_d_inl1_hrd0/CPPProcess.o build.512y_d_inl1_hrd0/MatrixElementKernels.o build.512y_d_inl1_hrd0/BridgeKernels.o build.512y_d_inl1_hrd0/CrossSectionKernels.o build.512y_d_inl1_hrd0/RandomNumberKernels.o build.512y_d_inl1_hrd0/RamboSamplingKernels.o build.512y_d_inl1_hrd0/testxxx.o  build.512y_d_inl1_hrd0/testmisc.o  build.512y_d_inl1_hrd0/runTest.o build.512y_d_inl1_hrd0/gCPPProcess.o build.512y_d_inl1_hrd0/gMatrixElementKernels.o build.512y_d_inl1_hrd0/gBridgeKernels.o build.512y_d_inl1_hrd0/gCrossSectionKernels.o build.512y_d_inl1_hrd0/gRandomNumberKernels.o build.512y_d_inl1_hrd0/gRamboSamplingKernels.o build.512y_d_inl1_hrd0/testxxx_cu.o  build.512y_d_inl1_hrd0/testmisc_cu.o  build.512y_d_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl1_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
 touch build.512y_d_inl1_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_d_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.512y_d_inl1_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_d_inl1_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_d_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512y_d_inl1_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_d_inl1_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.512y_d_inl1_hrd0/libmg5amc_ll_ll_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_d_inl1_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512y_d_inl1_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_d_inl1_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_20:56:32
+DATE: 2022-09-24_23:36:04
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_d_inl1_hrd0/gcheck.exe -p 2048 256 24 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_d_inl1_hrd0/gcheck.exe -p 2048 256 24 OMP=
 Process                     = SIGMA_SM_EPEM_MUPMUM_CUDA [nvcc 11.7.99 (gcc 11.2.0)] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
-EvtsPerSec[Rmb+ME]     (23) = ( 5.531022e+07                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 5.438382e+08                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 1.128067e+09                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 2.325050e+07                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 4.773567e+07                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 4.958971e+07                 )  sec^-1
 MeanMatrixElemValue         = ( 1.371952e-02 +- 2.312385e-06 )  GeV^0
-TOTAL       :     0.986029 sec
-real	0m1.294s
-==PROF== Profiling "sigmaKin": launch__registers_per_thread 142
-==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100%
+TOTAL       :     3.222285 sec
+real	0m3.688s
+   launch__registers_per_thread N/A
+   sm__sass_average_branch_targets_threads_uniform.pct N/A
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_d_inl1_hrd0/gcheck.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_d_inl1_hrd0/fgcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_d_inl1_hrd0/gcheck.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_d_inl1_hrd0/fgcheck.exe 2 64 2
 Avg ME (C++/CUDA)   = 1.282804e-02
 Avg ME (F77/CUDA)   = 1.2828039868165201E-002
 Relative difference = 1.0277080522138477e-08
@@ -450,12 +454,12 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 20:56:39 CEST 2022 Will execute './throughputX.sh -makej -eemumu -nocpp -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:36:31 CEST 2022 Will execute './throughputX.sh -makej -eemumu -nocpp -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
 CUDACPP_BUILDDIR='build.none_f_inl0_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -465,51 +469,52 @@ HELINL=0
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.none_f_inl0_hrd0 for tag=none_f_inl0_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.none_f_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gcheck_sa.cu -o build.none_f_inl0_hrd0/gcheck_sa.o
-AVX=none
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gCPPProcess.cu -o build.none_f_inl0_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.none_f_inl0_hrd0/gMatrixElementKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gBridgeKernels.cu -o build.none_f_inl0_hrd0/gBridgeKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -c read_slha.cc -o build.none_f_inl0_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.none_f_inl0_hrd0/gCrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -c Parameters_sm.cc -o build.none_f_inl0_hrd0/Parameters_sm.o
-mkdir -p ../lib/build.none_f_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fbridge.cc -o build.none_f_inl0_hrd0/fbridge_cu.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.none_f_inl0_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.none_f_inl0_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gcheck_sa.cu -o build.none_f_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gCPPProcess.cu -o build.none_f_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.none_f_inl0_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gBridgeKernels.cu -o build.none_f_inl0_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.none_f_inl0_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fbridge.cc -o build.none_f_inl0_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.none_f_inl0_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.none_f_inl0_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.none_f_inl0_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.none_f_inl0_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.none_f_inl0_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.none_f_inl0_hrd0/BridgeKernels.o
+AVX=none
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.none_f_inl0_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.none_f_inl0_hrd0/fbridge.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.none_f_inl0_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.none_f_inl0_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.none_f_inl0_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testxxx.cc -o build.none_f_inl0_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testxxx.cc -o build.none_f_inl0_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.none_f_inl0_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testmisc.cc -o build.none_f_inl0_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testmisc.cc -o build.none_f_inl0_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.none_f_inl0_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu runTest.cc -o build.none_f_inl0_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu runTest.cc -o build.none_f_inl0_hrd0/runTest_cu.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.none_f_inl0_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fsampler.cc -o build.none_f_inl0_hrd0/fsampler_cu.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -c Parameters_sm.cc -o build.none_f_inl0_hrd0/Parameters_sm.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fsampler.cc -o build.none_f_inl0_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.none_f_inl0_hrd0/fsampler.o
+mkdir -p ../lib/build.none_f_inl0_hrd0
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -c read_slha.cc -o build.none_f_inl0_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.none_f_inl0_hrd0/libmg5amc_common.so build.none_f_inl0_hrd0/Parameters_sm.o build.none_f_inl0_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.none_f_inl0_hrd0/libmg5amc_ll_ll_cpp.so build.none_f_inl0_hrd0/CPPProcess.o build.none_f_inl0_hrd0/MatrixElementKernels.o build.none_f_inl0_hrd0/BridgeKernels.o build.none_f_inl0_hrd0/CrossSectionKernels.o build.none_f_inl0_hrd0/fbridge.o -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_f_inl0_hrd0/check.exe build.none_f_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_ll_ll_cpp build.none_f_inl0_hrd0/RandomNumberKernels.o build.none_f_inl0_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_f_inl0_hrd0/fcheck.exe build.none_f_inl0_hrd0/fcheck_sa.o build.none_f_inl0_hrd0/fsampler.o -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_ll_ll_cpp build.none_f_inl0_hrd0/RandomNumberKernels.o build.none_f_inl0_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.none_f_inl0_hrd0/libmg5amc_ll_ll_cuda.so build.none_f_inl0_hrd0/gCPPProcess.o build.none_f_inl0_hrd0/gMatrixElementKernels.o build.none_f_inl0_hrd0/gBridgeKernels.o build.none_f_inl0_hrd0/gCrossSectionKernels.o build.none_f_inl0_hrd0/fbridge_cu.o -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl0_hrd0/fgcheck.exe build.none_f_inl0_hrd0/fcheck_sa.o build.none_f_inl0_hrd0/fsampler_cu.o -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_ll_ll_cuda build.none_f_inl0_hrd0/gRandomNumberKernels.o build.none_f_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl0_hrd0/gcheck.exe build.none_f_inl0_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_ll_ll_cuda build.none_f_inl0_hrd0/gRandomNumberKernels.o build.none_f_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl0_hrd0/runTest.exe build.none_f_inl0_hrd0/CPPProcess.o build.none_f_inl0_hrd0/MatrixElementKernels.o build.none_f_inl0_hrd0/BridgeKernels.o build.none_f_inl0_hrd0/CrossSectionKernels.o build.none_f_inl0_hrd0/RandomNumberKernels.o build.none_f_inl0_hrd0/RamboSamplingKernels.o build.none_f_inl0_hrd0/testxxx.o  build.none_f_inl0_hrd0/testmisc.o  build.none_f_inl0_hrd0/runTest.o build.none_f_inl0_hrd0/gCPPProcess.o build.none_f_inl0_hrd0/gMatrixElementKernels.o build.none_f_inl0_hrd0/gBridgeKernels.o build.none_f_inl0_hrd0/gCrossSectionKernels.o build.none_f_inl0_hrd0/gRandomNumberKernels.o build.none_f_inl0_hrd0/gRamboSamplingKernels.o build.none_f_inl0_hrd0/testxxx_cu.o  build.none_f_inl0_hrd0/testmisc_cu.o  build.none_f_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.none_f_inl0_hrd0/libmg5amc_ll_ll_cpp.so build.none_f_inl0_hrd0/CPPProcess.o build.none_f_inl0_hrd0/MatrixElementKernels.o build.none_f_inl0_hrd0/BridgeKernels.o build.none_f_inl0_hrd0/CrossSectionKernels.o build.none_f_inl0_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_f_inl0_hrd0/check.exe build.none_f_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_f_inl0_hrd0'  -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_ll_ll_cpp build.none_f_inl0_hrd0/RandomNumberKernels.o build.none_f_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_f_inl0_hrd0/fcheck.exe build.none_f_inl0_hrd0/fcheck_sa.o build.none_f_inl0_hrd0/fsampler.o -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_f_inl0_hrd0'  -lgfortran -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_ll_ll_cpp build.none_f_inl0_hrd0/RandomNumberKernels.o build.none_f_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.none_f_inl0_hrd0/libmg5amc_ll_ll_cuda.so build.none_f_inl0_hrd0/gCPPProcess.o build.none_f_inl0_hrd0/gMatrixElementKernels.o build.none_f_inl0_hrd0/gBridgeKernels.o build.none_f_inl0_hrd0/gCrossSectionKernels.o build.none_f_inl0_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl0_hrd0/fgcheck.exe build.none_f_inl0_hrd0/fcheck_sa.o build.none_f_inl0_hrd0/fsampler_cu.o -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl0_hrd0'  -lgfortran -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_ll_ll_cuda build.none_f_inl0_hrd0/gRandomNumberKernels.o build.none_f_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl0_hrd0/gcheck.exe build.none_f_inl0_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl0_hrd0'  -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_ll_ll_cuda build.none_f_inl0_hrd0/gRandomNumberKernels.o build.none_f_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl0_hrd0/runTest.exe build.none_f_inl0_hrd0/CPPProcess.o build.none_f_inl0_hrd0/MatrixElementKernels.o build.none_f_inl0_hrd0/BridgeKernels.o build.none_f_inl0_hrd0/CrossSectionKernels.o build.none_f_inl0_hrd0/RandomNumberKernels.o build.none_f_inl0_hrd0/RamboSamplingKernels.o build.none_f_inl0_hrd0/testxxx.o  build.none_f_inl0_hrd0/testmisc.o  build.none_f_inl0_hrd0/runTest.o build.none_f_inl0_hrd0/gCPPProcess.o build.none_f_inl0_hrd0/gMatrixElementKernels.o build.none_f_inl0_hrd0/gBridgeKernels.o build.none_f_inl0_hrd0/gCrossSectionKernels.o build.none_f_inl0_hrd0/gRandomNumberKernels.o build.none_f_inl0_hrd0/gRamboSamplingKernels.o build.none_f_inl0_hrd0/testxxx_cu.o  build.none_f_inl0_hrd0/testmisc_cu.o  build.none_f_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl0_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
 touch build.none_f_inl0_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_f_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.none_f_inl0_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.none_f_inl0_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_f_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.none_f_inl0_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.none_f_inl0_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.none_f_inl0_hrd0/libmg5amc_ll_ll_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_f_inl0_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.none_f_inl0_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.none_f_inl0_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
 CUDACPP_BUILDDIR='build.512y_f_inl0_hrd0'
 make -f cudacpp.mk
@@ -520,71 +525,72 @@ HELINL=0
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.512y_f_inl0_hrd0 for tag=512y_f_inl0_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.512y_f_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gcheck_sa.cu -o build.512y_f_inl0_hrd0/gcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gCPPProcess.cu -o build.512y_f_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gcheck_sa.cu -o build.512y_f_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gCPPProcess.cu -o build.512y_f_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512y_f_inl0_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512y_f_inl0_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512y_f_inl0_hrd0/gCrossSectionKernels.o
 AVX=512y
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512y_f_inl0_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512y_f_inl0_hrd0/gBridgeKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512y_f_inl0_hrd0/gCrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -c Parameters_sm.cc -o build.512y_f_inl0_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -c read_slha.cc -o build.512y_f_inl0_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512y_f_inl0_hrd0/fbridge_cu.o
-mkdir -p ../lib/build.512y_f_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512y_f_inl0_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512y_f_inl0_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512y_f_inl0_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512y_f_inl0_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512y_f_inl0_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.512y_f_inl0_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.512y_f_inl0_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.512y_f_inl0_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.512y_f_inl0_hrd0/BridgeKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.512y_f_inl0_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.512y_f_inl0_hrd0/fbridge.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.512y_f_inl0_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.512y_f_inl0_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.512y_f_inl0_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512y_f_inl0_hrd0/testxxx_cu.o
+mkdir -p ../lib/build.512y_f_inl0_hrd0
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -c read_slha.cc -o build.512y_f_inl0_hrd0/read_slha.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -c Parameters_sm.cc -o build.512y_f_inl0_hrd0/Parameters_sm.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512y_f_inl0_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.512y_f_inl0_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512y_f_inl0_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512y_f_inl0_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.512y_f_inl0_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu runTest.cc -o build.512y_f_inl0_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu runTest.cc -o build.512y_f_inl0_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.512y_f_inl0_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512y_f_inl0_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512y_f_inl0_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.512y_f_inl0_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.512y_f_inl0_hrd0/libmg5amc_common.so build.512y_f_inl0_hrd0/Parameters_sm.o build.512y_f_inl0_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512y_f_inl0_hrd0/libmg5amc_ll_ll_cuda.so build.512y_f_inl0_hrd0/gCPPProcess.o build.512y_f_inl0_hrd0/gMatrixElementKernels.o build.512y_f_inl0_hrd0/gBridgeKernels.o build.512y_f_inl0_hrd0/gCrossSectionKernels.o build.512y_f_inl0_hrd0/fbridge_cu.o -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl0_hrd0/runTest.exe build.512y_f_inl0_hrd0/CPPProcess.o build.512y_f_inl0_hrd0/MatrixElementKernels.o build.512y_f_inl0_hrd0/BridgeKernels.o build.512y_f_inl0_hrd0/CrossSectionKernels.o build.512y_f_inl0_hrd0/RandomNumberKernels.o build.512y_f_inl0_hrd0/RamboSamplingKernels.o build.512y_f_inl0_hrd0/testxxx.o  build.512y_f_inl0_hrd0/testmisc.o  build.512y_f_inl0_hrd0/runTest.o build.512y_f_inl0_hrd0/gCPPProcess.o build.512y_f_inl0_hrd0/gMatrixElementKernels.o build.512y_f_inl0_hrd0/gBridgeKernels.o build.512y_f_inl0_hrd0/gCrossSectionKernels.o build.512y_f_inl0_hrd0/gRandomNumberKernels.o build.512y_f_inl0_hrd0/gRamboSamplingKernels.o build.512y_f_inl0_hrd0/testxxx_cu.o  build.512y_f_inl0_hrd0/testmisc_cu.o  build.512y_f_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512y_f_inl0_hrd0/libmg5amc_ll_ll_cpp.so build.512y_f_inl0_hrd0/CPPProcess.o build.512y_f_inl0_hrd0/MatrixElementKernels.o build.512y_f_inl0_hrd0/BridgeKernels.o build.512y_f_inl0_hrd0/CrossSectionKernels.o build.512y_f_inl0_hrd0/fbridge.o -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_f_inl0_hrd0/check.exe build.512y_f_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_ll_ll_cpp build.512y_f_inl0_hrd0/RandomNumberKernels.o build.512y_f_inl0_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_f_inl0_hrd0/fcheck.exe build.512y_f_inl0_hrd0/fcheck_sa.o build.512y_f_inl0_hrd0/fsampler.o -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_ll_ll_cpp build.512y_f_inl0_hrd0/RandomNumberKernels.o build.512y_f_inl0_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl0_hrd0/gcheck.exe build.512y_f_inl0_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_ll_ll_cuda build.512y_f_inl0_hrd0/gRandomNumberKernels.o build.512y_f_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl0_hrd0/fgcheck.exe build.512y_f_inl0_hrd0/fcheck_sa.o build.512y_f_inl0_hrd0/fsampler_cu.o -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_ll_ll_cuda build.512y_f_inl0_hrd0/gRandomNumberKernels.o build.512y_f_inl0_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512y_f_inl0_hrd0/libmg5amc_ll_ll_cuda.so build.512y_f_inl0_hrd0/gCPPProcess.o build.512y_f_inl0_hrd0/gMatrixElementKernels.o build.512y_f_inl0_hrd0/gBridgeKernels.o build.512y_f_inl0_hrd0/gCrossSectionKernels.o build.512y_f_inl0_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512y_f_inl0_hrd0/libmg5amc_ll_ll_cpp.so build.512y_f_inl0_hrd0/CPPProcess.o build.512y_f_inl0_hrd0/MatrixElementKernels.o build.512y_f_inl0_hrd0/BridgeKernels.o build.512y_f_inl0_hrd0/CrossSectionKernels.o build.512y_f_inl0_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_f_inl0_hrd0/fcheck.exe build.512y_f_inl0_hrd0/fcheck_sa.o build.512y_f_inl0_hrd0/fsampler.o -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_f_inl0_hrd0'  -lgfortran -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_ll_ll_cpp build.512y_f_inl0_hrd0/RandomNumberKernels.o build.512y_f_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl0_hrd0/gcheck.exe build.512y_f_inl0_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl0_hrd0'  -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_ll_ll_cuda build.512y_f_inl0_hrd0/gRandomNumberKernels.o build.512y_f_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl0_hrd0/fgcheck.exe build.512y_f_inl0_hrd0/fcheck_sa.o build.512y_f_inl0_hrd0/fsampler_cu.o -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl0_hrd0'  -lgfortran -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_ll_ll_cuda build.512y_f_inl0_hrd0/gRandomNumberKernels.o build.512y_f_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_f_inl0_hrd0/check.exe build.512y_f_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_f_inl0_hrd0'  -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_ll_ll_cpp build.512y_f_inl0_hrd0/RandomNumberKernels.o build.512y_f_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl0_hrd0/runTest.exe build.512y_f_inl0_hrd0/CPPProcess.o build.512y_f_inl0_hrd0/MatrixElementKernels.o build.512y_f_inl0_hrd0/BridgeKernels.o build.512y_f_inl0_hrd0/CrossSectionKernels.o build.512y_f_inl0_hrd0/RandomNumberKernels.o build.512y_f_inl0_hrd0/RamboSamplingKernels.o build.512y_f_inl0_hrd0/testxxx.o  build.512y_f_inl0_hrd0/testmisc.o  build.512y_f_inl0_hrd0/runTest.o build.512y_f_inl0_hrd0/gCPPProcess.o build.512y_f_inl0_hrd0/gMatrixElementKernels.o build.512y_f_inl0_hrd0/gBridgeKernels.o build.512y_f_inl0_hrd0/gCrossSectionKernels.o build.512y_f_inl0_hrd0/gRandomNumberKernels.o build.512y_f_inl0_hrd0/gRamboSamplingKernels.o build.512y_f_inl0_hrd0/testxxx_cu.o  build.512y_f_inl0_hrd0/testmisc_cu.o  build.512y_f_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl0_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
 touch build.512y_f_inl0_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_f_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.512y_f_inl0_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_f_inl0_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_f_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512y_f_inl0_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_f_inl0_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.512y_f_inl0_hrd0/libmg5amc_ll_ll_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_f_inl0_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512y_f_inl0_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_f_inl0_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_20:57:00
+DATE: 2022-09-24_23:37:12
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_f_inl0_hrd0/gcheck.exe -p 2048 256 24 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_f_inl0_hrd0/gcheck.exe -p 2048 256 24 OMP=
 Process                     = SIGMA_SM_EPEM_MUPMUM_CUDA [nvcc 11.7.99 (gcc 11.2.0)] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK
 FP precision                = FLOAT (NaN/abnormal=4, zero=0)
-EvtsPerSec[Rmb+ME]     (23) = ( 1.103659e+08                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 1.232297e+09                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 3.036306e+09                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 6.904961e+07                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 8.651419e+08                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 1.485295e+09                 )  sec^-1
 MeanMatrixElemValue         = ( 1.371934e-02 +- 2.312374e-06 )  GeV^0
-TOTAL       :     0.779104 sec
-real	0m1.071s
-==PROF== Profiling "sigmaKin": launch__registers_per_thread 72
-==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100%
+TOTAL       :     2.726060 sec
+real	0m3.182s
+   launch__registers_per_thread N/A
+   sm__sass_average_branch_targets_threads_uniform.pct N/A
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_f_inl0_hrd0/gcheck.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_f_inl0_hrd0/fgcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_f_inl0_hrd0/gcheck.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_f_inl0_hrd0/fgcheck.exe 2 64 2
 Avg ME (C++/CUDA)   = 1.282802e-02
 Avg ME (F77/CUDA)   = 1.2828112568968209E-002
 Relative difference = 7.216154029052431e-06
@@ -592,12 +598,12 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 20:57:06 CEST 2022 Will execute './throughputX.sh -makej -eemumu -nocpp -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:37:39 CEST 2022 Will execute './throughputX.sh -makej -eemumu -nocpp -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
 CUDACPP_BUILDDIR='build.none_f_inl1_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -607,22 +613,18 @@ HELINL=1
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.none_f_inl1_hrd0 for tag=none_f_inl1_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.none_f_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.none_f_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.none_f_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.none_f_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.none_f_inl1_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.none_f_inl1_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.none_f_inl1_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.none_f_inl1_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.none_f_inl1_hrd0/gRandomNumberKernels.o
 AVX=none
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.none_f_inl1_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.none_f_inl1_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.none_f_inl1_hrd0/gBridgeKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.none_f_inl1_hrd0/gCrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.none_f_inl1_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.none_f_inl1_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.none_f_inl1_hrd0/fbridge_cu.o
-mkdir -p ../lib/build.none_f_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.none_f_inl1_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.none_f_inl1_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.none_f_inl1_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.none_f_inl1_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.none_f_inl1_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.none_f_inl1_hrd0/MatrixElementKernels.o
@@ -631,27 +633,32 @@ ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.none_f_inl1_hrd0/fbridge.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.none_f_inl1_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.none_f_inl1_hrd0/RamboSamplingKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.none_f_inl1_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.none_f_inl1_hrd0/testxxx_cu.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.none_f_inl1_hrd0/Parameters_sm.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.none_f_inl1_hrd0/read_slha.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.none_f_inl1_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.none_f_inl1_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.none_f_inl1_hrd0/testmisc_cu.o
+mkdir -p ../lib/build.none_f_inl1_hrd0
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.none_f_inl1_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.none_f_inl1_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.none_f_inl1_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.none_f_inl1_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.none_f_inl1_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.none_f_inl1_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.none_f_inl1_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.none_f_inl1_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.none_f_inl1_hrd0/libmg5amc_common.so build.none_f_inl1_hrd0/Parameters_sm.o build.none_f_inl1_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.none_f_inl1_hrd0/libmg5amc_ll_ll_cpp.so build.none_f_inl1_hrd0/CPPProcess.o build.none_f_inl1_hrd0/MatrixElementKernels.o build.none_f_inl1_hrd0/BridgeKernels.o build.none_f_inl1_hrd0/CrossSectionKernels.o build.none_f_inl1_hrd0/fbridge.o -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_f_inl1_hrd0/check.exe build.none_f_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_ll_ll_cpp build.none_f_inl1_hrd0/RandomNumberKernels.o build.none_f_inl1_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_f_inl1_hrd0/fcheck.exe build.none_f_inl1_hrd0/fcheck_sa.o build.none_f_inl1_hrd0/fsampler.o -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_ll_ll_cpp build.none_f_inl1_hrd0/RandomNumberKernels.o build.none_f_inl1_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.none_f_inl1_hrd0/libmg5amc_ll_ll_cuda.so build.none_f_inl1_hrd0/gCPPProcess.o build.none_f_inl1_hrd0/gMatrixElementKernels.o build.none_f_inl1_hrd0/gBridgeKernels.o build.none_f_inl1_hrd0/gCrossSectionKernels.o build.none_f_inl1_hrd0/fbridge_cu.o -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl1_hrd0/fgcheck.exe build.none_f_inl1_hrd0/fcheck_sa.o build.none_f_inl1_hrd0/fsampler_cu.o -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_ll_ll_cuda build.none_f_inl1_hrd0/gRandomNumberKernels.o build.none_f_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl1_hrd0/gcheck.exe build.none_f_inl1_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_ll_ll_cuda build.none_f_inl1_hrd0/gRandomNumberKernels.o build.none_f_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl1_hrd0/runTest.exe build.none_f_inl1_hrd0/CPPProcess.o build.none_f_inl1_hrd0/MatrixElementKernels.o build.none_f_inl1_hrd0/BridgeKernels.o build.none_f_inl1_hrd0/CrossSectionKernels.o build.none_f_inl1_hrd0/RandomNumberKernels.o build.none_f_inl1_hrd0/RamboSamplingKernels.o build.none_f_inl1_hrd0/testxxx.o  build.none_f_inl1_hrd0/testmisc.o  build.none_f_inl1_hrd0/runTest.o build.none_f_inl1_hrd0/gCPPProcess.o build.none_f_inl1_hrd0/gMatrixElementKernels.o build.none_f_inl1_hrd0/gBridgeKernels.o build.none_f_inl1_hrd0/gCrossSectionKernels.o build.none_f_inl1_hrd0/gRandomNumberKernels.o build.none_f_inl1_hrd0/gRamboSamplingKernels.o build.none_f_inl1_hrd0/testxxx_cu.o  build.none_f_inl1_hrd0/testmisc_cu.o  build.none_f_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.none_f_inl1_hrd0/libmg5amc_ll_ll_cpp.so build.none_f_inl1_hrd0/CPPProcess.o build.none_f_inl1_hrd0/MatrixElementKernels.o build.none_f_inl1_hrd0/BridgeKernels.o build.none_f_inl1_hrd0/CrossSectionKernels.o build.none_f_inl1_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_f_inl1_hrd0/check.exe build.none_f_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_f_inl1_hrd0'  -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_ll_ll_cpp build.none_f_inl1_hrd0/RandomNumberKernels.o build.none_f_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_f_inl1_hrd0/fcheck.exe build.none_f_inl1_hrd0/fcheck_sa.o build.none_f_inl1_hrd0/fsampler.o -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_f_inl1_hrd0'  -lgfortran -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_ll_ll_cpp build.none_f_inl1_hrd0/RandomNumberKernels.o build.none_f_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.none_f_inl1_hrd0/libmg5amc_ll_ll_cuda.so build.none_f_inl1_hrd0/gCPPProcess.o build.none_f_inl1_hrd0/gMatrixElementKernels.o build.none_f_inl1_hrd0/gBridgeKernels.o build.none_f_inl1_hrd0/gCrossSectionKernels.o build.none_f_inl1_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl1_hrd0/fgcheck.exe build.none_f_inl1_hrd0/fcheck_sa.o build.none_f_inl1_hrd0/fsampler_cu.o -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl1_hrd0'  -lgfortran -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_ll_ll_cuda build.none_f_inl1_hrd0/gRandomNumberKernels.o build.none_f_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl1_hrd0/gcheck.exe build.none_f_inl1_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl1_hrd0'  -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_ll_ll_cuda build.none_f_inl1_hrd0/gRandomNumberKernels.o build.none_f_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl1_hrd0/runTest.exe build.none_f_inl1_hrd0/CPPProcess.o build.none_f_inl1_hrd0/MatrixElementKernels.o build.none_f_inl1_hrd0/BridgeKernels.o build.none_f_inl1_hrd0/CrossSectionKernels.o build.none_f_inl1_hrd0/RandomNumberKernels.o build.none_f_inl1_hrd0/RamboSamplingKernels.o build.none_f_inl1_hrd0/testxxx.o  build.none_f_inl1_hrd0/testmisc.o  build.none_f_inl1_hrd0/runTest.o build.none_f_inl1_hrd0/gCPPProcess.o build.none_f_inl1_hrd0/gMatrixElementKernels.o build.none_f_inl1_hrd0/gBridgeKernels.o build.none_f_inl1_hrd0/gCrossSectionKernels.o build.none_f_inl1_hrd0/gRandomNumberKernels.o build.none_f_inl1_hrd0/gRamboSamplingKernels.o build.none_f_inl1_hrd0/testxxx_cu.o  build.none_f_inl1_hrd0/testmisc_cu.o  build.none_f_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl1_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
 touch build.none_f_inl1_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_f_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.none_f_inl1_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.none_f_inl1_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_f_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.none_f_inl1_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.none_f_inl1_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.none_f_inl1_hrd0/libmg5amc_ll_ll_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_f_inl1_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.none_f_inl1_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.none_f_inl1_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
 CUDACPP_BUILDDIR='build.512y_f_inl1_hrd0'
 make -f cudacpp.mk
@@ -662,71 +669,72 @@ HELINL=1
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.512y_f_inl1_hrd0 for tag=512y_f_inl1_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.512y_f_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.512y_f_inl1_hrd0/gcheck_sa.o
-AVX=512y
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.512y_f_inl1_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512y_f_inl1_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512y_f_inl1_hrd0/gBridgeKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512y_f_inl1_hrd0/gCrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.512y_f_inl1_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.512y_f_inl1_hrd0/read_slha.o
-mkdir -p ../lib/build.512y_f_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512y_f_inl1_hrd0/fbridge_cu.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512y_f_inl1_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512y_f_inl1_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.512y_f_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.512y_f_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512y_f_inl1_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512y_f_inl1_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512y_f_inl1_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512y_f_inl1_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512y_f_inl1_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512y_f_inl1_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.512y_f_inl1_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.512y_f_inl1_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.512y_f_inl1_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.512y_f_inl1_hrd0/BridgeKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.512y_f_inl1_hrd0/CrossSectionKernels.o
+AVX=512y
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.512y_f_inl1_hrd0/fbridge.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.512y_f_inl1_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.512y_f_inl1_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.512y_f_inl1_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512y_f_inl1_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512y_f_inl1_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.512y_f_inl1_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512y_f_inl1_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512y_f_inl1_hrd0/testmisc_cu.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.512y_f_inl1_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.512y_f_inl1_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.512y_f_inl1_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.512y_f_inl1_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512y_f_inl1_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512y_f_inl1_hrd0/fsampler_cu.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.512y_f_inl1_hrd0/Parameters_sm.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.512y_f_inl1_hrd0/fsampler.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.512y_f_inl1_hrd0/read_slha.o
+mkdir -p ../lib/build.512y_f_inl1_hrd0
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.512y_f_inl1_hrd0/libmg5amc_common.so build.512y_f_inl1_hrd0/Parameters_sm.o build.512y_f_inl1_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512y_f_inl1_hrd0/libmg5amc_ll_ll_cuda.so build.512y_f_inl1_hrd0/gCPPProcess.o build.512y_f_inl1_hrd0/gMatrixElementKernels.o build.512y_f_inl1_hrd0/gBridgeKernels.o build.512y_f_inl1_hrd0/gCrossSectionKernels.o build.512y_f_inl1_hrd0/fbridge_cu.o -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512y_f_inl1_hrd0/libmg5amc_ll_ll_cpp.so build.512y_f_inl1_hrd0/CPPProcess.o build.512y_f_inl1_hrd0/MatrixElementKernels.o build.512y_f_inl1_hrd0/BridgeKernels.o build.512y_f_inl1_hrd0/CrossSectionKernels.o build.512y_f_inl1_hrd0/fbridge.o -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl1_hrd0/runTest.exe build.512y_f_inl1_hrd0/CPPProcess.o build.512y_f_inl1_hrd0/MatrixElementKernels.o build.512y_f_inl1_hrd0/BridgeKernels.o build.512y_f_inl1_hrd0/CrossSectionKernels.o build.512y_f_inl1_hrd0/RandomNumberKernels.o build.512y_f_inl1_hrd0/RamboSamplingKernels.o build.512y_f_inl1_hrd0/testxxx.o  build.512y_f_inl1_hrd0/testmisc.o  build.512y_f_inl1_hrd0/runTest.o build.512y_f_inl1_hrd0/gCPPProcess.o build.512y_f_inl1_hrd0/gMatrixElementKernels.o build.512y_f_inl1_hrd0/gBridgeKernels.o build.512y_f_inl1_hrd0/gCrossSectionKernels.o build.512y_f_inl1_hrd0/gRandomNumberKernels.o build.512y_f_inl1_hrd0/gRamboSamplingKernels.o build.512y_f_inl1_hrd0/testxxx_cu.o  build.512y_f_inl1_hrd0/testmisc_cu.o  build.512y_f_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_f_inl1_hrd0/check.exe build.512y_f_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_ll_ll_cpp build.512y_f_inl1_hrd0/RandomNumberKernels.o build.512y_f_inl1_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_f_inl1_hrd0/fcheck.exe build.512y_f_inl1_hrd0/fcheck_sa.o build.512y_f_inl1_hrd0/fsampler.o -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_ll_ll_cpp build.512y_f_inl1_hrd0/RandomNumberKernels.o build.512y_f_inl1_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl1_hrd0/gcheck.exe build.512y_f_inl1_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_ll_ll_cuda build.512y_f_inl1_hrd0/gRandomNumberKernels.o build.512y_f_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl1_hrd0/fgcheck.exe build.512y_f_inl1_hrd0/fcheck_sa.o build.512y_f_inl1_hrd0/fsampler_cu.o -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_ll_ll_cuda build.512y_f_inl1_hrd0/gRandomNumberKernels.o build.512y_f_inl1_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512y_f_inl1_hrd0/libmg5amc_ll_ll_cuda.so build.512y_f_inl1_hrd0/gCPPProcess.o build.512y_f_inl1_hrd0/gMatrixElementKernels.o build.512y_f_inl1_hrd0/gBridgeKernels.o build.512y_f_inl1_hrd0/gCrossSectionKernels.o build.512y_f_inl1_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl1_hrd0/gcheck.exe build.512y_f_inl1_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl1_hrd0'  -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_ll_ll_cuda build.512y_f_inl1_hrd0/gRandomNumberKernels.o build.512y_f_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl1_hrd0/fgcheck.exe build.512y_f_inl1_hrd0/fcheck_sa.o build.512y_f_inl1_hrd0/fsampler_cu.o -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl1_hrd0'  -lgfortran -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_ll_ll_cuda build.512y_f_inl1_hrd0/gRandomNumberKernels.o build.512y_f_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512y_f_inl1_hrd0/libmg5amc_ll_ll_cpp.so build.512y_f_inl1_hrd0/CPPProcess.o build.512y_f_inl1_hrd0/MatrixElementKernels.o build.512y_f_inl1_hrd0/BridgeKernels.o build.512y_f_inl1_hrd0/CrossSectionKernels.o build.512y_f_inl1_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_f_inl1_hrd0/fcheck.exe build.512y_f_inl1_hrd0/fcheck_sa.o build.512y_f_inl1_hrd0/fsampler.o -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_f_inl1_hrd0'  -lgfortran -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_ll_ll_cpp build.512y_f_inl1_hrd0/RandomNumberKernels.o build.512y_f_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_f_inl1_hrd0/check.exe build.512y_f_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_f_inl1_hrd0'  -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_ll_ll_cpp build.512y_f_inl1_hrd0/RandomNumberKernels.o build.512y_f_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl1_hrd0/runTest.exe build.512y_f_inl1_hrd0/CPPProcess.o build.512y_f_inl1_hrd0/MatrixElementKernels.o build.512y_f_inl1_hrd0/BridgeKernels.o build.512y_f_inl1_hrd0/CrossSectionKernels.o build.512y_f_inl1_hrd0/RandomNumberKernels.o build.512y_f_inl1_hrd0/RamboSamplingKernels.o build.512y_f_inl1_hrd0/testxxx.o  build.512y_f_inl1_hrd0/testmisc.o  build.512y_f_inl1_hrd0/runTest.o build.512y_f_inl1_hrd0/gCPPProcess.o build.512y_f_inl1_hrd0/gMatrixElementKernels.o build.512y_f_inl1_hrd0/gBridgeKernels.o build.512y_f_inl1_hrd0/gCrossSectionKernels.o build.512y_f_inl1_hrd0/gRandomNumberKernels.o build.512y_f_inl1_hrd0/gRamboSamplingKernels.o build.512y_f_inl1_hrd0/testxxx_cu.o  build.512y_f_inl1_hrd0/testmisc_cu.o  build.512y_f_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl1_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
 touch build.512y_f_inl1_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_f_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.512y_f_inl1_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_f_inl1_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_f_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512y_f_inl1_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_f_inl1_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.512y_f_inl1_hrd0/libmg5amc_ll_ll_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_f_inl1_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512y_f_inl1_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_f_inl1_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_20:57:18
+DATE: 2022-09-24_23:38:02
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_f_inl1_hrd0/gcheck.exe -p 2048 256 24 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_f_inl1_hrd0/gcheck.exe -p 2048 256 24 OMP=
 Process                     = SIGMA_SM_EPEM_MUPMUM_CUDA [nvcc 11.7.99 (gcc 11.2.0)] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK
 FP precision                = FLOAT (NaN/abnormal=4, zero=0)
-EvtsPerSec[Rmb+ME]     (23) = ( 1.104396e+08                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 1.230567e+09                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 3.029100e+09                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 6.844988e+07                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 9.048805e+08                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 1.420555e+09                 )  sec^-1
 MeanMatrixElemValue         = ( 1.371934e-02 +- 2.312374e-06 )  GeV^0
-TOTAL       :     0.777647 sec
-real	0m1.071s
-==PROF== Profiling "sigmaKin": launch__registers_per_thread 72
-==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100%
+TOTAL       :     2.690892 sec
+real	0m3.132s
+   launch__registers_per_thread N/A
+   sm__sass_average_branch_targets_threads_uniform.pct N/A
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_f_inl1_hrd0/gcheck.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_f_inl1_hrd0/fgcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_f_inl1_hrd0/gcheck.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_f_inl1_hrd0/fgcheck.exe 2 64 2
 Avg ME (C++/CUDA)   = 1.282802e-02
 Avg ME (F77/CUDA)   = 1.2828112568968209E-002
 Relative difference = 7.216154029052431e-06
@@ -734,35 +742,35 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 20:57:25 CEST 2022 Will execute './throughputX.sh -makej -eemumu -noneonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:38:30 CEST 2022 Will execute './throughputX.sh -makej -eemumu -noneonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -noneonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
 CUDACPP_BUILDDIR='build.none_d_inl0_hrd0'
 make: Nothing to be done for `all'.
 
-DATE: 2022-08-31_20:57:25
+DATE: 2022-09-24_23:38:30
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_d_inl0_hrd0/check.exe -p 2048 256 24 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_d_inl0_hrd0/check.exe -p 2048 256 24 OMP=
 Process                     = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.2.0] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CPP:DBL+CXS:CURHST+RMBHST+MESHST/none+NAVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = SCALAR ('none': ~vector[1], no SIMD)
-EvtsPerSec[Rmb+ME]     (23) = ( 1.067090e+06                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 1.602924e+06                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 1.602924e+06                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 1.071665e+06                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 1.603460e+06                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 1.603460e+06                 )  sec^-1
 MeanMatrixElemValue         = ( 1.371952e-02 +- 2.312385e-06 )  GeV^0
-TOTAL       :    12.725230 sec
-real	0m12.745s
+TOTAL       :    12.669991 sec
+real	0m12.689s
 =Symbols in CPPProcess.o= (~sse4:  370) (avx2:    0) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_d_inl0_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_d_inl0_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_d_inl0_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_d_inl0_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 1.282804e-02
 Avg ME (F77/C++)    = 1.2828039868164916E-002
 Relative difference = 1.0277102699700292e-08
@@ -770,35 +778,35 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 20:57:40 CEST 2022 Will execute './throughputX.sh -makej -eemumu -noneonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:38:58 CEST 2022 Will execute './throughputX.sh -makej -eemumu -noneonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -noneonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
 CUDACPP_BUILDDIR='build.none_d_inl1_hrd0'
 make: Nothing to be done for `all'.
 
-DATE: 2022-08-31_20:57:40
+DATE: 2022-09-24_23:38:58
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_d_inl1_hrd0/check.exe -p 2048 256 24 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_d_inl1_hrd0/check.exe -p 2048 256 24 OMP=
 Process                     = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.2.0] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CPP:DBL+CXS:CURHST+RMBHST+MESHST/none+NAVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = SCALAR ('none': ~vector[1], no SIMD)
-EvtsPerSec[Rmb+ME]     (23) = ( 1.882121e+06                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 4.650216e+06                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 4.650216e+06                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 1.908702e+06                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 4.669919e+06                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 4.669919e+06                 )  sec^-1
 MeanMatrixElemValue         = ( 1.371952e-02 +- 2.312385e-06 )  GeV^0
-TOTAL       :     7.616728 sec
-real	0m7.637s
+TOTAL       :     7.519922 sec
+real	0m7.538s
 =Symbols in CPPProcess.o= (~sse4:  109) (avx2:    0) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_d_inl1_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_d_inl1_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_d_inl1_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_d_inl1_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 1.282804e-02
 Avg ME (F77/C++)    = 1.2828039868164916E-002
 Relative difference = 1.0277102699700292e-08
@@ -806,35 +814,35 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 20:57:49 CEST 2022 Will execute './throughputX.sh -makej -eemumu -noneonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:39:20 CEST 2022 Will execute './throughputX.sh -makej -eemumu -noneonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -noneonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
 CUDACPP_BUILDDIR='build.none_f_inl0_hrd0'
 make: Nothing to be done for `all'.
 
-DATE: 2022-08-31_20:57:49
+DATE: 2022-09-24_23:39:21
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_f_inl0_hrd0/check.exe -p 2048 256 24 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_f_inl0_hrd0/check.exe -p 2048 256 24 OMP=
 Process                     = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.2.0] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CPP:FLT+CXS:CURHST+RMBHST+MESHST/none+NAVBRK
 FP precision                = FLOAT (NaN/abnormal=12, zero=0)
 Internal loops fptype_sv    = SCALAR ('none': ~vector[1], no SIMD)
-EvtsPerSec[Rmb+ME]     (23) = ( 1.176368e+06                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 1.655938e+06                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 1.655938e+06                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 1.181742e+06                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 1.662875e+06                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 1.662875e+06                 )  sec^-1
 MeanMatrixElemValue         = ( 1.371957e-02 +- 2.312985e-06 )  GeV^0
-TOTAL       :    11.527417 sec
-real	0m11.541s
+TOTAL       :    11.474534 sec
+real	0m11.487s
 =Symbols in CPPProcess.o= (~sse4:  363) (avx2:    0) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_f_inl0_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_f_inl0_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_f_inl0_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_f_inl0_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 1.282804e-02
 Avg ME (F77/C++)    = 1.2828040373278782E-002
 Relative difference = 2.909866052404734e-08
@@ -842,35 +850,35 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 20:58:03 CEST 2022 Will execute './throughputX.sh -makej -eemumu -noneonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:39:47 CEST 2022 Will execute './throughputX.sh -makej -eemumu -noneonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -noneonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
 CUDACPP_BUILDDIR='build.none_f_inl1_hrd0'
 make: Nothing to be done for `all'.
 
-DATE: 2022-08-31_20:58:03
+DATE: 2022-09-24_23:39:47
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_f_inl1_hrd0/check.exe -p 2048 256 24 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_f_inl1_hrd0/check.exe -p 2048 256 24 OMP=
 Process                     = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.2.0] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CPP:FLT+CXS:CURHST+RMBHST+MESHST/none+NAVBRK
 FP precision                = FLOAT (NaN/abnormal=12, zero=0)
 Internal loops fptype_sv    = SCALAR ('none': ~vector[1], no SIMD)
-EvtsPerSec[Rmb+ME]     (23) = ( 2.228182e+06                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 4.936409e+06                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 4.936409e+06                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 2.238637e+06                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 4.952863e+06                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 4.952863e+06                 )  sec^-1
 MeanMatrixElemValue         = ( 1.371957e-02 +- 2.312985e-06 )  GeV^0
-TOTAL       :     6.476570 sec
-real	0m6.489s
+TOTAL       :     6.448900 sec
+real	0m6.462s
 =Symbols in CPPProcess.o= (~sse4:  125) (avx2:    0) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_f_inl1_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_f_inl1_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_f_inl1_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.none_f_inl1_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 1.282804e-02
 Avg ME (F77/C++)    = 1.2828040393287665E-002
 Relative difference = 3.0658437655940004e-08
@@ -878,13 +886,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 20:58:11 CEST 2022 Will execute './throughputX.sh -makej -eemumu -sse4only  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:40:09 CEST 2022 Will execute './throughputX.sh -makej -eemumu -sse4only  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -sse4only implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
 CUDACPP_BUILDDIR='build.sse4_d_inl0_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -894,22 +902,18 @@ HELINL=0
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.sse4_d_inl0_hrd0 for tag=sse4_d_inl0_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.sse4_d_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gcheck_sa.cu -o build.sse4_d_inl0_hrd0/gcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gCPPProcess.cu -o build.sse4_d_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gcheck_sa.cu -o build.sse4_d_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gCPPProcess.cu -o build.sse4_d_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.sse4_d_inl0_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gBridgeKernels.cu -o build.sse4_d_inl0_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.sse4_d_inl0_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fbridge.cc -o build.sse4_d_inl0_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.sse4_d_inl0_hrd0/gRandomNumberKernels.o
 AVX=sse4
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.sse4_d_inl0_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gBridgeKernels.cu -o build.sse4_d_inl0_hrd0/gBridgeKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.sse4_d_inl0_hrd0/gCrossSectionKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fbridge.cc -o build.sse4_d_inl0_hrd0/fbridge_cu.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -c Parameters_sm.cc -o build.sse4_d_inl0_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -c read_slha.cc -o build.sse4_d_inl0_hrd0/read_slha.o
-mkdir -p ../lib/build.sse4_d_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.sse4_d_inl0_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.sse4_d_inl0_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.sse4_d_inl0_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.sse4_d_inl0_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.sse4_d_inl0_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.sse4_d_inl0_hrd0/MatrixElementKernels.o
@@ -919,46 +923,51 @@ ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.sse4_d_inl0_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.sse4_d_inl0_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.sse4_d_inl0_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testxxx.cc -o build.sse4_d_inl0_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testxxx.cc -o build.sse4_d_inl0_hrd0/testxxx_cu.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -c Parameters_sm.cc -o build.sse4_d_inl0_hrd0/Parameters_sm.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -c read_slha.cc -o build.sse4_d_inl0_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.sse4_d_inl0_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testmisc.cc -o build.sse4_d_inl0_hrd0/testmisc_cu.o
+mkdir -p ../lib/build.sse4_d_inl0_hrd0
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testmisc.cc -o build.sse4_d_inl0_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.sse4_d_inl0_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu runTest.cc -o build.sse4_d_inl0_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu runTest.cc -o build.sse4_d_inl0_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.sse4_d_inl0_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fsampler.cc -o build.sse4_d_inl0_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fsampler.cc -o build.sse4_d_inl0_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.sse4_d_inl0_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.sse4_d_inl0_hrd0/libmg5amc_common.so build.sse4_d_inl0_hrd0/Parameters_sm.o build.sse4_d_inl0_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.sse4_d_inl0_hrd0/libmg5amc_ll_ll_cuda.so build.sse4_d_inl0_hrd0/gCPPProcess.o build.sse4_d_inl0_hrd0/gMatrixElementKernels.o build.sse4_d_inl0_hrd0/gBridgeKernels.o build.sse4_d_inl0_hrd0/gCrossSectionKernels.o build.sse4_d_inl0_hrd0/fbridge_cu.o -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.sse4_d_inl0_hrd0/libmg5amc_ll_ll_cpp.so build.sse4_d_inl0_hrd0/CPPProcess.o build.sse4_d_inl0_hrd0/MatrixElementKernels.o build.sse4_d_inl0_hrd0/BridgeKernels.o build.sse4_d_inl0_hrd0/CrossSectionKernels.o build.sse4_d_inl0_hrd0/fbridge.o -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl0_hrd0/runTest.exe build.sse4_d_inl0_hrd0/CPPProcess.o build.sse4_d_inl0_hrd0/MatrixElementKernels.o build.sse4_d_inl0_hrd0/BridgeKernels.o build.sse4_d_inl0_hrd0/CrossSectionKernels.o build.sse4_d_inl0_hrd0/RandomNumberKernels.o build.sse4_d_inl0_hrd0/RamboSamplingKernels.o build.sse4_d_inl0_hrd0/testxxx.o  build.sse4_d_inl0_hrd0/testmisc.o  build.sse4_d_inl0_hrd0/runTest.o build.sse4_d_inl0_hrd0/gCPPProcess.o build.sse4_d_inl0_hrd0/gMatrixElementKernels.o build.sse4_d_inl0_hrd0/gBridgeKernels.o build.sse4_d_inl0_hrd0/gCrossSectionKernels.o build.sse4_d_inl0_hrd0/gRandomNumberKernels.o build.sse4_d_inl0_hrd0/gRamboSamplingKernels.o build.sse4_d_inl0_hrd0/testxxx_cu.o  build.sse4_d_inl0_hrd0/testmisc_cu.o  build.sse4_d_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_d_inl0_hrd0/check.exe build.sse4_d_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_ll_ll_cpp build.sse4_d_inl0_hrd0/RandomNumberKernels.o build.sse4_d_inl0_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_d_inl0_hrd0/fcheck.exe build.sse4_d_inl0_hrd0/fcheck_sa.o build.sse4_d_inl0_hrd0/fsampler.o -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_ll_ll_cpp build.sse4_d_inl0_hrd0/RandomNumberKernels.o build.sse4_d_inl0_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl0_hrd0/gcheck.exe build.sse4_d_inl0_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_ll_ll_cuda build.sse4_d_inl0_hrd0/gRandomNumberKernels.o build.sse4_d_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl0_hrd0/fgcheck.exe build.sse4_d_inl0_hrd0/fcheck_sa.o build.sse4_d_inl0_hrd0/fsampler_cu.o -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_ll_ll_cuda build.sse4_d_inl0_hrd0/gRandomNumberKernels.o build.sse4_d_inl0_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.sse4_d_inl0_hrd0/libmg5amc_ll_ll_cuda.so build.sse4_d_inl0_hrd0/gCPPProcess.o build.sse4_d_inl0_hrd0/gMatrixElementKernels.o build.sse4_d_inl0_hrd0/gBridgeKernels.o build.sse4_d_inl0_hrd0/gCrossSectionKernels.o build.sse4_d_inl0_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.sse4_d_inl0_hrd0/libmg5amc_ll_ll_cpp.so build.sse4_d_inl0_hrd0/CPPProcess.o build.sse4_d_inl0_hrd0/MatrixElementKernels.o build.sse4_d_inl0_hrd0/BridgeKernels.o build.sse4_d_inl0_hrd0/CrossSectionKernels.o build.sse4_d_inl0_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_d_inl0_hrd0/fcheck.exe build.sse4_d_inl0_hrd0/fcheck_sa.o build.sse4_d_inl0_hrd0/fsampler.o -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_d_inl0_hrd0'  -lgfortran -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_ll_ll_cpp build.sse4_d_inl0_hrd0/RandomNumberKernels.o build.sse4_d_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl0_hrd0/gcheck.exe build.sse4_d_inl0_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl0_hrd0'  -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_ll_ll_cuda build.sse4_d_inl0_hrd0/gRandomNumberKernels.o build.sse4_d_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl0_hrd0/fgcheck.exe build.sse4_d_inl0_hrd0/fcheck_sa.o build.sse4_d_inl0_hrd0/fsampler_cu.o -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl0_hrd0'  -lgfortran -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_ll_ll_cuda build.sse4_d_inl0_hrd0/gRandomNumberKernels.o build.sse4_d_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl0_hrd0/runTest.exe build.sse4_d_inl0_hrd0/CPPProcess.o build.sse4_d_inl0_hrd0/MatrixElementKernels.o build.sse4_d_inl0_hrd0/BridgeKernels.o build.sse4_d_inl0_hrd0/CrossSectionKernels.o build.sse4_d_inl0_hrd0/RandomNumberKernels.o build.sse4_d_inl0_hrd0/RamboSamplingKernels.o build.sse4_d_inl0_hrd0/testxxx.o  build.sse4_d_inl0_hrd0/testmisc.o  build.sse4_d_inl0_hrd0/runTest.o build.sse4_d_inl0_hrd0/gCPPProcess.o build.sse4_d_inl0_hrd0/gMatrixElementKernels.o build.sse4_d_inl0_hrd0/gBridgeKernels.o build.sse4_d_inl0_hrd0/gCrossSectionKernels.o build.sse4_d_inl0_hrd0/gRandomNumberKernels.o build.sse4_d_inl0_hrd0/gRamboSamplingKernels.o build.sse4_d_inl0_hrd0/testxxx_cu.o  build.sse4_d_inl0_hrd0/testmisc_cu.o  build.sse4_d_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl0_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_d_inl0_hrd0/check.exe build.sse4_d_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_d_inl0_hrd0'  -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_ll_ll_cpp build.sse4_d_inl0_hrd0/RandomNumberKernels.o build.sse4_d_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
 touch build.sse4_d_inl0_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_d_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.sse4_d_inl0_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_d_inl0_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_d_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.sse4_d_inl0_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_d_inl0_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.sse4_d_inl0_hrd0/libmg5amc_ll_ll_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_d_inl0_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.sse4_d_inl0_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_d_inl0_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_20:58:13
+DATE: 2022-09-24_23:40:18
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.sse4_d_inl0_hrd0/check.exe -p 2048 256 24 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.sse4_d_inl0_hrd0/check.exe -p 2048 256 24 OMP=
 Process                     = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.2.0] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CPP:DBL+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 1.533206e+06                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 3.062250e+06                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 3.062250e+06                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 1.548485e+06                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 3.070359e+06                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 3.070359e+06                 )  sec^-1
 MeanMatrixElemValue         = ( 1.371952e-02 +- 2.312385e-06 )  GeV^0
-TOTAL       :     9.125490 sec
-real	0m9.145s
+TOTAL       :     9.041410 sec
+real	0m9.060s
 =Symbols in CPPProcess.o= (~sse4: 1350) (avx2:    0) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.sse4_d_inl0_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.sse4_d_inl0_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.sse4_d_inl0_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.sse4_d_inl0_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 1.282804e-02
 Avg ME (F77/C++)    = 1.2828039868164916E-002
 Relative difference = 1.0277102699700292e-08
@@ -966,13 +975,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 20:58:24 CEST 2022 Will execute './throughputX.sh -makej -eemumu -sse4only  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:40:42 CEST 2022 Will execute './throughputX.sh -makej -eemumu -sse4only  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -sse4only implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
 CUDACPP_BUILDDIR='build.sse4_d_inl1_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -982,22 +991,18 @@ HELINL=1
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.sse4_d_inl1_hrd0 for tag=sse4_d_inl1_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.sse4_d_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.sse4_d_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.sse4_d_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.sse4_d_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.sse4_d_inl1_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.sse4_d_inl1_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.sse4_d_inl1_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.sse4_d_inl1_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.sse4_d_inl1_hrd0/gRandomNumberKernels.o
 AVX=sse4
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.sse4_d_inl1_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.sse4_d_inl1_hrd0/gMatrixElementKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.sse4_d_inl1_hrd0/gBridgeKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.sse4_d_inl1_hrd0/gCrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.sse4_d_inl1_hrd0/read_slha.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.sse4_d_inl1_hrd0/Parameters_sm.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.sse4_d_inl1_hrd0/fbridge_cu.o
-mkdir -p ../lib/build.sse4_d_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.sse4_d_inl1_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.sse4_d_inl1_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.sse4_d_inl1_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.sse4_d_inl1_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.sse4_d_inl1_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.sse4_d_inl1_hrd0/MatrixElementKernels.o
@@ -1007,46 +1012,51 @@ ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.sse4_d_inl1_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.sse4_d_inl1_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.sse4_d_inl1_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.sse4_d_inl1_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.sse4_d_inl1_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.sse4_d_inl1_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.sse4_d_inl1_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.sse4_d_inl1_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.sse4_d_inl1_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.sse4_d_inl1_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.sse4_d_inl1_hrd0/runTest_cu.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.sse4_d_inl1_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.sse4_d_inl1_hrd0/fsampler_cu.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.sse4_d_inl1_hrd0/read_slha.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.sse4_d_inl1_hrd0/fsampler_cu.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.sse4_d_inl1_hrd0/Parameters_sm.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.sse4_d_inl1_hrd0/fsampler.o
+mkdir -p ../lib/build.sse4_d_inl1_hrd0
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.sse4_d_inl1_hrd0/libmg5amc_common.so build.sse4_d_inl1_hrd0/Parameters_sm.o build.sse4_d_inl1_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.sse4_d_inl1_hrd0/libmg5amc_ll_ll_cuda.so build.sse4_d_inl1_hrd0/gCPPProcess.o build.sse4_d_inl1_hrd0/gMatrixElementKernels.o build.sse4_d_inl1_hrd0/gBridgeKernels.o build.sse4_d_inl1_hrd0/gCrossSectionKernels.o build.sse4_d_inl1_hrd0/fbridge_cu.o -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.sse4_d_inl1_hrd0/libmg5amc_ll_ll_cpp.so build.sse4_d_inl1_hrd0/CPPProcess.o build.sse4_d_inl1_hrd0/MatrixElementKernels.o build.sse4_d_inl1_hrd0/BridgeKernels.o build.sse4_d_inl1_hrd0/CrossSectionKernels.o build.sse4_d_inl1_hrd0/fbridge.o -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl1_hrd0/runTest.exe build.sse4_d_inl1_hrd0/CPPProcess.o build.sse4_d_inl1_hrd0/MatrixElementKernels.o build.sse4_d_inl1_hrd0/BridgeKernels.o build.sse4_d_inl1_hrd0/CrossSectionKernels.o build.sse4_d_inl1_hrd0/RandomNumberKernels.o build.sse4_d_inl1_hrd0/RamboSamplingKernels.o build.sse4_d_inl1_hrd0/testxxx.o  build.sse4_d_inl1_hrd0/testmisc.o  build.sse4_d_inl1_hrd0/runTest.o build.sse4_d_inl1_hrd0/gCPPProcess.o build.sse4_d_inl1_hrd0/gMatrixElementKernels.o build.sse4_d_inl1_hrd0/gBridgeKernels.o build.sse4_d_inl1_hrd0/gCrossSectionKernels.o build.sse4_d_inl1_hrd0/gRandomNumberKernels.o build.sse4_d_inl1_hrd0/gRamboSamplingKernels.o build.sse4_d_inl1_hrd0/testxxx_cu.o  build.sse4_d_inl1_hrd0/testmisc_cu.o  build.sse4_d_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_d_inl1_hrd0/check.exe build.sse4_d_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_ll_ll_cpp build.sse4_d_inl1_hrd0/RandomNumberKernels.o build.sse4_d_inl1_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_d_inl1_hrd0/fcheck.exe build.sse4_d_inl1_hrd0/fcheck_sa.o build.sse4_d_inl1_hrd0/fsampler.o -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_ll_ll_cpp build.sse4_d_inl1_hrd0/RandomNumberKernels.o build.sse4_d_inl1_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl1_hrd0/gcheck.exe build.sse4_d_inl1_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_ll_ll_cuda build.sse4_d_inl1_hrd0/gRandomNumberKernels.o build.sse4_d_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl1_hrd0/fgcheck.exe build.sse4_d_inl1_hrd0/fcheck_sa.o build.sse4_d_inl1_hrd0/fsampler_cu.o -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_ll_ll_cuda build.sse4_d_inl1_hrd0/gRandomNumberKernels.o build.sse4_d_inl1_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.sse4_d_inl1_hrd0/libmg5amc_ll_ll_cuda.so build.sse4_d_inl1_hrd0/gCPPProcess.o build.sse4_d_inl1_hrd0/gMatrixElementKernels.o build.sse4_d_inl1_hrd0/gBridgeKernels.o build.sse4_d_inl1_hrd0/gCrossSectionKernels.o build.sse4_d_inl1_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl1_hrd0/gcheck.exe build.sse4_d_inl1_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl1_hrd0'  -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_ll_ll_cuda build.sse4_d_inl1_hrd0/gRandomNumberKernels.o build.sse4_d_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl1_hrd0/fgcheck.exe build.sse4_d_inl1_hrd0/fcheck_sa.o build.sse4_d_inl1_hrd0/fsampler_cu.o -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl1_hrd0'  -lgfortran -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_ll_ll_cuda build.sse4_d_inl1_hrd0/gRandomNumberKernels.o build.sse4_d_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.sse4_d_inl1_hrd0/libmg5amc_ll_ll_cpp.so build.sse4_d_inl1_hrd0/CPPProcess.o build.sse4_d_inl1_hrd0/MatrixElementKernels.o build.sse4_d_inl1_hrd0/BridgeKernels.o build.sse4_d_inl1_hrd0/CrossSectionKernels.o build.sse4_d_inl1_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_d_inl1_hrd0/fcheck.exe build.sse4_d_inl1_hrd0/fcheck_sa.o build.sse4_d_inl1_hrd0/fsampler.o -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_d_inl1_hrd0'  -lgfortran -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_ll_ll_cpp build.sse4_d_inl1_hrd0/RandomNumberKernels.o build.sse4_d_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_d_inl1_hrd0/check.exe build.sse4_d_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_d_inl1_hrd0'  -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_ll_ll_cpp build.sse4_d_inl1_hrd0/RandomNumberKernels.o build.sse4_d_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl1_hrd0/runTest.exe build.sse4_d_inl1_hrd0/CPPProcess.o build.sse4_d_inl1_hrd0/MatrixElementKernels.o build.sse4_d_inl1_hrd0/BridgeKernels.o build.sse4_d_inl1_hrd0/CrossSectionKernels.o build.sse4_d_inl1_hrd0/RandomNumberKernels.o build.sse4_d_inl1_hrd0/RamboSamplingKernels.o build.sse4_d_inl1_hrd0/testxxx.o  build.sse4_d_inl1_hrd0/testmisc.o  build.sse4_d_inl1_hrd0/runTest.o build.sse4_d_inl1_hrd0/gCPPProcess.o build.sse4_d_inl1_hrd0/gMatrixElementKernels.o build.sse4_d_inl1_hrd0/gBridgeKernels.o build.sse4_d_inl1_hrd0/gCrossSectionKernels.o build.sse4_d_inl1_hrd0/gRandomNumberKernels.o build.sse4_d_inl1_hrd0/gRamboSamplingKernels.o build.sse4_d_inl1_hrd0/testxxx_cu.o  build.sse4_d_inl1_hrd0/testmisc_cu.o  build.sse4_d_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl1_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
 touch build.sse4_d_inl1_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_d_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.sse4_d_inl1_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_d_inl1_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_d_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.sse4_d_inl1_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_d_inl1_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.sse4_d_inl1_hrd0/libmg5amc_ll_ll_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_d_inl1_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.sse4_d_inl1_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_d_inl1_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_20:58:25
+DATE: 2022-09-24_23:40:49
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.sse4_d_inl1_hrd0/check.exe -p 2048 256 24 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.sse4_d_inl1_hrd0/check.exe -p 2048 256 24 OMP=
 Process                     = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.2.0] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CPP:DBL+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 2.222375e+06                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 7.925393e+06                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 7.925393e+06                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 2.257616e+06                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 8.243490e+06                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 8.243490e+06                 )  sec^-1
 MeanMatrixElemValue         = ( 1.371952e-02 +- 2.312385e-06 )  GeV^0
-TOTAL       :     6.579843 sec
-real	0m6.599s
+TOTAL       :     6.487877 sec
+real	0m6.506s
 =Symbols in CPPProcess.o= (~sse4:  459) (avx2:    0) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.sse4_d_inl1_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.sse4_d_inl1_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.sse4_d_inl1_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.sse4_d_inl1_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 1.282804e-02
 Avg ME (F77/C++)    = 1.2828039868164914E-002
 Relative difference = 1.0277102834929327e-08
@@ -1054,13 +1064,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 20:58:34 CEST 2022 Will execute './throughputX.sh -makej -eemumu -sse4only -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:41:11 CEST 2022 Will execute './throughputX.sh -makej -eemumu -sse4only -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -sse4only implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
 CUDACPP_BUILDDIR='build.sse4_f_inl0_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -1070,71 +1080,72 @@ HELINL=0
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.sse4_f_inl0_hrd0 for tag=sse4_f_inl0_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.sse4_f_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gcheck_sa.cu -o build.sse4_f_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gcheck_sa.cu -o build.sse4_f_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gCPPProcess.cu -o build.sse4_f_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.sse4_f_inl0_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gBridgeKernels.cu -o build.sse4_f_inl0_hrd0/gBridgeKernels.o
 AVX=sse4
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gCPPProcess.cu -o build.sse4_f_inl0_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.sse4_f_inl0_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gBridgeKernels.cu -o build.sse4_f_inl0_hrd0/gBridgeKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -c Parameters_sm.cc -o build.sse4_f_inl0_hrd0/Parameters_sm.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.sse4_f_inl0_hrd0/gCrossSectionKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fbridge.cc -o build.sse4_f_inl0_hrd0/fbridge_cu.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -c read_slha.cc -o build.sse4_f_inl0_hrd0/read_slha.o
-mkdir -p ../lib/build.sse4_f_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.sse4_f_inl0_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.sse4_f_inl0_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.sse4_f_inl0_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fbridge.cc -o build.sse4_f_inl0_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.sse4_f_inl0_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.sse4_f_inl0_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.sse4_f_inl0_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.sse4_f_inl0_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.sse4_f_inl0_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.sse4_f_inl0_hrd0/BridgeKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.sse4_f_inl0_hrd0/CrossSectionKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.sse4_f_inl0_hrd0/fbridge.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.sse4_f_inl0_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.sse4_f_inl0_hrd0/RamboSamplingKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -c Parameters_sm.cc -o build.sse4_f_inl0_hrd0/Parameters_sm.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.sse4_f_inl0_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testxxx.cc -o build.sse4_f_inl0_hrd0/testxxx_cu.o
+mkdir -p ../lib/build.sse4_f_inl0_hrd0
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -c read_slha.cc -o build.sse4_f_inl0_hrd0/read_slha.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testxxx.cc -o build.sse4_f_inl0_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.sse4_f_inl0_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testmisc.cc -o build.sse4_f_inl0_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testmisc.cc -o build.sse4_f_inl0_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.sse4_f_inl0_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu runTest.cc -o build.sse4_f_inl0_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu runTest.cc -o build.sse4_f_inl0_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.sse4_f_inl0_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fsampler.cc -o build.sse4_f_inl0_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fsampler.cc -o build.sse4_f_inl0_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.sse4_f_inl0_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.sse4_f_inl0_hrd0/libmg5amc_common.so build.sse4_f_inl0_hrd0/Parameters_sm.o build.sse4_f_inl0_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.sse4_f_inl0_hrd0/libmg5amc_ll_ll_cuda.so build.sse4_f_inl0_hrd0/gCPPProcess.o build.sse4_f_inl0_hrd0/gMatrixElementKernels.o build.sse4_f_inl0_hrd0/gBridgeKernels.o build.sse4_f_inl0_hrd0/gCrossSectionKernels.o build.sse4_f_inl0_hrd0/fbridge_cu.o -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.sse4_f_inl0_hrd0/libmg5amc_ll_ll_cpp.so build.sse4_f_inl0_hrd0/CPPProcess.o build.sse4_f_inl0_hrd0/MatrixElementKernels.o build.sse4_f_inl0_hrd0/BridgeKernels.o build.sse4_f_inl0_hrd0/CrossSectionKernels.o build.sse4_f_inl0_hrd0/fbridge.o -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl0_hrd0/runTest.exe build.sse4_f_inl0_hrd0/CPPProcess.o build.sse4_f_inl0_hrd0/MatrixElementKernels.o build.sse4_f_inl0_hrd0/BridgeKernels.o build.sse4_f_inl0_hrd0/CrossSectionKernels.o build.sse4_f_inl0_hrd0/RandomNumberKernels.o build.sse4_f_inl0_hrd0/RamboSamplingKernels.o build.sse4_f_inl0_hrd0/testxxx.o  build.sse4_f_inl0_hrd0/testmisc.o  build.sse4_f_inl0_hrd0/runTest.o build.sse4_f_inl0_hrd0/gCPPProcess.o build.sse4_f_inl0_hrd0/gMatrixElementKernels.o build.sse4_f_inl0_hrd0/gBridgeKernels.o build.sse4_f_inl0_hrd0/gCrossSectionKernels.o build.sse4_f_inl0_hrd0/gRandomNumberKernels.o build.sse4_f_inl0_hrd0/gRamboSamplingKernels.o build.sse4_f_inl0_hrd0/testxxx_cu.o  build.sse4_f_inl0_hrd0/testmisc_cu.o  build.sse4_f_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_f_inl0_hrd0/check.exe build.sse4_f_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_ll_ll_cpp build.sse4_f_inl0_hrd0/RandomNumberKernels.o build.sse4_f_inl0_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_f_inl0_hrd0/fcheck.exe build.sse4_f_inl0_hrd0/fcheck_sa.o build.sse4_f_inl0_hrd0/fsampler.o -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_ll_ll_cpp build.sse4_f_inl0_hrd0/RandomNumberKernels.o build.sse4_f_inl0_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl0_hrd0/gcheck.exe build.sse4_f_inl0_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_ll_ll_cuda build.sse4_f_inl0_hrd0/gRandomNumberKernels.o build.sse4_f_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl0_hrd0/fgcheck.exe build.sse4_f_inl0_hrd0/fcheck_sa.o build.sse4_f_inl0_hrd0/fsampler_cu.o -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_ll_ll_cuda build.sse4_f_inl0_hrd0/gRandomNumberKernels.o build.sse4_f_inl0_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.sse4_f_inl0_hrd0/libmg5amc_ll_ll_cuda.so build.sse4_f_inl0_hrd0/gCPPProcess.o build.sse4_f_inl0_hrd0/gMatrixElementKernels.o build.sse4_f_inl0_hrd0/gBridgeKernels.o build.sse4_f_inl0_hrd0/gCrossSectionKernels.o build.sse4_f_inl0_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.sse4_f_inl0_hrd0/libmg5amc_ll_ll_cpp.so build.sse4_f_inl0_hrd0/CPPProcess.o build.sse4_f_inl0_hrd0/MatrixElementKernels.o build.sse4_f_inl0_hrd0/BridgeKernels.o build.sse4_f_inl0_hrd0/CrossSectionKernels.o build.sse4_f_inl0_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_f_inl0_hrd0/fcheck.exe build.sse4_f_inl0_hrd0/fcheck_sa.o build.sse4_f_inl0_hrd0/fsampler.o -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_f_inl0_hrd0'  -lgfortran -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_ll_ll_cpp build.sse4_f_inl0_hrd0/RandomNumberKernels.o build.sse4_f_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl0_hrd0/gcheck.exe build.sse4_f_inl0_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl0_hrd0'  -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_ll_ll_cuda build.sse4_f_inl0_hrd0/gRandomNumberKernels.o build.sse4_f_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl0_hrd0/fgcheck.exe build.sse4_f_inl0_hrd0/fcheck_sa.o build.sse4_f_inl0_hrd0/fsampler_cu.o -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl0_hrd0'  -lgfortran -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_ll_ll_cuda build.sse4_f_inl0_hrd0/gRandomNumberKernels.o build.sse4_f_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_f_inl0_hrd0/check.exe build.sse4_f_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_f_inl0_hrd0'  -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_ll_ll_cpp build.sse4_f_inl0_hrd0/RandomNumberKernels.o build.sse4_f_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl0_hrd0/runTest.exe build.sse4_f_inl0_hrd0/CPPProcess.o build.sse4_f_inl0_hrd0/MatrixElementKernels.o build.sse4_f_inl0_hrd0/BridgeKernels.o build.sse4_f_inl0_hrd0/CrossSectionKernels.o build.sse4_f_inl0_hrd0/RandomNumberKernels.o build.sse4_f_inl0_hrd0/RamboSamplingKernels.o build.sse4_f_inl0_hrd0/testxxx.o  build.sse4_f_inl0_hrd0/testmisc.o  build.sse4_f_inl0_hrd0/runTest.o build.sse4_f_inl0_hrd0/gCPPProcess.o build.sse4_f_inl0_hrd0/gMatrixElementKernels.o build.sse4_f_inl0_hrd0/gBridgeKernels.o build.sse4_f_inl0_hrd0/gCrossSectionKernels.o build.sse4_f_inl0_hrd0/gRandomNumberKernels.o build.sse4_f_inl0_hrd0/gRamboSamplingKernels.o build.sse4_f_inl0_hrd0/testxxx_cu.o  build.sse4_f_inl0_hrd0/testmisc_cu.o  build.sse4_f_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl0_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
 touch build.sse4_f_inl0_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_f_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.sse4_f_inl0_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_f_inl0_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_f_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.sse4_f_inl0_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_f_inl0_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.sse4_f_inl0_hrd0/libmg5amc_ll_ll_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_f_inl0_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.sse4_f_inl0_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_f_inl0_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_20:58:35
+DATE: 2022-09-24_23:41:20
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.sse4_f_inl0_hrd0/check.exe -p 2048 256 24 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.sse4_f_inl0_hrd0/check.exe -p 2048 256 24 OMP=
 Process                     = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.2.0] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CPP:FLT+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK
 FP precision                = FLOAT (NaN/abnormal=12, zero=0)
 Internal loops fptype_sv    = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 2.375853e+06                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 6.088850e+06                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 6.088850e+06                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 2.396629e+06                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 6.108306e+06                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 6.108306e+06                 )  sec^-1
 MeanMatrixElemValue         = ( 1.371957e-02 +- 2.312985e-06 )  GeV^0
-TOTAL       :     6.109565 sec
-real	0m6.123s
+TOTAL       :     6.061096 sec
+real	0m6.073s
 =Symbols in CPPProcess.o= (~sse4: 1389) (avx2:    0) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.sse4_f_inl0_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.sse4_f_inl0_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.sse4_f_inl0_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.sse4_f_inl0_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 1.282804e-02
 Avg ME (F77/C++)    = 1.2828040051317657E-002
 Relative difference = 4.0004284926834985e-09
@@ -1142,13 +1153,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 20:58:43 CEST 2022 Will execute './throughputX.sh -makej -eemumu -sse4only -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:41:41 CEST 2022 Will execute './throughputX.sh -makej -eemumu -sse4only -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -sse4only implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
 CUDACPP_BUILDDIR='build.sse4_f_inl1_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -1158,71 +1169,72 @@ HELINL=1
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.sse4_f_inl1_hrd0 for tag=sse4_f_inl1_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.sse4_f_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.sse4_f_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.sse4_f_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.sse4_f_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.sse4_f_inl1_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.sse4_f_inl1_hrd0/gBridgeKernels.o
 AVX=sse4
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.sse4_f_inl1_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.sse4_f_inl1_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.sse4_f_inl1_hrd0/gBridgeKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.sse4_f_inl1_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.sse4_f_inl1_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.sse4_f_inl1_hrd0/gCrossSectionKernels.o
-mkdir -p ../lib/build.sse4_f_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.sse4_f_inl1_hrd0/fbridge_cu.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.sse4_f_inl1_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.sse4_f_inl1_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.sse4_f_inl1_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.sse4_f_inl1_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.sse4_f_inl1_hrd0/gRandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.sse4_f_inl1_hrd0/check_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.sse4_f_inl1_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.sse4_f_inl1_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.sse4_f_inl1_hrd0/MatrixElementKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.sse4_f_inl1_hrd0/BridgeKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.sse4_f_inl1_hrd0/CrossSectionKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.sse4_f_inl1_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.sse4_f_inl1_hrd0/fbridge.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.sse4_f_inl1_hrd0/Parameters_sm.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.sse4_f_inl1_hrd0/RandomNumberKernels.o
+mkdir -p ../lib/build.sse4_f_inl1_hrd0
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.sse4_f_inl1_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.sse4_f_inl1_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.sse4_f_inl1_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.sse4_f_inl1_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.sse4_f_inl1_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.sse4_f_inl1_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.sse4_f_inl1_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.sse4_f_inl1_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.sse4_f_inl1_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.sse4_f_inl1_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.sse4_f_inl1_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.sse4_f_inl1_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.sse4_f_inl1_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.sse4_f_inl1_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.sse4_f_inl1_hrd0/libmg5amc_common.so build.sse4_f_inl1_hrd0/Parameters_sm.o build.sse4_f_inl1_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.sse4_f_inl1_hrd0/libmg5amc_ll_ll_cuda.so build.sse4_f_inl1_hrd0/gCPPProcess.o build.sse4_f_inl1_hrd0/gMatrixElementKernels.o build.sse4_f_inl1_hrd0/gBridgeKernels.o build.sse4_f_inl1_hrd0/gCrossSectionKernels.o build.sse4_f_inl1_hrd0/fbridge_cu.o -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.sse4_f_inl1_hrd0/libmg5amc_ll_ll_cpp.so build.sse4_f_inl1_hrd0/CPPProcess.o build.sse4_f_inl1_hrd0/MatrixElementKernels.o build.sse4_f_inl1_hrd0/BridgeKernels.o build.sse4_f_inl1_hrd0/CrossSectionKernels.o build.sse4_f_inl1_hrd0/fbridge.o -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl1_hrd0/runTest.exe build.sse4_f_inl1_hrd0/CPPProcess.o build.sse4_f_inl1_hrd0/MatrixElementKernels.o build.sse4_f_inl1_hrd0/BridgeKernels.o build.sse4_f_inl1_hrd0/CrossSectionKernels.o build.sse4_f_inl1_hrd0/RandomNumberKernels.o build.sse4_f_inl1_hrd0/RamboSamplingKernels.o build.sse4_f_inl1_hrd0/testxxx.o  build.sse4_f_inl1_hrd0/testmisc.o  build.sse4_f_inl1_hrd0/runTest.o build.sse4_f_inl1_hrd0/gCPPProcess.o build.sse4_f_inl1_hrd0/gMatrixElementKernels.o build.sse4_f_inl1_hrd0/gBridgeKernels.o build.sse4_f_inl1_hrd0/gCrossSectionKernels.o build.sse4_f_inl1_hrd0/gRandomNumberKernels.o build.sse4_f_inl1_hrd0/gRamboSamplingKernels.o build.sse4_f_inl1_hrd0/testxxx_cu.o  build.sse4_f_inl1_hrd0/testmisc_cu.o  build.sse4_f_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_f_inl1_hrd0/check.exe build.sse4_f_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_ll_ll_cpp build.sse4_f_inl1_hrd0/RandomNumberKernels.o build.sse4_f_inl1_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_f_inl1_hrd0/fcheck.exe build.sse4_f_inl1_hrd0/fcheck_sa.o build.sse4_f_inl1_hrd0/fsampler.o -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_ll_ll_cpp build.sse4_f_inl1_hrd0/RandomNumberKernels.o build.sse4_f_inl1_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl1_hrd0/gcheck.exe build.sse4_f_inl1_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_ll_ll_cuda build.sse4_f_inl1_hrd0/gRandomNumberKernels.o build.sse4_f_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl1_hrd0/fgcheck.exe build.sse4_f_inl1_hrd0/fcheck_sa.o build.sse4_f_inl1_hrd0/fsampler_cu.o -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_ll_ll_cuda build.sse4_f_inl1_hrd0/gRandomNumberKernels.o build.sse4_f_inl1_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.sse4_f_inl1_hrd0/libmg5amc_ll_ll_cuda.so build.sse4_f_inl1_hrd0/gCPPProcess.o build.sse4_f_inl1_hrd0/gMatrixElementKernels.o build.sse4_f_inl1_hrd0/gBridgeKernels.o build.sse4_f_inl1_hrd0/gCrossSectionKernels.o build.sse4_f_inl1_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl1_hrd0/gcheck.exe build.sse4_f_inl1_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl1_hrd0'  -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_ll_ll_cuda build.sse4_f_inl1_hrd0/gRandomNumberKernels.o build.sse4_f_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl1_hrd0/fgcheck.exe build.sse4_f_inl1_hrd0/fcheck_sa.o build.sse4_f_inl1_hrd0/fsampler_cu.o -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl1_hrd0'  -lgfortran -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_ll_ll_cuda build.sse4_f_inl1_hrd0/gRandomNumberKernels.o build.sse4_f_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.sse4_f_inl1_hrd0/libmg5amc_ll_ll_cpp.so build.sse4_f_inl1_hrd0/CPPProcess.o build.sse4_f_inl1_hrd0/MatrixElementKernels.o build.sse4_f_inl1_hrd0/BridgeKernels.o build.sse4_f_inl1_hrd0/CrossSectionKernels.o build.sse4_f_inl1_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_f_inl1_hrd0/fcheck.exe build.sse4_f_inl1_hrd0/fcheck_sa.o build.sse4_f_inl1_hrd0/fsampler.o -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_f_inl1_hrd0'  -lgfortran -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_ll_ll_cpp build.sse4_f_inl1_hrd0/RandomNumberKernels.o build.sse4_f_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_f_inl1_hrd0/check.exe build.sse4_f_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_f_inl1_hrd0'  -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_ll_ll_cpp build.sse4_f_inl1_hrd0/RandomNumberKernels.o build.sse4_f_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl1_hrd0/runTest.exe build.sse4_f_inl1_hrd0/CPPProcess.o build.sse4_f_inl1_hrd0/MatrixElementKernels.o build.sse4_f_inl1_hrd0/BridgeKernels.o build.sse4_f_inl1_hrd0/CrossSectionKernels.o build.sse4_f_inl1_hrd0/RandomNumberKernels.o build.sse4_f_inl1_hrd0/RamboSamplingKernels.o build.sse4_f_inl1_hrd0/testxxx.o  build.sse4_f_inl1_hrd0/testmisc.o  build.sse4_f_inl1_hrd0/runTest.o build.sse4_f_inl1_hrd0/gCPPProcess.o build.sse4_f_inl1_hrd0/gMatrixElementKernels.o build.sse4_f_inl1_hrd0/gBridgeKernels.o build.sse4_f_inl1_hrd0/gCrossSectionKernels.o build.sse4_f_inl1_hrd0/gRandomNumberKernels.o build.sse4_f_inl1_hrd0/gRamboSamplingKernels.o build.sse4_f_inl1_hrd0/testxxx_cu.o  build.sse4_f_inl1_hrd0/testmisc_cu.o  build.sse4_f_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl1_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
 touch build.sse4_f_inl1_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_f_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.sse4_f_inl1_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_f_inl1_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_f_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.sse4_f_inl1_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_f_inl1_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.sse4_f_inl1_hrd0/libmg5amc_ll_ll_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_f_inl1_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.sse4_f_inl1_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_f_inl1_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_20:58:45
+DATE: 2022-09-24_23:41:48
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.sse4_f_inl1_hrd0/check.exe -p 2048 256 24 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.sse4_f_inl1_hrd0/check.exe -p 2048 256 24 OMP=
 Process                     = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.2.0] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CPP:FLT+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK
 FP precision                = FLOAT (NaN/abnormal=12, zero=0)
 Internal loops fptype_sv    = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 3.067071e+06                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 1.429687e+07                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 1.429687e+07                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 3.112174e+06                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 1.471368e+07                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 1.471368e+07                 )  sec^-1
 MeanMatrixElemValue         = ( 1.371957e-02 +- 2.312985e-06 )  GeV^0
-TOTAL       :     4.920297 sec
-real	0m4.933s
+TOTAL       :     4.854089 sec
+real	0m4.866s
 =Symbols in CPPProcess.o= (~sse4:  507) (avx2:    0) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.sse4_f_inl1_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.sse4_f_inl1_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.sse4_f_inl1_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.sse4_f_inl1_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 1.282804e-02
 Avg ME (F77/C++)    = 1.2828040020394837E-002
 Relative difference = 1.589863834303921e-09
@@ -1230,13 +1242,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 20:58:52 CEST 2022 Will execute './throughputX.sh -makej -eemumu -avx2only  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:42:08 CEST 2022 Will execute './throughputX.sh -makej -eemumu -avx2only  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -avx2only implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
 CUDACPP_BUILDDIR='build.avx2_d_inl0_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -1246,71 +1258,72 @@ HELINL=0
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.avx2_d_inl0_hrd0 for tag=avx2_d_inl0_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.avx2_d_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gcheck_sa.cu -o build.avx2_d_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gcheck_sa.cu -o build.avx2_d_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gCPPProcess.cu -o build.avx2_d_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.avx2_d_inl0_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gBridgeKernels.cu -o build.avx2_d_inl0_hrd0/gBridgeKernels.o
 AVX=avx2
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gCPPProcess.cu -o build.avx2_d_inl0_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.avx2_d_inl0_hrd0/gMatrixElementKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gBridgeKernels.cu -o build.avx2_d_inl0_hrd0/gBridgeKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -c Parameters_sm.cc -o build.avx2_d_inl0_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -c read_slha.cc -o build.avx2_d_inl0_hrd0/read_slha.o
-mkdir -p ../lib/build.avx2_d_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.avx2_d_inl0_hrd0/gCrossSectionKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fbridge.cc -o build.avx2_d_inl0_hrd0/fbridge_cu.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.avx2_d_inl0_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.avx2_d_inl0_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.avx2_d_inl0_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fbridge.cc -o build.avx2_d_inl0_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.avx2_d_inl0_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.avx2_d_inl0_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.avx2_d_inl0_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.avx2_d_inl0_hrd0/CPPProcess.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.avx2_d_inl0_hrd0/MatrixElementKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -c Parameters_sm.cc -o build.avx2_d_inl0_hrd0/Parameters_sm.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.avx2_d_inl0_hrd0/BridgeKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -c read_slha.cc -o build.avx2_d_inl0_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.avx2_d_inl0_hrd0/CrossSectionKernels.o
+mkdir -p ../lib/build.avx2_d_inl0_hrd0
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.avx2_d_inl0_hrd0/fbridge.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.avx2_d_inl0_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.avx2_d_inl0_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.avx2_d_inl0_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testxxx.cc -o build.avx2_d_inl0_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testxxx.cc -o build.avx2_d_inl0_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.avx2_d_inl0_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testmisc.cc -o build.avx2_d_inl0_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testmisc.cc -o build.avx2_d_inl0_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.avx2_d_inl0_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu runTest.cc -o build.avx2_d_inl0_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu runTest.cc -o build.avx2_d_inl0_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.avx2_d_inl0_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fsampler.cc -o build.avx2_d_inl0_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fsampler.cc -o build.avx2_d_inl0_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.avx2_d_inl0_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.avx2_d_inl0_hrd0/libmg5amc_common.so build.avx2_d_inl0_hrd0/Parameters_sm.o build.avx2_d_inl0_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.avx2_d_inl0_hrd0/libmg5amc_ll_ll_cuda.so build.avx2_d_inl0_hrd0/gCPPProcess.o build.avx2_d_inl0_hrd0/gMatrixElementKernels.o build.avx2_d_inl0_hrd0/gBridgeKernels.o build.avx2_d_inl0_hrd0/gCrossSectionKernels.o build.avx2_d_inl0_hrd0/fbridge_cu.o -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.avx2_d_inl0_hrd0/libmg5amc_ll_ll_cpp.so build.avx2_d_inl0_hrd0/CPPProcess.o build.avx2_d_inl0_hrd0/MatrixElementKernels.o build.avx2_d_inl0_hrd0/BridgeKernels.o build.avx2_d_inl0_hrd0/CrossSectionKernels.o build.avx2_d_inl0_hrd0/fbridge.o -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl0_hrd0/runTest.exe build.avx2_d_inl0_hrd0/CPPProcess.o build.avx2_d_inl0_hrd0/MatrixElementKernels.o build.avx2_d_inl0_hrd0/BridgeKernels.o build.avx2_d_inl0_hrd0/CrossSectionKernels.o build.avx2_d_inl0_hrd0/RandomNumberKernels.o build.avx2_d_inl0_hrd0/RamboSamplingKernels.o build.avx2_d_inl0_hrd0/testxxx.o  build.avx2_d_inl0_hrd0/testmisc.o  build.avx2_d_inl0_hrd0/runTest.o build.avx2_d_inl0_hrd0/gCPPProcess.o build.avx2_d_inl0_hrd0/gMatrixElementKernels.o build.avx2_d_inl0_hrd0/gBridgeKernels.o build.avx2_d_inl0_hrd0/gCrossSectionKernels.o build.avx2_d_inl0_hrd0/gRandomNumberKernels.o build.avx2_d_inl0_hrd0/gRamboSamplingKernels.o build.avx2_d_inl0_hrd0/testxxx_cu.o  build.avx2_d_inl0_hrd0/testmisc_cu.o  build.avx2_d_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_d_inl0_hrd0/check.exe build.avx2_d_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_ll_ll_cpp build.avx2_d_inl0_hrd0/RandomNumberKernels.o build.avx2_d_inl0_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_d_inl0_hrd0/fcheck.exe build.avx2_d_inl0_hrd0/fcheck_sa.o build.avx2_d_inl0_hrd0/fsampler.o -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_ll_ll_cpp build.avx2_d_inl0_hrd0/RandomNumberKernels.o build.avx2_d_inl0_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl0_hrd0/gcheck.exe build.avx2_d_inl0_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_ll_ll_cuda build.avx2_d_inl0_hrd0/gRandomNumberKernels.o build.avx2_d_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl0_hrd0/fgcheck.exe build.avx2_d_inl0_hrd0/fcheck_sa.o build.avx2_d_inl0_hrd0/fsampler_cu.o -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_ll_ll_cuda build.avx2_d_inl0_hrd0/gRandomNumberKernels.o build.avx2_d_inl0_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.avx2_d_inl0_hrd0/libmg5amc_ll_ll_cuda.so build.avx2_d_inl0_hrd0/gCPPProcess.o build.avx2_d_inl0_hrd0/gMatrixElementKernels.o build.avx2_d_inl0_hrd0/gBridgeKernels.o build.avx2_d_inl0_hrd0/gCrossSectionKernels.o build.avx2_d_inl0_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.avx2_d_inl0_hrd0/libmg5amc_ll_ll_cpp.so build.avx2_d_inl0_hrd0/CPPProcess.o build.avx2_d_inl0_hrd0/MatrixElementKernels.o build.avx2_d_inl0_hrd0/BridgeKernels.o build.avx2_d_inl0_hrd0/CrossSectionKernels.o build.avx2_d_inl0_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_d_inl0_hrd0/fcheck.exe build.avx2_d_inl0_hrd0/fcheck_sa.o build.avx2_d_inl0_hrd0/fsampler.o -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_d_inl0_hrd0'  -lgfortran -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_ll_ll_cpp build.avx2_d_inl0_hrd0/RandomNumberKernels.o build.avx2_d_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl0_hrd0/gcheck.exe build.avx2_d_inl0_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl0_hrd0'  -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_ll_ll_cuda build.avx2_d_inl0_hrd0/gRandomNumberKernels.o build.avx2_d_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl0_hrd0/fgcheck.exe build.avx2_d_inl0_hrd0/fcheck_sa.o build.avx2_d_inl0_hrd0/fsampler_cu.o -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl0_hrd0'  -lgfortran -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_ll_ll_cuda build.avx2_d_inl0_hrd0/gRandomNumberKernels.o build.avx2_d_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_d_inl0_hrd0/check.exe build.avx2_d_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_d_inl0_hrd0'  -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_ll_ll_cpp build.avx2_d_inl0_hrd0/RandomNumberKernels.o build.avx2_d_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl0_hrd0/runTest.exe build.avx2_d_inl0_hrd0/CPPProcess.o build.avx2_d_inl0_hrd0/MatrixElementKernels.o build.avx2_d_inl0_hrd0/BridgeKernels.o build.avx2_d_inl0_hrd0/CrossSectionKernels.o build.avx2_d_inl0_hrd0/RandomNumberKernels.o build.avx2_d_inl0_hrd0/RamboSamplingKernels.o build.avx2_d_inl0_hrd0/testxxx.o  build.avx2_d_inl0_hrd0/testmisc.o  build.avx2_d_inl0_hrd0/runTest.o build.avx2_d_inl0_hrd0/gCPPProcess.o build.avx2_d_inl0_hrd0/gMatrixElementKernels.o build.avx2_d_inl0_hrd0/gBridgeKernels.o build.avx2_d_inl0_hrd0/gCrossSectionKernels.o build.avx2_d_inl0_hrd0/gRandomNumberKernels.o build.avx2_d_inl0_hrd0/gRamboSamplingKernels.o build.avx2_d_inl0_hrd0/testxxx_cu.o  build.avx2_d_inl0_hrd0/testmisc_cu.o  build.avx2_d_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl0_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
 touch build.avx2_d_inl0_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_d_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.avx2_d_inl0_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_d_inl0_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_d_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.avx2_d_inl0_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_d_inl0_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.avx2_d_inl0_hrd0/libmg5amc_ll_ll_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_d_inl0_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.avx2_d_inl0_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_d_inl0_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_20:58:53
+DATE: 2022-09-24_23:42:18
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.avx2_d_inl0_hrd0/check.exe -p 2048 256 24 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.avx2_d_inl0_hrd0/check.exe -p 2048 256 24 OMP=
 Process                     = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.2.0] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CPP:DBL+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 1.995788e+06                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 5.372729e+06                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 5.372729e+06                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 2.020829e+06                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 5.434791e+06                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 5.434791e+06                 )  sec^-1
 MeanMatrixElemValue         = ( 1.371952e-02 +- 2.312385e-06 )  GeV^0
-TOTAL       :     7.225261 sec
-real	0m7.245s
+TOTAL       :     7.133747 sec
+real	0m7.151s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2: 1083) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.avx2_d_inl0_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.avx2_d_inl0_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.avx2_d_inl0_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.avx2_d_inl0_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 1.282804e-02
 Avg ME (F77/C++)    = 1.2828039868165088E-002
 Relative difference = 1.0277089312025782e-08
@@ -1318,13 +1331,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 20:59:02 CEST 2022 Will execute './throughputX.sh -makej -eemumu -avx2only  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:42:40 CEST 2022 Will execute './throughputX.sh -makej -eemumu -avx2only  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -avx2only implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
 CUDACPP_BUILDDIR='build.avx2_d_inl1_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -1334,22 +1347,18 @@ HELINL=1
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.avx2_d_inl1_hrd0 for tag=avx2_d_inl1_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.avx2_d_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.avx2_d_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.avx2_d_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.avx2_d_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.avx2_d_inl1_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.avx2_d_inl1_hrd0/gBridgeKernels.o
 AVX=avx2
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.avx2_d_inl1_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.avx2_d_inl1_hrd0/gMatrixElementKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.avx2_d_inl1_hrd0/gBridgeKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.avx2_d_inl1_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.avx2_d_inl1_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.avx2_d_inl1_hrd0/gCrossSectionKernels.o
-mkdir -p ../lib/build.avx2_d_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.avx2_d_inl1_hrd0/fbridge_cu.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.avx2_d_inl1_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.avx2_d_inl1_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.avx2_d_inl1_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.avx2_d_inl1_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.avx2_d_inl1_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.avx2_d_inl1_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.avx2_d_inl1_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.avx2_d_inl1_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.avx2_d_inl1_hrd0/MatrixElementKernels.o
@@ -1357,48 +1366,53 @@ ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.avx2_d_inl1_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.avx2_d_inl1_hrd0/fbridge.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.avx2_d_inl1_hrd0/RandomNumberKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.avx2_d_inl1_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.avx2_d_inl1_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.avx2_d_inl1_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.avx2_d_inl1_hrd0/testxxx_cu.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.avx2_d_inl1_hrd0/Parameters_sm.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.avx2_d_inl1_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.avx2_d_inl1_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.avx2_d_inl1_hrd0/testmisc_cu.o
+mkdir -p ../lib/build.avx2_d_inl1_hrd0
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.avx2_d_inl1_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.avx2_d_inl1_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.avx2_d_inl1_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.avx2_d_inl1_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.avx2_d_inl1_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.avx2_d_inl1_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.avx2_d_inl1_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.avx2_d_inl1_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.avx2_d_inl1_hrd0/libmg5amc_common.so build.avx2_d_inl1_hrd0/Parameters_sm.o build.avx2_d_inl1_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.avx2_d_inl1_hrd0/libmg5amc_ll_ll_cuda.so build.avx2_d_inl1_hrd0/gCPPProcess.o build.avx2_d_inl1_hrd0/gMatrixElementKernels.o build.avx2_d_inl1_hrd0/gBridgeKernels.o build.avx2_d_inl1_hrd0/gCrossSectionKernels.o build.avx2_d_inl1_hrd0/fbridge_cu.o -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.avx2_d_inl1_hrd0/libmg5amc_ll_ll_cpp.so build.avx2_d_inl1_hrd0/CPPProcess.o build.avx2_d_inl1_hrd0/MatrixElementKernels.o build.avx2_d_inl1_hrd0/BridgeKernels.o build.avx2_d_inl1_hrd0/CrossSectionKernels.o build.avx2_d_inl1_hrd0/fbridge.o -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl1_hrd0/runTest.exe build.avx2_d_inl1_hrd0/CPPProcess.o build.avx2_d_inl1_hrd0/MatrixElementKernels.o build.avx2_d_inl1_hrd0/BridgeKernels.o build.avx2_d_inl1_hrd0/CrossSectionKernels.o build.avx2_d_inl1_hrd0/RandomNumberKernels.o build.avx2_d_inl1_hrd0/RamboSamplingKernels.o build.avx2_d_inl1_hrd0/testxxx.o  build.avx2_d_inl1_hrd0/testmisc.o  build.avx2_d_inl1_hrd0/runTest.o build.avx2_d_inl1_hrd0/gCPPProcess.o build.avx2_d_inl1_hrd0/gMatrixElementKernels.o build.avx2_d_inl1_hrd0/gBridgeKernels.o build.avx2_d_inl1_hrd0/gCrossSectionKernels.o build.avx2_d_inl1_hrd0/gRandomNumberKernels.o build.avx2_d_inl1_hrd0/gRamboSamplingKernels.o build.avx2_d_inl1_hrd0/testxxx_cu.o  build.avx2_d_inl1_hrd0/testmisc_cu.o  build.avx2_d_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_d_inl1_hrd0/fcheck.exe build.avx2_d_inl1_hrd0/fcheck_sa.o build.avx2_d_inl1_hrd0/fsampler.o -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_ll_ll_cpp build.avx2_d_inl1_hrd0/RandomNumberKernels.o build.avx2_d_inl1_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_d_inl1_hrd0/check.exe build.avx2_d_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_ll_ll_cpp build.avx2_d_inl1_hrd0/RandomNumberKernels.o build.avx2_d_inl1_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl1_hrd0/gcheck.exe build.avx2_d_inl1_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_ll_ll_cuda build.avx2_d_inl1_hrd0/gRandomNumberKernels.o build.avx2_d_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl1_hrd0/fgcheck.exe build.avx2_d_inl1_hrd0/fcheck_sa.o build.avx2_d_inl1_hrd0/fsampler_cu.o -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_ll_ll_cuda build.avx2_d_inl1_hrd0/gRandomNumberKernels.o build.avx2_d_inl1_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.avx2_d_inl1_hrd0/libmg5amc_ll_ll_cuda.so build.avx2_d_inl1_hrd0/gCPPProcess.o build.avx2_d_inl1_hrd0/gMatrixElementKernels.o build.avx2_d_inl1_hrd0/gBridgeKernels.o build.avx2_d_inl1_hrd0/gCrossSectionKernels.o build.avx2_d_inl1_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl1_hrd0/gcheck.exe build.avx2_d_inl1_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl1_hrd0'  -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_ll_ll_cuda build.avx2_d_inl1_hrd0/gRandomNumberKernels.o build.avx2_d_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl1_hrd0/fgcheck.exe build.avx2_d_inl1_hrd0/fcheck_sa.o build.avx2_d_inl1_hrd0/fsampler_cu.o -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl1_hrd0'  -lgfortran -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_ll_ll_cuda build.avx2_d_inl1_hrd0/gRandomNumberKernels.o build.avx2_d_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.avx2_d_inl1_hrd0/libmg5amc_ll_ll_cpp.so build.avx2_d_inl1_hrd0/CPPProcess.o build.avx2_d_inl1_hrd0/MatrixElementKernels.o build.avx2_d_inl1_hrd0/BridgeKernels.o build.avx2_d_inl1_hrd0/CrossSectionKernels.o build.avx2_d_inl1_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_d_inl1_hrd0/fcheck.exe build.avx2_d_inl1_hrd0/fcheck_sa.o build.avx2_d_inl1_hrd0/fsampler.o -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_d_inl1_hrd0'  -lgfortran -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_ll_ll_cpp build.avx2_d_inl1_hrd0/RandomNumberKernels.o build.avx2_d_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_d_inl1_hrd0/check.exe build.avx2_d_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_d_inl1_hrd0'  -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_ll_ll_cpp build.avx2_d_inl1_hrd0/RandomNumberKernels.o build.avx2_d_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl1_hrd0/runTest.exe build.avx2_d_inl1_hrd0/CPPProcess.o build.avx2_d_inl1_hrd0/MatrixElementKernels.o build.avx2_d_inl1_hrd0/BridgeKernels.o build.avx2_d_inl1_hrd0/CrossSectionKernels.o build.avx2_d_inl1_hrd0/RandomNumberKernels.o build.avx2_d_inl1_hrd0/RamboSamplingKernels.o build.avx2_d_inl1_hrd0/testxxx.o  build.avx2_d_inl1_hrd0/testmisc.o  build.avx2_d_inl1_hrd0/runTest.o build.avx2_d_inl1_hrd0/gCPPProcess.o build.avx2_d_inl1_hrd0/gMatrixElementKernels.o build.avx2_d_inl1_hrd0/gBridgeKernels.o build.avx2_d_inl1_hrd0/gCrossSectionKernels.o build.avx2_d_inl1_hrd0/gRandomNumberKernels.o build.avx2_d_inl1_hrd0/gRamboSamplingKernels.o build.avx2_d_inl1_hrd0/testxxx_cu.o  build.avx2_d_inl1_hrd0/testmisc_cu.o  build.avx2_d_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl1_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
 touch build.avx2_d_inl1_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_d_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.avx2_d_inl1_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_d_inl1_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_d_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.avx2_d_inl1_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_d_inl1_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.avx2_d_inl1_hrd0/libmg5amc_ll_ll_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_d_inl1_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.avx2_d_inl1_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_d_inl1_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_20:59:04
+DATE: 2022-09-24_23:42:47
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.avx2_d_inl1_hrd0/check.exe -p 2048 256 24 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.avx2_d_inl1_hrd0/check.exe -p 2048 256 24 OMP=
 Process                     = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.2.0] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CPP:DBL+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 2.425490e+06                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 1.023114e+07                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 1.023114e+07                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 2.466042e+06                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 1.102532e+07                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 1.102532e+07                 )  sec^-1
 MeanMatrixElemValue         = ( 1.371952e-02 +- 2.312385e-06 )  GeV^0
-TOTAL       :     6.105927 sec
-real	0m6.126s
+TOTAL       :     6.006999 sec
+real	0m6.030s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2:  451) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.avx2_d_inl1_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.avx2_d_inl1_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.avx2_d_inl1_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.avx2_d_inl1_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 1.282804e-02
 Avg ME (F77/C++)    = 1.2828039868165088E-002
 Relative difference = 1.0277089312025782e-08
@@ -1406,13 +1420,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 20:59:12 CEST 2022 Will execute './throughputX.sh -makej -eemumu -avx2only -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:43:08 CEST 2022 Will execute './throughputX.sh -makej -eemumu -avx2only -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -avx2only implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
 CUDACPP_BUILDDIR='build.avx2_f_inl0_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -1422,71 +1436,72 @@ HELINL=0
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.avx2_f_inl0_hrd0 for tag=avx2_f_inl0_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.avx2_f_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gcheck_sa.cu -o build.avx2_f_inl0_hrd0/gcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gCPPProcess.cu -o build.avx2_f_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gcheck_sa.cu -o build.avx2_f_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gCPPProcess.cu -o build.avx2_f_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.avx2_f_inl0_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gBridgeKernels.cu -o build.avx2_f_inl0_hrd0/gBridgeKernels.o
 AVX=avx2
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.avx2_f_inl0_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gBridgeKernels.cu -o build.avx2_f_inl0_hrd0/gBridgeKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.avx2_f_inl0_hrd0/gCrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -c Parameters_sm.cc -o build.avx2_f_inl0_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -c read_slha.cc -o build.avx2_f_inl0_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fbridge.cc -o build.avx2_f_inl0_hrd0/fbridge_cu.o
-mkdir -p ../lib/build.avx2_f_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.avx2_f_inl0_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.avx2_f_inl0_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.avx2_f_inl0_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fbridge.cc -o build.avx2_f_inl0_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.avx2_f_inl0_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.avx2_f_inl0_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.avx2_f_inl0_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.avx2_f_inl0_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.avx2_f_inl0_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.avx2_f_inl0_hrd0/BridgeKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.avx2_f_inl0_hrd0/CrossSectionKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.avx2_f_inl0_hrd0/fbridge.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.avx2_f_inl0_hrd0/RandomNumberKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -c Parameters_sm.cc -o build.avx2_f_inl0_hrd0/Parameters_sm.o
+mkdir -p ../lib/build.avx2_f_inl0_hrd0
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -c read_slha.cc -o build.avx2_f_inl0_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.avx2_f_inl0_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.avx2_f_inl0_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testxxx.cc -o build.avx2_f_inl0_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testxxx.cc -o build.avx2_f_inl0_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.avx2_f_inl0_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testmisc.cc -o build.avx2_f_inl0_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testmisc.cc -o build.avx2_f_inl0_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.avx2_f_inl0_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu runTest.cc -o build.avx2_f_inl0_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu runTest.cc -o build.avx2_f_inl0_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.avx2_f_inl0_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fsampler.cc -o build.avx2_f_inl0_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fsampler.cc -o build.avx2_f_inl0_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.avx2_f_inl0_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.avx2_f_inl0_hrd0/libmg5amc_common.so build.avx2_f_inl0_hrd0/Parameters_sm.o build.avx2_f_inl0_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.avx2_f_inl0_hrd0/libmg5amc_ll_ll_cuda.so build.avx2_f_inl0_hrd0/gCPPProcess.o build.avx2_f_inl0_hrd0/gMatrixElementKernels.o build.avx2_f_inl0_hrd0/gBridgeKernels.o build.avx2_f_inl0_hrd0/gCrossSectionKernels.o build.avx2_f_inl0_hrd0/fbridge_cu.o -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.avx2_f_inl0_hrd0/libmg5amc_ll_ll_cpp.so build.avx2_f_inl0_hrd0/CPPProcess.o build.avx2_f_inl0_hrd0/MatrixElementKernels.o build.avx2_f_inl0_hrd0/BridgeKernels.o build.avx2_f_inl0_hrd0/CrossSectionKernels.o build.avx2_f_inl0_hrd0/fbridge.o -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl0_hrd0/runTest.exe build.avx2_f_inl0_hrd0/CPPProcess.o build.avx2_f_inl0_hrd0/MatrixElementKernels.o build.avx2_f_inl0_hrd0/BridgeKernels.o build.avx2_f_inl0_hrd0/CrossSectionKernels.o build.avx2_f_inl0_hrd0/RandomNumberKernels.o build.avx2_f_inl0_hrd0/RamboSamplingKernels.o build.avx2_f_inl0_hrd0/testxxx.o  build.avx2_f_inl0_hrd0/testmisc.o  build.avx2_f_inl0_hrd0/runTest.o build.avx2_f_inl0_hrd0/gCPPProcess.o build.avx2_f_inl0_hrd0/gMatrixElementKernels.o build.avx2_f_inl0_hrd0/gBridgeKernels.o build.avx2_f_inl0_hrd0/gCrossSectionKernels.o build.avx2_f_inl0_hrd0/gRandomNumberKernels.o build.avx2_f_inl0_hrd0/gRamboSamplingKernels.o build.avx2_f_inl0_hrd0/testxxx_cu.o  build.avx2_f_inl0_hrd0/testmisc_cu.o  build.avx2_f_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_f_inl0_hrd0/check.exe build.avx2_f_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_ll_ll_cpp build.avx2_f_inl0_hrd0/RandomNumberKernels.o build.avx2_f_inl0_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_f_inl0_hrd0/fcheck.exe build.avx2_f_inl0_hrd0/fcheck_sa.o build.avx2_f_inl0_hrd0/fsampler.o -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_ll_ll_cpp build.avx2_f_inl0_hrd0/RandomNumberKernels.o build.avx2_f_inl0_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl0_hrd0/gcheck.exe build.avx2_f_inl0_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_ll_ll_cuda build.avx2_f_inl0_hrd0/gRandomNumberKernels.o build.avx2_f_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl0_hrd0/fgcheck.exe build.avx2_f_inl0_hrd0/fcheck_sa.o build.avx2_f_inl0_hrd0/fsampler_cu.o -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_ll_ll_cuda build.avx2_f_inl0_hrd0/gRandomNumberKernels.o build.avx2_f_inl0_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.avx2_f_inl0_hrd0/libmg5amc_ll_ll_cuda.so build.avx2_f_inl0_hrd0/gCPPProcess.o build.avx2_f_inl0_hrd0/gMatrixElementKernels.o build.avx2_f_inl0_hrd0/gBridgeKernels.o build.avx2_f_inl0_hrd0/gCrossSectionKernels.o build.avx2_f_inl0_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.avx2_f_inl0_hrd0/libmg5amc_ll_ll_cpp.so build.avx2_f_inl0_hrd0/CPPProcess.o build.avx2_f_inl0_hrd0/MatrixElementKernels.o build.avx2_f_inl0_hrd0/BridgeKernels.o build.avx2_f_inl0_hrd0/CrossSectionKernels.o build.avx2_f_inl0_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_f_inl0_hrd0/fcheck.exe build.avx2_f_inl0_hrd0/fcheck_sa.o build.avx2_f_inl0_hrd0/fsampler.o -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_f_inl0_hrd0'  -lgfortran -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_ll_ll_cpp build.avx2_f_inl0_hrd0/RandomNumberKernels.o build.avx2_f_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl0_hrd0/gcheck.exe build.avx2_f_inl0_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl0_hrd0'  -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_ll_ll_cuda build.avx2_f_inl0_hrd0/gRandomNumberKernels.o build.avx2_f_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl0_hrd0/fgcheck.exe build.avx2_f_inl0_hrd0/fcheck_sa.o build.avx2_f_inl0_hrd0/fsampler_cu.o -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl0_hrd0'  -lgfortran -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_ll_ll_cuda build.avx2_f_inl0_hrd0/gRandomNumberKernels.o build.avx2_f_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_f_inl0_hrd0/check.exe build.avx2_f_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_f_inl0_hrd0'  -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_ll_ll_cpp build.avx2_f_inl0_hrd0/RandomNumberKernels.o build.avx2_f_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl0_hrd0/runTest.exe build.avx2_f_inl0_hrd0/CPPProcess.o build.avx2_f_inl0_hrd0/MatrixElementKernels.o build.avx2_f_inl0_hrd0/BridgeKernels.o build.avx2_f_inl0_hrd0/CrossSectionKernels.o build.avx2_f_inl0_hrd0/RandomNumberKernels.o build.avx2_f_inl0_hrd0/RamboSamplingKernels.o build.avx2_f_inl0_hrd0/testxxx.o  build.avx2_f_inl0_hrd0/testmisc.o  build.avx2_f_inl0_hrd0/runTest.o build.avx2_f_inl0_hrd0/gCPPProcess.o build.avx2_f_inl0_hrd0/gMatrixElementKernels.o build.avx2_f_inl0_hrd0/gBridgeKernels.o build.avx2_f_inl0_hrd0/gCrossSectionKernels.o build.avx2_f_inl0_hrd0/gRandomNumberKernels.o build.avx2_f_inl0_hrd0/gRamboSamplingKernels.o build.avx2_f_inl0_hrd0/testxxx_cu.o  build.avx2_f_inl0_hrd0/testmisc_cu.o  build.avx2_f_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl0_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
 touch build.avx2_f_inl0_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_f_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.avx2_f_inl0_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_f_inl0_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_f_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.avx2_f_inl0_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_f_inl0_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.avx2_f_inl0_hrd0/libmg5amc_ll_ll_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_f_inl0_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.avx2_f_inl0_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_f_inl0_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_20:59:13
+DATE: 2022-09-24_23:43:18
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.avx2_f_inl0_hrd0/check.exe -p 2048 256 24 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.avx2_f_inl0_hrd0/check.exe -p 2048 256 24 OMP=
 Process                     = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.2.0] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CPP:FLT+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK
 FP precision                = FLOAT (NaN/abnormal=11, zero=0)
 Internal loops fptype_sv    = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 2.907683e+06                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 1.123831e+07                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 1.123831e+07                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 2.977841e+06                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 1.137094e+07                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 1.137094e+07                 )  sec^-1
 MeanMatrixElemValue         = ( 1.371955e-02 +- 2.312467e-06 )  GeV^0
-TOTAL       :     5.142084 sec
-real	0m5.155s
+TOTAL       :     5.036090 sec
+real	0m5.048s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2: 1180) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.avx2_f_inl0_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.avx2_f_inl0_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.avx2_f_inl0_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.avx2_f_inl0_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 1.282805e-02
 Avg ME (F77/C++)    = 1.2828053435441689E-002
 Relative difference = 2.678070079295827e-07
@@ -1494,13 +1509,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 20:59:20 CEST 2022 Will execute './throughputX.sh -makej -eemumu -avx2only -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:43:38 CEST 2022 Will execute './throughputX.sh -makej -eemumu -avx2only -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -avx2only implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
 CUDACPP_BUILDDIR='build.avx2_f_inl1_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -1510,71 +1525,72 @@ HELINL=1
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.avx2_f_inl1_hrd0 for tag=avx2_f_inl1_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.avx2_f_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.avx2_f_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.avx2_f_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.avx2_f_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.avx2_f_inl1_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.avx2_f_inl1_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.avx2_f_inl1_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.avx2_f_inl1_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.avx2_f_inl1_hrd0/gRandomNumberKernels.o
 AVX=avx2
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.avx2_f_inl1_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.avx2_f_inl1_hrd0/gMatrixElementKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.avx2_f_inl1_hrd0/gBridgeKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.avx2_f_inl1_hrd0/Parameters_sm.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.avx2_f_inl1_hrd0/gCrossSectionKernels.o
-mkdir -p ../lib/build.avx2_f_inl1_hrd0
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.avx2_f_inl1_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.avx2_f_inl1_hrd0/fbridge_cu.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.avx2_f_inl1_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.avx2_f_inl1_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.avx2_f_inl1_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.avx2_f_inl1_hrd0/check_sa.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.avx2_f_inl1_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.avx2_f_inl1_hrd0/CPPProcess.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.avx2_f_inl1_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.avx2_f_inl1_hrd0/BridgeKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.avx2_f_inl1_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.avx2_f_inl1_hrd0/fbridge.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.avx2_f_inl1_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.avx2_f_inl1_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.avx2_f_inl1_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.avx2_f_inl1_hrd0/testxxx_cu.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.avx2_f_inl1_hrd0/Parameters_sm.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.avx2_f_inl1_hrd0/testxxx_cu.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.avx2_f_inl1_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.avx2_f_inl1_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.avx2_f_inl1_hrd0/testmisc_cu.o
+mkdir -p ../lib/build.avx2_f_inl1_hrd0
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.avx2_f_inl1_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.avx2_f_inl1_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.avx2_f_inl1_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.avx2_f_inl1_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.avx2_f_inl1_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.avx2_f_inl1_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.avx2_f_inl1_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.avx2_f_inl1_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.avx2_f_inl1_hrd0/libmg5amc_common.so build.avx2_f_inl1_hrd0/Parameters_sm.o build.avx2_f_inl1_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.avx2_f_inl1_hrd0/libmg5amc_ll_ll_cuda.so build.avx2_f_inl1_hrd0/gCPPProcess.o build.avx2_f_inl1_hrd0/gMatrixElementKernels.o build.avx2_f_inl1_hrd0/gBridgeKernels.o build.avx2_f_inl1_hrd0/gCrossSectionKernels.o build.avx2_f_inl1_hrd0/fbridge_cu.o -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.avx2_f_inl1_hrd0/libmg5amc_ll_ll_cpp.so build.avx2_f_inl1_hrd0/CPPProcess.o build.avx2_f_inl1_hrd0/MatrixElementKernels.o build.avx2_f_inl1_hrd0/BridgeKernels.o build.avx2_f_inl1_hrd0/CrossSectionKernels.o build.avx2_f_inl1_hrd0/fbridge.o -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl1_hrd0/runTest.exe build.avx2_f_inl1_hrd0/CPPProcess.o build.avx2_f_inl1_hrd0/MatrixElementKernels.o build.avx2_f_inl1_hrd0/BridgeKernels.o build.avx2_f_inl1_hrd0/CrossSectionKernels.o build.avx2_f_inl1_hrd0/RandomNumberKernels.o build.avx2_f_inl1_hrd0/RamboSamplingKernels.o build.avx2_f_inl1_hrd0/testxxx.o  build.avx2_f_inl1_hrd0/testmisc.o  build.avx2_f_inl1_hrd0/runTest.o build.avx2_f_inl1_hrd0/gCPPProcess.o build.avx2_f_inl1_hrd0/gMatrixElementKernels.o build.avx2_f_inl1_hrd0/gBridgeKernels.o build.avx2_f_inl1_hrd0/gCrossSectionKernels.o build.avx2_f_inl1_hrd0/gRandomNumberKernels.o build.avx2_f_inl1_hrd0/gRamboSamplingKernels.o build.avx2_f_inl1_hrd0/testxxx_cu.o  build.avx2_f_inl1_hrd0/testmisc_cu.o  build.avx2_f_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_f_inl1_hrd0/check.exe build.avx2_f_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_ll_ll_cpp build.avx2_f_inl1_hrd0/RandomNumberKernels.o build.avx2_f_inl1_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_f_inl1_hrd0/fcheck.exe build.avx2_f_inl1_hrd0/fcheck_sa.o build.avx2_f_inl1_hrd0/fsampler.o -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_ll_ll_cpp build.avx2_f_inl1_hrd0/RandomNumberKernels.o build.avx2_f_inl1_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl1_hrd0/gcheck.exe build.avx2_f_inl1_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_ll_ll_cuda build.avx2_f_inl1_hrd0/gRandomNumberKernels.o build.avx2_f_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl1_hrd0/fgcheck.exe build.avx2_f_inl1_hrd0/fcheck_sa.o build.avx2_f_inl1_hrd0/fsampler_cu.o -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_ll_ll_cuda build.avx2_f_inl1_hrd0/gRandomNumberKernels.o build.avx2_f_inl1_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.avx2_f_inl1_hrd0/libmg5amc_ll_ll_cuda.so build.avx2_f_inl1_hrd0/gCPPProcess.o build.avx2_f_inl1_hrd0/gMatrixElementKernels.o build.avx2_f_inl1_hrd0/gBridgeKernels.o build.avx2_f_inl1_hrd0/gCrossSectionKernels.o build.avx2_f_inl1_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl1_hrd0/gcheck.exe build.avx2_f_inl1_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl1_hrd0'  -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_ll_ll_cuda build.avx2_f_inl1_hrd0/gRandomNumberKernels.o build.avx2_f_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl1_hrd0/fgcheck.exe build.avx2_f_inl1_hrd0/fcheck_sa.o build.avx2_f_inl1_hrd0/fsampler_cu.o -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl1_hrd0'  -lgfortran -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_ll_ll_cuda build.avx2_f_inl1_hrd0/gRandomNumberKernels.o build.avx2_f_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.avx2_f_inl1_hrd0/libmg5amc_ll_ll_cpp.so build.avx2_f_inl1_hrd0/CPPProcess.o build.avx2_f_inl1_hrd0/MatrixElementKernels.o build.avx2_f_inl1_hrd0/BridgeKernels.o build.avx2_f_inl1_hrd0/CrossSectionKernels.o build.avx2_f_inl1_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_f_inl1_hrd0/fcheck.exe build.avx2_f_inl1_hrd0/fcheck_sa.o build.avx2_f_inl1_hrd0/fsampler.o -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_f_inl1_hrd0'  -lgfortran -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_ll_ll_cpp build.avx2_f_inl1_hrd0/RandomNumberKernels.o build.avx2_f_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_f_inl1_hrd0/check.exe build.avx2_f_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_f_inl1_hrd0'  -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_ll_ll_cpp build.avx2_f_inl1_hrd0/RandomNumberKernels.o build.avx2_f_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl1_hrd0/runTest.exe build.avx2_f_inl1_hrd0/CPPProcess.o build.avx2_f_inl1_hrd0/MatrixElementKernels.o build.avx2_f_inl1_hrd0/BridgeKernels.o build.avx2_f_inl1_hrd0/CrossSectionKernels.o build.avx2_f_inl1_hrd0/RandomNumberKernels.o build.avx2_f_inl1_hrd0/RamboSamplingKernels.o build.avx2_f_inl1_hrd0/testxxx.o  build.avx2_f_inl1_hrd0/testmisc.o  build.avx2_f_inl1_hrd0/runTest.o build.avx2_f_inl1_hrd0/gCPPProcess.o build.avx2_f_inl1_hrd0/gMatrixElementKernels.o build.avx2_f_inl1_hrd0/gBridgeKernels.o build.avx2_f_inl1_hrd0/gCrossSectionKernels.o build.avx2_f_inl1_hrd0/gRandomNumberKernels.o build.avx2_f_inl1_hrd0/gRamboSamplingKernels.o build.avx2_f_inl1_hrd0/testxxx_cu.o  build.avx2_f_inl1_hrd0/testmisc_cu.o  build.avx2_f_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl1_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
 touch build.avx2_f_inl1_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_f_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.avx2_f_inl1_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_f_inl1_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_f_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.avx2_f_inl1_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_f_inl1_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.avx2_f_inl1_hrd0/libmg5amc_ll_ll_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_f_inl1_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.avx2_f_inl1_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_f_inl1_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_20:59:22
+DATE: 2022-09-24_23:43:46
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.avx2_f_inl1_hrd0/check.exe -p 2048 256 24 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.avx2_f_inl1_hrd0/check.exe -p 2048 256 24 OMP=
 Process                     = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.2.0] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CPP:FLT+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK
 FP precision                = FLOAT (NaN/abnormal=11, zero=0)
 Internal loops fptype_sv    = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 3.435855e+06                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 2.462085e+07                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 2.462085e+07                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 3.526480e+06                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 2.761771e+07                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 2.761771e+07                 )  sec^-1
 MeanMatrixElemValue         = ( 1.371955e-02 +- 2.312467e-06 )  GeV^0
-TOTAL       :     4.478790 sec
-real	0m4.492s
+TOTAL       :     4.379423 sec
+real	0m4.391s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2:  553) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.avx2_f_inl1_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.avx2_f_inl1_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.avx2_f_inl1_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.avx2_f_inl1_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 1.282805e-02
 Avg ME (F77/C++)    = 1.2828053508201265E-002
 Relative difference = 2.7347892035133305e-07
@@ -1582,35 +1598,35 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 20:59:28 CEST 2022 Will execute './throughputX.sh -makej -eemumu -512yonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:44:05 CEST 2022 Will execute './throughputX.sh -makej -eemumu -512yonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -512yonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
 CUDACPP_BUILDDIR='build.512y_d_inl0_hrd0'
 make: Nothing to be done for `all'.
 
-DATE: 2022-08-31_20:59:28
+DATE: 2022-09-24_23:44:05
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512y_d_inl0_hrd0/check.exe -p 2048 256 24 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512y_d_inl0_hrd0/check.exe -p 2048 256 24 OMP=
 Process                     = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.2.0] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 2.040463e+06                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 5.846252e+06                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 5.846252e+06                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 2.068318e+06                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 5.855420e+06                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 5.855420e+06                 )  sec^-1
 MeanMatrixElemValue         = ( 1.371952e-02 +- 2.312385e-06 )  GeV^0
-TOTAL       :     7.086303 sec
-real	0m7.106s
+TOTAL       :     6.991784 sec
+real	0m7.009s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2: 1042) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512y_d_inl0_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512y_d_inl0_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512y_d_inl0_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512y_d_inl0_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 1.282804e-02
 Avg ME (F77/C++)    = 1.2828039868165088E-002
 Relative difference = 1.0277089312025782e-08
@@ -1618,35 +1634,35 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 20:59:37 CEST 2022 Will execute './throughputX.sh -makej -eemumu -512yonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:44:27 CEST 2022 Will execute './throughputX.sh -makej -eemumu -512yonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -512yonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
 CUDACPP_BUILDDIR='build.512y_d_inl1_hrd0'
 make: Nothing to be done for `all'.
 
-DATE: 2022-08-31_20:59:38
+DATE: 2022-09-24_23:44:28
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512y_d_inl1_hrd0/check.exe -p 2048 256 24 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512y_d_inl1_hrd0/check.exe -p 2048 256 24 OMP=
 Process                     = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.2.0] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 2.412673e+06                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 1.021613e+07                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 1.021613e+07                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 2.458005e+06                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 1.094437e+07                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 1.094437e+07                 )  sec^-1
 MeanMatrixElemValue         = ( 1.371952e-02 +- 2.312385e-06 )  GeV^0
-TOTAL       :     6.133152 sec
-real	0m6.153s
+TOTAL       :     6.024678 sec
+real	0m6.042s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2:  416) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512y_d_inl1_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512y_d_inl1_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512y_d_inl1_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512y_d_inl1_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 1.282804e-02
 Avg ME (F77/C++)    = 1.2828039868165088E-002
 Relative difference = 1.0277089312025782e-08
@@ -1654,35 +1670,35 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 20:59:46 CEST 2022 Will execute './throughputX.sh -makej -eemumu -512yonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:44:49 CEST 2022 Will execute './throughputX.sh -makej -eemumu -512yonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -512yonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
 CUDACPP_BUILDDIR='build.512y_f_inl0_hrd0'
 make: Nothing to be done for `all'.
 
-DATE: 2022-08-31_20:59:46
+DATE: 2022-09-24_23:44:49
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512y_f_inl0_hrd0/check.exe -p 2048 256 24 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512y_f_inl0_hrd0/check.exe -p 2048 256 24 OMP=
 Process                     = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.2.0] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK
 FP precision                = FLOAT (NaN/abnormal=11, zero=0)
 Internal loops fptype_sv    = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 2.999196e+06                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 1.206278e+07                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 1.206278e+07                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 3.008537e+06                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 1.228219e+07                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 1.228219e+07                 )  sec^-1
 MeanMatrixElemValue         = ( 1.371955e-02 +- 2.312467e-06 )  GeV^0
-TOTAL       :     5.002606 sec
-real	0m5.016s
+TOTAL       :     4.984895 sec
+real	0m4.997s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2: 1129) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512y_f_inl0_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512y_f_inl0_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512y_f_inl0_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512y_f_inl0_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 1.282805e-02
 Avg ME (F77/C++)    = 1.2828053435441689E-002
 Relative difference = 2.678070079295827e-07
@@ -1690,35 +1706,35 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 20:59:53 CEST 2022 Will execute './throughputX.sh -makej -eemumu -512yonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:45:09 CEST 2022 Will execute './throughputX.sh -makej -eemumu -512yonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -512yonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
 CUDACPP_BUILDDIR='build.512y_f_inl1_hrd0'
 make: Nothing to be done for `all'.
 
-DATE: 2022-08-31_20:59:53
+DATE: 2022-09-24_23:45:09
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512y_f_inl1_hrd0/check.exe -p 2048 256 24 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512y_f_inl1_hrd0/check.exe -p 2048 256 24 OMP=
 Process                     = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.2.0] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK
 FP precision                = FLOAT (NaN/abnormal=11, zero=0)
 Internal loops fptype_sv    = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 3.444287e+06                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 2.514256e+07                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 2.514256e+07                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 3.526058e+06                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 2.795492e+07                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 2.795492e+07                 )  sec^-1
 MeanMatrixElemValue         = ( 1.371955e-02 +- 2.312467e-06 )  GeV^0
-TOTAL       :     4.468134 sec
-real	0m4.481s
+TOTAL       :     4.374878 sec
+real	0m4.387s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2:  523) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512y_f_inl1_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512y_f_inl1_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512y_f_inl1_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512y_f_inl1_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 1.282805e-02
 Avg ME (F77/C++)    = 1.2828053508201265E-002
 Relative difference = 2.7347892035133305e-07
@@ -1726,13 +1742,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:00:00 CEST 2022 Will execute './throughputX.sh -makej -eemumu -512zonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:45:29 CEST 2022 Will execute './throughputX.sh -makej -eemumu -512zonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -512zonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
 CUDACPP_BUILDDIR='build.512z_d_inl0_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -1742,71 +1758,72 @@ HELINL=0
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.512z_d_inl0_hrd0 for tag=512z_d_inl0_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.512z_d_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gcheck_sa.cu -o build.512z_d_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gcheck_sa.cu -o build.512z_d_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gCPPProcess.cu -o build.512z_d_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512z_d_inl0_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512z_d_inl0_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512z_d_inl0_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512z_d_inl0_hrd0/fbridge_cu.o
 AVX=512z
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gCPPProcess.cu -o build.512z_d_inl0_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512z_d_inl0_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512z_d_inl0_hrd0/gBridgeKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512z_d_inl0_hrd0/gCrossSectionKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512z_d_inl0_hrd0/fbridge_cu.o
-mkdir -p ../lib/build.512z_d_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512z_d_inl0_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512z_d_inl0_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512z_d_inl0_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512z_d_inl0_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.512z_d_inl0_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.512z_d_inl0_hrd0/CPPProcess.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -c Parameters_sm.cc -o build.512z_d_inl0_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -c read_slha.cc -o build.512z_d_inl0_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.512z_d_inl0_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.512z_d_inl0_hrd0/BridgeKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.512z_d_inl0_hrd0/CrossSectionKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.512z_d_inl0_hrd0/fbridge.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.512z_d_inl0_hrd0/RandomNumberKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -c Parameters_sm.cc -o build.512z_d_inl0_hrd0/Parameters_sm.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.512z_d_inl0_hrd0/RamboSamplingKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -c read_slha.cc -o build.512z_d_inl0_hrd0/read_slha.o
+mkdir -p ../lib/build.512z_d_inl0_hrd0
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.512z_d_inl0_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512z_d_inl0_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512z_d_inl0_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.512z_d_inl0_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512z_d_inl0_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512z_d_inl0_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.512z_d_inl0_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu runTest.cc -o build.512z_d_inl0_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu runTest.cc -o build.512z_d_inl0_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.512z_d_inl0_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512z_d_inl0_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512z_d_inl0_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.512z_d_inl0_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.512z_d_inl0_hrd0/libmg5amc_common.so build.512z_d_inl0_hrd0/Parameters_sm.o build.512z_d_inl0_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512z_d_inl0_hrd0/libmg5amc_ll_ll_cuda.so build.512z_d_inl0_hrd0/gCPPProcess.o build.512z_d_inl0_hrd0/gMatrixElementKernels.o build.512z_d_inl0_hrd0/gBridgeKernels.o build.512z_d_inl0_hrd0/gCrossSectionKernels.o build.512z_d_inl0_hrd0/fbridge_cu.o -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512z_d_inl0_hrd0/libmg5amc_ll_ll_cpp.so build.512z_d_inl0_hrd0/CPPProcess.o build.512z_d_inl0_hrd0/MatrixElementKernels.o build.512z_d_inl0_hrd0/BridgeKernels.o build.512z_d_inl0_hrd0/CrossSectionKernels.o build.512z_d_inl0_hrd0/fbridge.o -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl0_hrd0/runTest.exe build.512z_d_inl0_hrd0/CPPProcess.o build.512z_d_inl0_hrd0/MatrixElementKernels.o build.512z_d_inl0_hrd0/BridgeKernels.o build.512z_d_inl0_hrd0/CrossSectionKernels.o build.512z_d_inl0_hrd0/RandomNumberKernels.o build.512z_d_inl0_hrd0/RamboSamplingKernels.o build.512z_d_inl0_hrd0/testxxx.o  build.512z_d_inl0_hrd0/testmisc.o  build.512z_d_inl0_hrd0/runTest.o build.512z_d_inl0_hrd0/gCPPProcess.o build.512z_d_inl0_hrd0/gMatrixElementKernels.o build.512z_d_inl0_hrd0/gBridgeKernels.o build.512z_d_inl0_hrd0/gCrossSectionKernels.o build.512z_d_inl0_hrd0/gRandomNumberKernels.o build.512z_d_inl0_hrd0/gRamboSamplingKernels.o build.512z_d_inl0_hrd0/testxxx_cu.o  build.512z_d_inl0_hrd0/testmisc_cu.o  build.512z_d_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_d_inl0_hrd0/check.exe build.512z_d_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_ll_ll_cpp build.512z_d_inl0_hrd0/RandomNumberKernels.o build.512z_d_inl0_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_d_inl0_hrd0/fcheck.exe build.512z_d_inl0_hrd0/fcheck_sa.o build.512z_d_inl0_hrd0/fsampler.o -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_ll_ll_cpp build.512z_d_inl0_hrd0/RandomNumberKernels.o build.512z_d_inl0_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl0_hrd0/gcheck.exe build.512z_d_inl0_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_ll_ll_cuda build.512z_d_inl0_hrd0/gRandomNumberKernels.o build.512z_d_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl0_hrd0/fgcheck.exe build.512z_d_inl0_hrd0/fcheck_sa.o build.512z_d_inl0_hrd0/fsampler_cu.o -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_ll_ll_cuda build.512z_d_inl0_hrd0/gRandomNumberKernels.o build.512z_d_inl0_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512z_d_inl0_hrd0/libmg5amc_ll_ll_cuda.so build.512z_d_inl0_hrd0/gCPPProcess.o build.512z_d_inl0_hrd0/gMatrixElementKernels.o build.512z_d_inl0_hrd0/gBridgeKernels.o build.512z_d_inl0_hrd0/gCrossSectionKernels.o build.512z_d_inl0_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512z_d_inl0_hrd0/libmg5amc_ll_ll_cpp.so build.512z_d_inl0_hrd0/CPPProcess.o build.512z_d_inl0_hrd0/MatrixElementKernels.o build.512z_d_inl0_hrd0/BridgeKernels.o build.512z_d_inl0_hrd0/CrossSectionKernels.o build.512z_d_inl0_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_d_inl0_hrd0/fcheck.exe build.512z_d_inl0_hrd0/fcheck_sa.o build.512z_d_inl0_hrd0/fsampler.o -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_d_inl0_hrd0'  -lgfortran -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_ll_ll_cpp build.512z_d_inl0_hrd0/RandomNumberKernels.o build.512z_d_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl0_hrd0/gcheck.exe build.512z_d_inl0_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl0_hrd0'  -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_ll_ll_cuda build.512z_d_inl0_hrd0/gRandomNumberKernels.o build.512z_d_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl0_hrd0/fgcheck.exe build.512z_d_inl0_hrd0/fcheck_sa.o build.512z_d_inl0_hrd0/fsampler_cu.o -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl0_hrd0'  -lgfortran -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_ll_ll_cuda build.512z_d_inl0_hrd0/gRandomNumberKernels.o build.512z_d_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_d_inl0_hrd0/check.exe build.512z_d_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_d_inl0_hrd0'  -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_ll_ll_cpp build.512z_d_inl0_hrd0/RandomNumberKernels.o build.512z_d_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl0_hrd0/runTest.exe build.512z_d_inl0_hrd0/CPPProcess.o build.512z_d_inl0_hrd0/MatrixElementKernels.o build.512z_d_inl0_hrd0/BridgeKernels.o build.512z_d_inl0_hrd0/CrossSectionKernels.o build.512z_d_inl0_hrd0/RandomNumberKernels.o build.512z_d_inl0_hrd0/RamboSamplingKernels.o build.512z_d_inl0_hrd0/testxxx.o  build.512z_d_inl0_hrd0/testmisc.o  build.512z_d_inl0_hrd0/runTest.o build.512z_d_inl0_hrd0/gCPPProcess.o build.512z_d_inl0_hrd0/gMatrixElementKernels.o build.512z_d_inl0_hrd0/gBridgeKernels.o build.512z_d_inl0_hrd0/gCrossSectionKernels.o build.512z_d_inl0_hrd0/gRandomNumberKernels.o build.512z_d_inl0_hrd0/gRamboSamplingKernels.o build.512z_d_inl0_hrd0/testxxx_cu.o  build.512z_d_inl0_hrd0/testmisc_cu.o  build.512z_d_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl0_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
 touch build.512z_d_inl0_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_d_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.512z_d_inl0_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_d_inl0_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_d_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512z_d_inl0_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_d_inl0_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.512z_d_inl0_hrd0/libmg5amc_ll_ll_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_d_inl0_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512z_d_inl0_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_d_inl0_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:00:01
+DATE: 2022-09-24_23:45:38
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512z_d_inl0_hrd0/check.exe -p 2048 256 24 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512z_d_inl0_hrd0/check.exe -p 2048 256 24 OMP=
 Process                     = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.2.0] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 1.891430e+06                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 4.743013e+06                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 4.743013e+06                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 1.934670e+06                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 4.919846e+06                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 4.919846e+06                 )  sec^-1
 MeanMatrixElemValue         = ( 1.371952e-02 +- 2.312385e-06 )  GeV^0
-TOTAL       :     7.565296 sec
-real	0m7.586s
+TOTAL       :     7.409181 sec
+real	0m7.426s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2:  280) (512y:    0) (512z:  740)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512z_d_inl0_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512z_d_inl0_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512z_d_inl0_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512z_d_inl0_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 1.282804e-02
 Avg ME (F77/C++)    = 1.2828039868165088E-002
 Relative difference = 1.0277089312025782e-08
@@ -1814,13 +1831,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:00:11 CEST 2022 Will execute './throughputX.sh -makej -eemumu -512zonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:46:00 CEST 2022 Will execute './throughputX.sh -makej -eemumu -512zonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -512zonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
 CUDACPP_BUILDDIR='build.512z_d_inl1_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -1830,22 +1847,18 @@ HELINL=1
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.512z_d_inl1_hrd0 for tag=512z_d_inl1_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.512z_d_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.512z_d_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.512z_d_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.512z_d_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512z_d_inl1_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512z_d_inl1_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512z_d_inl1_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512z_d_inl1_hrd0/fbridge_cu.o
 AVX=512z
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.512z_d_inl1_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512z_d_inl1_hrd0/gMatrixElementKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512z_d_inl1_hrd0/gBridgeKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512z_d_inl1_hrd0/gCrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.512z_d_inl1_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.512z_d_inl1_hrd0/read_slha.o
-mkdir -p ../lib/build.512z_d_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512z_d_inl1_hrd0/fbridge_cu.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512z_d_inl1_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512z_d_inl1_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512z_d_inl1_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512z_d_inl1_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.512z_d_inl1_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.512z_d_inl1_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.512z_d_inl1_hrd0/MatrixElementKernels.o
@@ -1855,46 +1868,51 @@ ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.512z_d_inl1_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.512z_d_inl1_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.512z_d_inl1_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512z_d_inl1_hrd0/testxxx_cu.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512z_d_inl1_hrd0/testxxx_cu.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.512z_d_inl1_hrd0/Parameters_sm.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.512z_d_inl1_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.512z_d_inl1_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512z_d_inl1_hrd0/testmisc_cu.o
+mkdir -p ../lib/build.512z_d_inl1_hrd0
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512z_d_inl1_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.512z_d_inl1_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.512z_d_inl1_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.512z_d_inl1_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.512z_d_inl1_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512z_d_inl1_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512z_d_inl1_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.512z_d_inl1_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.512z_d_inl1_hrd0/libmg5amc_common.so build.512z_d_inl1_hrd0/Parameters_sm.o build.512z_d_inl1_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512z_d_inl1_hrd0/libmg5amc_ll_ll_cuda.so build.512z_d_inl1_hrd0/gCPPProcess.o build.512z_d_inl1_hrd0/gMatrixElementKernels.o build.512z_d_inl1_hrd0/gBridgeKernels.o build.512z_d_inl1_hrd0/gCrossSectionKernels.o build.512z_d_inl1_hrd0/fbridge_cu.o -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512z_d_inl1_hrd0/libmg5amc_ll_ll_cpp.so build.512z_d_inl1_hrd0/CPPProcess.o build.512z_d_inl1_hrd0/MatrixElementKernels.o build.512z_d_inl1_hrd0/BridgeKernels.o build.512z_d_inl1_hrd0/CrossSectionKernels.o build.512z_d_inl1_hrd0/fbridge.o -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl1_hrd0/runTest.exe build.512z_d_inl1_hrd0/CPPProcess.o build.512z_d_inl1_hrd0/MatrixElementKernels.o build.512z_d_inl1_hrd0/BridgeKernels.o build.512z_d_inl1_hrd0/CrossSectionKernels.o build.512z_d_inl1_hrd0/RandomNumberKernels.o build.512z_d_inl1_hrd0/RamboSamplingKernels.o build.512z_d_inl1_hrd0/testxxx.o  build.512z_d_inl1_hrd0/testmisc.o  build.512z_d_inl1_hrd0/runTest.o build.512z_d_inl1_hrd0/gCPPProcess.o build.512z_d_inl1_hrd0/gMatrixElementKernels.o build.512z_d_inl1_hrd0/gBridgeKernels.o build.512z_d_inl1_hrd0/gCrossSectionKernels.o build.512z_d_inl1_hrd0/gRandomNumberKernels.o build.512z_d_inl1_hrd0/gRamboSamplingKernels.o build.512z_d_inl1_hrd0/testxxx_cu.o  build.512z_d_inl1_hrd0/testmisc_cu.o  build.512z_d_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_d_inl1_hrd0/check.exe build.512z_d_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_ll_ll_cpp build.512z_d_inl1_hrd0/RandomNumberKernels.o build.512z_d_inl1_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_d_inl1_hrd0/fcheck.exe build.512z_d_inl1_hrd0/fcheck_sa.o build.512z_d_inl1_hrd0/fsampler.o -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_ll_ll_cpp build.512z_d_inl1_hrd0/RandomNumberKernels.o build.512z_d_inl1_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl1_hrd0/gcheck.exe build.512z_d_inl1_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_ll_ll_cuda build.512z_d_inl1_hrd0/gRandomNumberKernels.o build.512z_d_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl1_hrd0/fgcheck.exe build.512z_d_inl1_hrd0/fcheck_sa.o build.512z_d_inl1_hrd0/fsampler_cu.o -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_ll_ll_cuda build.512z_d_inl1_hrd0/gRandomNumberKernels.o build.512z_d_inl1_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512z_d_inl1_hrd0/libmg5amc_ll_ll_cuda.so build.512z_d_inl1_hrd0/gCPPProcess.o build.512z_d_inl1_hrd0/gMatrixElementKernels.o build.512z_d_inl1_hrd0/gBridgeKernels.o build.512z_d_inl1_hrd0/gCrossSectionKernels.o build.512z_d_inl1_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl1_hrd0/gcheck.exe build.512z_d_inl1_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl1_hrd0'  -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_ll_ll_cuda build.512z_d_inl1_hrd0/gRandomNumberKernels.o build.512z_d_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl1_hrd0/fgcheck.exe build.512z_d_inl1_hrd0/fcheck_sa.o build.512z_d_inl1_hrd0/fsampler_cu.o -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl1_hrd0'  -lgfortran -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_ll_ll_cuda build.512z_d_inl1_hrd0/gRandomNumberKernels.o build.512z_d_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512z_d_inl1_hrd0/libmg5amc_ll_ll_cpp.so build.512z_d_inl1_hrd0/CPPProcess.o build.512z_d_inl1_hrd0/MatrixElementKernels.o build.512z_d_inl1_hrd0/BridgeKernels.o build.512z_d_inl1_hrd0/CrossSectionKernels.o build.512z_d_inl1_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_d_inl1_hrd0/fcheck.exe build.512z_d_inl1_hrd0/fcheck_sa.o build.512z_d_inl1_hrd0/fsampler.o -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_d_inl1_hrd0'  -lgfortran -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_ll_ll_cpp build.512z_d_inl1_hrd0/RandomNumberKernels.o build.512z_d_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_d_inl1_hrd0/check.exe build.512z_d_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_d_inl1_hrd0'  -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_ll_ll_cpp build.512z_d_inl1_hrd0/RandomNumberKernels.o build.512z_d_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl1_hrd0/runTest.exe build.512z_d_inl1_hrd0/CPPProcess.o build.512z_d_inl1_hrd0/MatrixElementKernels.o build.512z_d_inl1_hrd0/BridgeKernels.o build.512z_d_inl1_hrd0/CrossSectionKernels.o build.512z_d_inl1_hrd0/RandomNumberKernels.o build.512z_d_inl1_hrd0/RamboSamplingKernels.o build.512z_d_inl1_hrd0/testxxx.o  build.512z_d_inl1_hrd0/testmisc.o  build.512z_d_inl1_hrd0/runTest.o build.512z_d_inl1_hrd0/gCPPProcess.o build.512z_d_inl1_hrd0/gMatrixElementKernels.o build.512z_d_inl1_hrd0/gBridgeKernels.o build.512z_d_inl1_hrd0/gCrossSectionKernels.o build.512z_d_inl1_hrd0/gRandomNumberKernels.o build.512z_d_inl1_hrd0/gRamboSamplingKernels.o build.512z_d_inl1_hrd0/testxxx_cu.o  build.512z_d_inl1_hrd0/testmisc_cu.o  build.512z_d_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl1_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
 touch build.512z_d_inl1_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_d_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.512z_d_inl1_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_d_inl1_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_d_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512z_d_inl1_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_d_inl1_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.512z_d_inl1_hrd0/libmg5amc_ll_ll_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_d_inl1_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512z_d_inl1_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_d_inl1_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:00:12
+DATE: 2022-09-24_23:46:08
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512z_d_inl1_hrd0/check.exe -p 2048 256 24 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512z_d_inl1_hrd0/check.exe -p 2048 256 24 OMP=
 Process                     = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.2.0] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 2.302897e+06                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 8.547101e+06                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 8.547101e+06                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 2.364528e+06                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 9.140349e+06                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 9.140349e+06                 )  sec^-1
 MeanMatrixElemValue         = ( 1.371952e-02 +- 2.312385e-06 )  GeV^0
-TOTAL       :     6.375592 sec
-real	0m6.395s
+TOTAL       :     6.226075 sec
+real	0m6.243s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2:  247) (512y:    0) (512z:  269)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512z_d_inl1_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512z_d_inl1_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512z_d_inl1_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512z_d_inl1_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 1.282804e-02
 Avg ME (F77/C++)    = 1.2828039868165088E-002
 Relative difference = 1.0277089312025782e-08
@@ -1902,13 +1920,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:00:21 CEST 2022 Will execute './throughputX.sh -makej -eemumu -512zonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:46:30 CEST 2022 Will execute './throughputX.sh -makej -eemumu -512zonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -512zonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
 CUDACPP_BUILDDIR='build.512z_f_inl0_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -1918,72 +1936,72 @@ HELINL=0
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.512z_f_inl0_hrd0 for tag=512z_f_inl0_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.512z_f_inl0_hrd0
-mkdir -p build.512z_f_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gcheck_sa.cu -o build.512z_f_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gcheck_sa.cu -o build.512z_f_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gCPPProcess.cu -o build.512z_f_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512z_f_inl0_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512z_f_inl0_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512z_f_inl0_hrd0/gCrossSectionKernels.o
 AVX=512z
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gCPPProcess.cu -o build.512z_f_inl0_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512z_f_inl0_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512z_f_inl0_hrd0/gBridgeKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512z_f_inl0_hrd0/gCrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -c Parameters_sm.cc -o build.512z_f_inl0_hrd0/Parameters_sm.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512z_f_inl0_hrd0/fbridge_cu.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -c read_slha.cc -o build.512z_f_inl0_hrd0/read_slha.o
-mkdir -p ../lib/build.512z_f_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512z_f_inl0_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512z_f_inl0_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512z_f_inl0_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512z_f_inl0_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512z_f_inl0_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.512z_f_inl0_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.512z_f_inl0_hrd0/CPPProcess.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.512z_f_inl0_hrd0/MatrixElementKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -c Parameters_sm.cc -o build.512z_f_inl0_hrd0/Parameters_sm.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.512z_f_inl0_hrd0/BridgeKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -c read_slha.cc -o build.512z_f_inl0_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.512z_f_inl0_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.512z_f_inl0_hrd0/fbridge.o
+mkdir -p ../lib/build.512z_f_inl0_hrd0
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.512z_f_inl0_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.512z_f_inl0_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.512z_f_inl0_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512z_f_inl0_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512z_f_inl0_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.512z_f_inl0_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512z_f_inl0_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512z_f_inl0_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.512z_f_inl0_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu runTest.cc -o build.512z_f_inl0_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu runTest.cc -o build.512z_f_inl0_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.512z_f_inl0_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512z_f_inl0_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512z_f_inl0_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.512z_f_inl0_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.512z_f_inl0_hrd0/libmg5amc_common.so build.512z_f_inl0_hrd0/Parameters_sm.o build.512z_f_inl0_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512z_f_inl0_hrd0/libmg5amc_ll_ll_cuda.so build.512z_f_inl0_hrd0/gCPPProcess.o build.512z_f_inl0_hrd0/gMatrixElementKernels.o build.512z_f_inl0_hrd0/gBridgeKernels.o build.512z_f_inl0_hrd0/gCrossSectionKernels.o build.512z_f_inl0_hrd0/fbridge_cu.o -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512z_f_inl0_hrd0/libmg5amc_ll_ll_cpp.so build.512z_f_inl0_hrd0/CPPProcess.o build.512z_f_inl0_hrd0/MatrixElementKernels.o build.512z_f_inl0_hrd0/BridgeKernels.o build.512z_f_inl0_hrd0/CrossSectionKernels.o build.512z_f_inl0_hrd0/fbridge.o -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl0_hrd0/runTest.exe build.512z_f_inl0_hrd0/CPPProcess.o build.512z_f_inl0_hrd0/MatrixElementKernels.o build.512z_f_inl0_hrd0/BridgeKernels.o build.512z_f_inl0_hrd0/CrossSectionKernels.o build.512z_f_inl0_hrd0/RandomNumberKernels.o build.512z_f_inl0_hrd0/RamboSamplingKernels.o build.512z_f_inl0_hrd0/testxxx.o  build.512z_f_inl0_hrd0/testmisc.o  build.512z_f_inl0_hrd0/runTest.o build.512z_f_inl0_hrd0/gCPPProcess.o build.512z_f_inl0_hrd0/gMatrixElementKernels.o build.512z_f_inl0_hrd0/gBridgeKernels.o build.512z_f_inl0_hrd0/gCrossSectionKernels.o build.512z_f_inl0_hrd0/gRandomNumberKernels.o build.512z_f_inl0_hrd0/gRamboSamplingKernels.o build.512z_f_inl0_hrd0/testxxx_cu.o  build.512z_f_inl0_hrd0/testmisc_cu.o  build.512z_f_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_f_inl0_hrd0/check.exe build.512z_f_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_ll_ll_cpp build.512z_f_inl0_hrd0/RandomNumberKernels.o build.512z_f_inl0_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_f_inl0_hrd0/fcheck.exe build.512z_f_inl0_hrd0/fcheck_sa.o build.512z_f_inl0_hrd0/fsampler.o -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_ll_ll_cpp build.512z_f_inl0_hrd0/RandomNumberKernels.o build.512z_f_inl0_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl0_hrd0/gcheck.exe build.512z_f_inl0_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_ll_ll_cuda build.512z_f_inl0_hrd0/gRandomNumberKernels.o build.512z_f_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl0_hrd0/fgcheck.exe build.512z_f_inl0_hrd0/fcheck_sa.o build.512z_f_inl0_hrd0/fsampler_cu.o -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_ll_ll_cuda build.512z_f_inl0_hrd0/gRandomNumberKernels.o build.512z_f_inl0_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512z_f_inl0_hrd0/libmg5amc_ll_ll_cuda.so build.512z_f_inl0_hrd0/gCPPProcess.o build.512z_f_inl0_hrd0/gMatrixElementKernels.o build.512z_f_inl0_hrd0/gBridgeKernels.o build.512z_f_inl0_hrd0/gCrossSectionKernels.o build.512z_f_inl0_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512z_f_inl0_hrd0/libmg5amc_ll_ll_cpp.so build.512z_f_inl0_hrd0/CPPProcess.o build.512z_f_inl0_hrd0/MatrixElementKernels.o build.512z_f_inl0_hrd0/BridgeKernels.o build.512z_f_inl0_hrd0/CrossSectionKernels.o build.512z_f_inl0_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_f_inl0_hrd0/fcheck.exe build.512z_f_inl0_hrd0/fcheck_sa.o build.512z_f_inl0_hrd0/fsampler.o -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_f_inl0_hrd0'  -lgfortran -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_ll_ll_cpp build.512z_f_inl0_hrd0/RandomNumberKernels.o build.512z_f_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl0_hrd0/gcheck.exe build.512z_f_inl0_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl0_hrd0'  -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_ll_ll_cuda build.512z_f_inl0_hrd0/gRandomNumberKernels.o build.512z_f_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl0_hrd0/fgcheck.exe build.512z_f_inl0_hrd0/fcheck_sa.o build.512z_f_inl0_hrd0/fsampler_cu.o -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl0_hrd0'  -lgfortran -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_ll_ll_cuda build.512z_f_inl0_hrd0/gRandomNumberKernels.o build.512z_f_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_f_inl0_hrd0/check.exe build.512z_f_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_f_inl0_hrd0'  -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_ll_ll_cpp build.512z_f_inl0_hrd0/RandomNumberKernels.o build.512z_f_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl0_hrd0/runTest.exe build.512z_f_inl0_hrd0/CPPProcess.o build.512z_f_inl0_hrd0/MatrixElementKernels.o build.512z_f_inl0_hrd0/BridgeKernels.o build.512z_f_inl0_hrd0/CrossSectionKernels.o build.512z_f_inl0_hrd0/RandomNumberKernels.o build.512z_f_inl0_hrd0/RamboSamplingKernels.o build.512z_f_inl0_hrd0/testxxx.o  build.512z_f_inl0_hrd0/testmisc.o  build.512z_f_inl0_hrd0/runTest.o build.512z_f_inl0_hrd0/gCPPProcess.o build.512z_f_inl0_hrd0/gMatrixElementKernels.o build.512z_f_inl0_hrd0/gBridgeKernels.o build.512z_f_inl0_hrd0/gCrossSectionKernels.o build.512z_f_inl0_hrd0/gRandomNumberKernels.o build.512z_f_inl0_hrd0/gRamboSamplingKernels.o build.512z_f_inl0_hrd0/testxxx_cu.o  build.512z_f_inl0_hrd0/testmisc_cu.o  build.512z_f_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl0_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
 touch build.512z_f_inl0_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_f_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.512z_f_inl0_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_f_inl0_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_f_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512z_f_inl0_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_f_inl0_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.512z_f_inl0_hrd0/libmg5amc_ll_ll_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_f_inl0_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512z_f_inl0_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_f_inl0_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:00:22
+DATE: 2022-09-24_23:46:39
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512z_f_inl0_hrd0/check.exe -p 2048 256 24 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512z_f_inl0_hrd0/check.exe -p 2048 256 24 OMP=
 Process                     = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.2.0] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK
 FP precision                = FLOAT (NaN/abnormal=11, zero=0)
 Internal loops fptype_sv    = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 2.837604e+06                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 9.644016e+06                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 9.644016e+06                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 2.893179e+06                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 1.005686e+07                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 1.005686e+07                 )  sec^-1
 MeanMatrixElemValue         = ( 1.371954e-02 +- 2.312467e-06 )  GeV^0
-TOTAL       :     5.252193 sec
-real	0m5.265s
+TOTAL       :     5.160811 sec
+real	0m5.172s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2:  411) (512y:    0) (512z:  759)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512z_f_inl0_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512z_f_inl0_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512z_f_inl0_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512z_f_inl0_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 1.282805e-02
 Avg ME (F77/C++)    = 1.2828052580516669E-002
 Relative difference = 2.011620369740164e-07
@@ -1991,13 +2009,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:00:29 CEST 2022 Will execute './throughputX.sh -makej -eemumu -512zonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:46:59 CEST 2022 Will execute './throughputX.sh -makej -eemumu -512zonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -512zonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll
 CUDACPP_BUILDDIR='build.512z_f_inl1_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -2007,71 +2025,72 @@ HELINL=1
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.512z_f_inl1_hrd0 for tag=512z_f_inl1_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.512z_f_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.512z_f_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.512z_f_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.512z_f_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512z_f_inl1_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512z_f_inl1_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512z_f_inl1_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512z_f_inl1_hrd0/fbridge_cu.o
 AVX=512z
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.512z_f_inl1_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512z_f_inl1_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512z_f_inl1_hrd0/gBridgeKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512z_f_inl1_hrd0/gCrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.512z_f_inl1_hrd0/Parameters_sm.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512z_f_inl1_hrd0/fbridge_cu.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.512z_f_inl1_hrd0/read_slha.o
-mkdir -p ../lib/build.512z_f_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512z_f_inl1_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512z_f_inl1_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512z_f_inl1_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512z_f_inl1_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.512z_f_inl1_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.512z_f_inl1_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.512z_f_inl1_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.512z_f_inl1_hrd0/BridgeKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.512z_f_inl1_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.512z_f_inl1_hrd0/fbridge.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.512z_f_inl1_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.512z_f_inl1_hrd0/RandomNumberKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.512z_f_inl1_hrd0/Parameters_sm.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.512z_f_inl1_hrd0/RamboSamplingKernels.o
+mkdir -p ../lib/build.512z_f_inl1_hrd0
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.512z_f_inl1_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512z_f_inl1_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512z_f_inl1_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.512z_f_inl1_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512z_f_inl1_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512z_f_inl1_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.512z_f_inl1_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.512z_f_inl1_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.512z_f_inl1_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.512z_f_inl1_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512z_f_inl1_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512z_f_inl1_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.512z_f_inl1_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.512z_f_inl1_hrd0/libmg5amc_common.so build.512z_f_inl1_hrd0/Parameters_sm.o build.512z_f_inl1_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512z_f_inl1_hrd0/libmg5amc_ll_ll_cuda.so build.512z_f_inl1_hrd0/gCPPProcess.o build.512z_f_inl1_hrd0/gMatrixElementKernels.o build.512z_f_inl1_hrd0/gBridgeKernels.o build.512z_f_inl1_hrd0/gCrossSectionKernels.o build.512z_f_inl1_hrd0/fbridge_cu.o -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512z_f_inl1_hrd0/libmg5amc_ll_ll_cpp.so build.512z_f_inl1_hrd0/CPPProcess.o build.512z_f_inl1_hrd0/MatrixElementKernels.o build.512z_f_inl1_hrd0/BridgeKernels.o build.512z_f_inl1_hrd0/CrossSectionKernels.o build.512z_f_inl1_hrd0/fbridge.o -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl1_hrd0/runTest.exe build.512z_f_inl1_hrd0/CPPProcess.o build.512z_f_inl1_hrd0/MatrixElementKernels.o build.512z_f_inl1_hrd0/BridgeKernels.o build.512z_f_inl1_hrd0/CrossSectionKernels.o build.512z_f_inl1_hrd0/RandomNumberKernels.o build.512z_f_inl1_hrd0/RamboSamplingKernels.o build.512z_f_inl1_hrd0/testxxx.o  build.512z_f_inl1_hrd0/testmisc.o  build.512z_f_inl1_hrd0/runTest.o build.512z_f_inl1_hrd0/gCPPProcess.o build.512z_f_inl1_hrd0/gMatrixElementKernels.o build.512z_f_inl1_hrd0/gBridgeKernels.o build.512z_f_inl1_hrd0/gCrossSectionKernels.o build.512z_f_inl1_hrd0/gRandomNumberKernels.o build.512z_f_inl1_hrd0/gRamboSamplingKernels.o build.512z_f_inl1_hrd0/testxxx_cu.o  build.512z_f_inl1_hrd0/testmisc_cu.o  build.512z_f_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_f_inl1_hrd0/check.exe build.512z_f_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_ll_ll_cpp build.512z_f_inl1_hrd0/RandomNumberKernels.o build.512z_f_inl1_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_f_inl1_hrd0/fcheck.exe build.512z_f_inl1_hrd0/fcheck_sa.o build.512z_f_inl1_hrd0/fsampler.o -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_ll_ll_cpp build.512z_f_inl1_hrd0/RandomNumberKernels.o build.512z_f_inl1_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl1_hrd0/gcheck.exe build.512z_f_inl1_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_ll_ll_cuda build.512z_f_inl1_hrd0/gRandomNumberKernels.o build.512z_f_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl1_hrd0/fgcheck.exe build.512z_f_inl1_hrd0/fcheck_sa.o build.512z_f_inl1_hrd0/fsampler_cu.o -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_ll_ll_cuda build.512z_f_inl1_hrd0/gRandomNumberKernels.o build.512z_f_inl1_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512z_f_inl1_hrd0/libmg5amc_ll_ll_cuda.so build.512z_f_inl1_hrd0/gCPPProcess.o build.512z_f_inl1_hrd0/gMatrixElementKernels.o build.512z_f_inl1_hrd0/gBridgeKernels.o build.512z_f_inl1_hrd0/gCrossSectionKernels.o build.512z_f_inl1_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl1_hrd0/gcheck.exe build.512z_f_inl1_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl1_hrd0'  -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_ll_ll_cuda build.512z_f_inl1_hrd0/gRandomNumberKernels.o build.512z_f_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl1_hrd0/fgcheck.exe build.512z_f_inl1_hrd0/fcheck_sa.o build.512z_f_inl1_hrd0/fsampler_cu.o -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl1_hrd0'  -lgfortran -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_ll_ll_cuda build.512z_f_inl1_hrd0/gRandomNumberKernels.o build.512z_f_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512z_f_inl1_hrd0/libmg5amc_ll_ll_cpp.so build.512z_f_inl1_hrd0/CPPProcess.o build.512z_f_inl1_hrd0/MatrixElementKernels.o build.512z_f_inl1_hrd0/BridgeKernels.o build.512z_f_inl1_hrd0/CrossSectionKernels.o build.512z_f_inl1_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_f_inl1_hrd0/fcheck.exe build.512z_f_inl1_hrd0/fcheck_sa.o build.512z_f_inl1_hrd0/fsampler.o -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_f_inl1_hrd0'  -lgfortran -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_ll_ll_cpp build.512z_f_inl1_hrd0/RandomNumberKernels.o build.512z_f_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_f_inl1_hrd0/check.exe build.512z_f_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_f_inl1_hrd0'  -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_ll_ll_cpp build.512z_f_inl1_hrd0/RandomNumberKernels.o build.512z_f_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl1_hrd0/runTest.exe build.512z_f_inl1_hrd0/CPPProcess.o build.512z_f_inl1_hrd0/MatrixElementKernels.o build.512z_f_inl1_hrd0/BridgeKernels.o build.512z_f_inl1_hrd0/CrossSectionKernels.o build.512z_f_inl1_hrd0/RandomNumberKernels.o build.512z_f_inl1_hrd0/RamboSamplingKernels.o build.512z_f_inl1_hrd0/testxxx.o  build.512z_f_inl1_hrd0/testmisc.o  build.512z_f_inl1_hrd0/runTest.o build.512z_f_inl1_hrd0/gCPPProcess.o build.512z_f_inl1_hrd0/gMatrixElementKernels.o build.512z_f_inl1_hrd0/gBridgeKernels.o build.512z_f_inl1_hrd0/gCrossSectionKernels.o build.512z_f_inl1_hrd0/gRandomNumberKernels.o build.512z_f_inl1_hrd0/gRamboSamplingKernels.o build.512z_f_inl1_hrd0/testxxx_cu.o  build.512z_f_inl1_hrd0/testmisc_cu.o  build.512z_f_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl1_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll'
 touch build.512z_f_inl1_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_f_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.512z_f_inl1_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_f_inl1_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_f_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512z_f_inl1_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_f_inl1_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.512z_f_inl1_hrd0/libmg5amc_ll_ll_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_f_inl1_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512z_f_inl1_hrd0 -lmg5amc_common -lmg5amc_ll_ll_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_f_inl1_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:00:31
+DATE: 2022-09-24_23:47:09
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512z_f_inl1_hrd0/check.exe -p 2048 256 24 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512z_f_inl1_hrd0/check.exe -p 2048 256 24 OMP=
 Process                     = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.2.0] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK
 FP precision                = FLOAT (NaN/abnormal=11, zero=0)
 Internal loops fptype_sv    = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 3.289719e+06                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 1.831693e+07                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 1.831693e+07                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 3.348563e+06                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 2.054445e+07                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 2.054445e+07                 )  sec^-1
 MeanMatrixElemValue         = ( 1.371954e-02 +- 2.312467e-06 )  GeV^0
-TOTAL       :     4.642386 sec
-real	0m4.655s
+TOTAL       :     4.571934 sec
+real	0m4.584s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2:  375) (512y:    0) (512z:  297)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512z_f_inl1_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512z_f_inl1_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512z_f_inl1_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_ll_ll/build.512z_f_inl1_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 1.282805e-02
 Avg ME (F77/C++)    = 1.2828052556869807E-002
 Relative difference = 1.9931866543694755e-07
@@ -2079,12 +2098,12 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:00:37 CEST 2022 Will execute './throughputX.sh -makej -ggtt -nocpp  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:47:28 CEST 2022 Will execute './throughputX.sh -makej -ggtt -nocpp  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
 CUDACPP_BUILDDIR='build.none_d_inl0_hrd0'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -w -cpp  -c myamp.f -I../../Source/ -fopenmp -o myamp.o
 cd ../../Source; make
@@ -2103,7 +2122,7 @@ ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfort
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -std=c++11 -Wall -Wshadow -Wextra -c counters.cpp -o counters.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -w -cpp  -c -DMG5AMC_MEEXPORTER_CUDACPP auto_dsig1.f -I../../Source/ -fopenmp -o auto_dsig1_cudacpp.o
 make -f cudacpp.mk
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/Source'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/Source'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o StringCast.o StringCast.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o ranmar.o ranmar.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o alfas_functions.o alfas_functions.f
@@ -2122,45 +2141,45 @@ ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfort
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o dgauss.o dgauss.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o readgrid.o readgrid.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o getissud.o getissud.f
+OMPFLAGS=
+AVX=none
 cd DHELAS; make
 cd PDF; make	
 cd MODEL; make    
 cd CERNLIB; make
-OMPFLAGS=
-AVX=none
+cd BIAS/dummy; make
 FPTYPE=d
 HELINL=0
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.none_d_inl0_hrd0 for tag=none_d_inl0_hrd0_hasCurand (USEBUILDDIR is set = 1)
-cd BIAS/dummy; make
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/Source/BIAS/dummy'
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o dummy.o dummy.f
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/Source/DHELAS'
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/Source/CERNLIB'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o abend.o abend.f
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/Source/DHELAS'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o aloha_functions.o aloha_functions.f
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/Source/MODEL'
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/Source/PDF'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o Ctq6Pdf.o Ctq6Pdf.f
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/Source/MODEL'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o couplings.o couplings.f
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/Source/CERNLIB'
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o abend.o abend.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o lha_read.o lha_read.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o FFV1_1.o FFV1_1.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o pdfwrap.o pdfwrap.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o dlsqp2.o dlsqp2.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o printout.o printout.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o lha_read.o lha_read.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o FFV1_0.o FFV1_0.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o lenocc.o lenocc.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o mtlprt.o mtlprt.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o FFV1_2.o FFV1_2.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o printout.o printout.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o mtlprt.o mtlprt.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o opendata.o opendata.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I.. -c -o rw_para.o rw_para.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o VVV1P0_1.o VVV1P0_1.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o mtlset.o mtlset.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o radmul.o radmul.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o model_functions.o model_functions.f
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/Source/BIAS/dummy'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o dummy.o dummy.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o radmul.o radmul.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o couplings1.o couplings1.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o couplings2.o couplings2.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o VVV1P0_1.o VVV1P0_1.f
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/Source/PDF'
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o Ctq6Pdf.o Ctq6Pdf.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o pdfwrap.o pdfwrap.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o opendata.o opendata.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o pdf.o pdf.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o PhotonFlux.o PhotonFlux.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o pdg2pdf.o pdg2pdf.f
@@ -2168,83 +2187,85 @@ ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfort
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o eepdf.o eepdf.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o gridpdfaux.o gridpdfaux.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o dfint.o dfint.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o DiscreteSampler.o DiscreteSampler.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o kerset.o kerset.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o ElectroweakFluxDriver.o ElectroweakFluxDriver.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o ElectroweakFlux.o ElectroweakFlux.f
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
+ar cru  ../../../lib/libbias.a  dummy.o
+ranlib  ../../../lib/libbias.a
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/Source/BIAS/dummy'
+ar cru  ../../lib/libcernlib.a  abend.o dlsqp2.o lenocc.o mtlprt.o mtlset.o radmul.o
+ranlib  ../../lib/libcernlib.a
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/Source/CERNLIB'
+ar cru  ../../lib/libmodel.a  couplings.o lha_read.o printout.o rw_para.o model_functions.o couplings1.o couplings2.o
+ranlib  ../../lib/libmodel.a
+ar cru  ../lib/libgeneric.a  alfas_functions.o transpole.o invarients.o hfill.o pawgraphs.o ran1.o rw_events.o rw_routines.o kin_functions.o open_file.o basecode.o setrun.o run_printout.o dgauss.o readgrid.o getissud.o
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/Source/MODEL'
+ranlib  ../lib/libgeneric.a
+ar cru  ../../lib/libpdf.a  Ctq6Pdf.o pdfwrap.o opendata.o pdf.o PhotonFlux.o pdg2pdf.o NNPDFDriver.o eepdf.o gridpdfaux.o dfint.o kerset.o ElectroweakFluxDriver.o ElectroweakFlux.o
+ranlib  ../../lib/libpdf.a
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/Source/PDF'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
+mkdir -p build.none_d_inl0_hrd0
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.none_d_inl0_hrd0
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gcheck_sa.cu -o build.none_d_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gCPPProcess.cu -o build.none_d_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.none_d_inl0_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gBridgeKernels.cu -o build.none_d_inl0_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.none_d_inl0_hrd0/gCrossSectionKernels.o
 AVX=none
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gcheck_sa.cu -o build.none_d_inl0_hrd0/gcheck_sa.o
-ar cru  ../../../lib/libbias.a  dummy.o
-ranlib  ../../../lib/libbias.a
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -c Parameters_sm.cc -o build.none_d_inl0_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -c read_slha.cc -o build.none_d_inl0_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/Source/BIAS/dummy'
-mkdir -p ../lib/build.none_d_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gCPPProcess.cu -o build.none_d_inl0_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.none_d_inl0_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gBridgeKernels.cu -o build.none_d_inl0_hrd0/gBridgeKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.none_d_inl0_hrd0/gCrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o DiscreteSampler.o DiscreteSampler.f
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fbridge.cc -o build.none_d_inl0_hrd0/fbridge_cu.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.none_d_inl0_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.none_d_inl0_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fbridge.cc -o build.none_d_inl0_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.none_d_inl0_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.none_d_inl0_hrd0/gRamboSamplingKernels.o
+ar cru  ../../lib/libdhelas.a  aloha_functions.o FFV1_1.o FFV1_0.o FFV1_2.o VVV1P0_1.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.none_d_inl0_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.none_d_inl0_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.none_d_inl0_hrd0/MatrixElementKernels.o
+ranlib  ../../lib/libdhelas.a
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/Source/DHELAS'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.none_d_inl0_hrd0/BridgeKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -c Parameters_sm.cc -o build.none_d_inl0_hrd0/Parameters_sm.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -c read_slha.cc -o build.none_d_inl0_hrd0/read_slha.o
+mkdir -p ../lib/build.none_d_inl0_hrd0
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.none_d_inl0_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.none_d_inl0_hrd0/fbridge.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.none_d_inl0_hrd0/libmg5amc_common.so build.none_d_inl0_hrd0/Parameters_sm.o build.none_d_inl0_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.none_d_inl0_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.none_d_inl0_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.none_d_inl0_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testxxx.cc -o build.none_d_inl0_hrd0/testxxx_cu.o
-ar cru  ../../lib/libmodel.a  couplings.o lha_read.o printout.o rw_para.o model_functions.o couplings1.o couplings2.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testxxx.cc -o build.none_d_inl0_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.none_d_inl0_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testmisc.cc -o build.none_d_inl0_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testmisc.cc -o build.none_d_inl0_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.none_d_inl0_hrd0/runTest.o
-ranlib  ../../lib/libmodel.a
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu runTest.cc -o build.none_d_inl0_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu runTest.cc -o build.none_d_inl0_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.none_d_inl0_hrd0/fcheck_sa.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/Source/MODEL'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fsampler.cc -o build.none_d_inl0_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fsampler.cc -o build.none_d_inl0_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.none_d_inl0_hrd0/fsampler.o
-ar cru  ../../lib/libcernlib.a  abend.o dlsqp2.o lenocc.o mtlprt.o mtlset.o radmul.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
-ranlib  ../../lib/libcernlib.a
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/Source/CERNLIB'
-ar cru  ../lib/libgeneric.a  alfas_functions.o transpole.o invarients.o hfill.o pawgraphs.o ran1.o rw_events.o rw_routines.o kin_functions.o open_file.o basecode.o setrun.o run_printout.o dgauss.o readgrid.o getissud.o
-ranlib  ../lib/libgeneric.a
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.none_d_inl0_hrd0/libmg5amc_gg_ttx_cpp.so build.none_d_inl0_hrd0/CPPProcess.o build.none_d_inl0_hrd0/MatrixElementKernels.o build.none_d_inl0_hrd0/BridgeKernels.o build.none_d_inl0_hrd0/CrossSectionKernels.o build.none_d_inl0_hrd0/fbridge.o -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common
-ar cru  ../../lib/libpdf.a  Ctq6Pdf.o pdfwrap.o opendata.o pdf.o PhotonFlux.o pdg2pdf.o NNPDFDriver.o eepdf.o gridpdfaux.o dfint.o kerset.o ElectroweakFluxDriver.o ElectroweakFlux.o
-ranlib  ../../lib/libpdf.a
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/Source/PDF'
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_d_inl0_hrd0/check.exe build.none_d_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_gg_ttx_cpp build.none_d_inl0_hrd0/RandomNumberKernels.o build.none_d_inl0_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_d_inl0_hrd0/fcheck.exe build.none_d_inl0_hrd0/fcheck_sa.o build.none_d_inl0_hrd0/fsampler.o -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_gg_ttx_cpp build.none_d_inl0_hrd0/RandomNumberKernels.o build.none_d_inl0_hrd0/RamboSamplingKernels.o
-ar cru  ../../lib/libdhelas.a  aloha_functions.o FFV1_1.o FFV1_0.o FFV1_2.o VVV1P0_1.o
-ranlib  ../../lib/libdhelas.a
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/Source/DHELAS'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o dsample.o dsample.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.none_d_inl0_hrd0/libmg5amc_common.so build.none_d_inl0_hrd0/Parameters_sm.o build.none_d_inl0_hrd0/read_slha.o
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.none_d_inl0_hrd0/libmg5amc_gg_ttx_cpp.so build.none_d_inl0_hrd0/CPPProcess.o build.none_d_inl0_hrd0/MatrixElementKernels.o build.none_d_inl0_hrd0/BridgeKernels.o build.none_d_inl0_hrd0/CrossSectionKernels.o build.none_d_inl0_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_d_inl0_hrd0/check.exe build.none_d_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_d_inl0_hrd0'  -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_gg_ttx_cpp build.none_d_inl0_hrd0/RandomNumberKernels.o build.none_d_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_d_inl0_hrd0/fcheck.exe build.none_d_inl0_hrd0/fcheck_sa.o build.none_d_inl0_hrd0/fsampler.o -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_d_inl0_hrd0'  -lgfortran -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_gg_ttx_cpp build.none_d_inl0_hrd0/RandomNumberKernels.o build.none_d_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
 ar cru  ../lib/libdsample.a  dsample.o ranmar.o DiscreteSampler.o StringCast.o
 ranlib  ../lib/libdsample.a
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/Source'
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/Source'
 touch .libs
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -w -cpp  -c genps.f -I../../Source/ -fopenmp -o genps.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -w -cpp  -c driver.f -I../../Source/ -fopenmp -o driver.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -w -cpp  -c auto_dsig.f -I../../Source/ -fopenmp -o auto_dsig.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -w -cpp   -c matrix1.f -I../../Source/ -fopenmp
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -w -cpp  -c -DMG5AMC_MEEXPORTER_CUDACPP driver.f -I../../Source/ -fopenmp -o driver_cudacpp.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o madevent myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver.o  auto_dsig1.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.none_d_inl0_hrd0/libmg5amc_gg_ttx_cuda.so build.none_d_inl0_hrd0/gCPPProcess.o build.none_d_inl0_hrd0/gMatrixElementKernels.o build.none_d_inl0_hrd0/gBridgeKernels.o build.none_d_inl0_hrd0/gCrossSectionKernels.o build.none_d_inl0_hrd0/fbridge_cu.o -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl0_hrd0/fgcheck.exe build.none_d_inl0_hrd0/fcheck_sa.o build.none_d_inl0_hrd0/fsampler_cu.o -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_gg_ttx_cuda build.none_d_inl0_hrd0/gRandomNumberKernels.o build.none_d_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl0_hrd0/gcheck.exe build.none_d_inl0_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_gg_ttx_cuda build.none_d_inl0_hrd0/gRandomNumberKernels.o build.none_d_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl0_hrd0/runTest.exe build.none_d_inl0_hrd0/CPPProcess.o build.none_d_inl0_hrd0/MatrixElementKernels.o build.none_d_inl0_hrd0/BridgeKernels.o build.none_d_inl0_hrd0/CrossSectionKernels.o build.none_d_inl0_hrd0/RandomNumberKernels.o build.none_d_inl0_hrd0/RamboSamplingKernels.o build.none_d_inl0_hrd0/testxxx.o  build.none_d_inl0_hrd0/testmisc.o  build.none_d_inl0_hrd0/runTest.o build.none_d_inl0_hrd0/gCPPProcess.o build.none_d_inl0_hrd0/gMatrixElementKernels.o build.none_d_inl0_hrd0/gBridgeKernels.o build.none_d_inl0_hrd0/gCrossSectionKernels.o build.none_d_inl0_hrd0/gRandomNumberKernels.o build.none_d_inl0_hrd0/gRamboSamplingKernels.o build.none_d_inl0_hrd0/testxxx_cu.o  build.none_d_inl0_hrd0/testmisc_cu.o  build.none_d_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o madevent myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver.o  auto_dsig1.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -lstdc++  -Wl,--no-relax 
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.none_d_inl0_hrd0/libmg5amc_gg_ttx_cuda.so build.none_d_inl0_hrd0/gCPPProcess.o build.none_d_inl0_hrd0/gMatrixElementKernels.o build.none_d_inl0_hrd0/gBridgeKernels.o build.none_d_inl0_hrd0/gCrossSectionKernels.o build.none_d_inl0_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl0_hrd0/gcheck.exe build.none_d_inl0_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl0_hrd0'  -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_gg_ttx_cuda build.none_d_inl0_hrd0/gRandomNumberKernels.o build.none_d_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl0_hrd0/fgcheck.exe build.none_d_inl0_hrd0/fcheck_sa.o build.none_d_inl0_hrd0/fsampler_cu.o -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl0_hrd0'  -lgfortran -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_gg_ttx_cuda build.none_d_inl0_hrd0/gRandomNumberKernels.o build.none_d_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl0_hrd0/runTest.exe build.none_d_inl0_hrd0/CPPProcess.o build.none_d_inl0_hrd0/MatrixElementKernels.o build.none_d_inl0_hrd0/BridgeKernels.o build.none_d_inl0_hrd0/CrossSectionKernels.o build.none_d_inl0_hrd0/RandomNumberKernels.o build.none_d_inl0_hrd0/RamboSamplingKernels.o build.none_d_inl0_hrd0/testxxx.o  build.none_d_inl0_hrd0/testmisc.o  build.none_d_inl0_hrd0/runTest.o build.none_d_inl0_hrd0/gCPPProcess.o build.none_d_inl0_hrd0/gMatrixElementKernels.o build.none_d_inl0_hrd0/gBridgeKernels.o build.none_d_inl0_hrd0/gCrossSectionKernels.o build.none_d_inl0_hrd0/gRandomNumberKernels.o build.none_d_inl0_hrd0/gRamboSamplingKernels.o build.none_d_inl0_hrd0/testxxx_cu.o  build.none_d_inl0_hrd0/testmisc_cu.o  build.none_d_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl0_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
 touch build.none_d_inl0_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_d_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.none_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.none_d_inl0_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_d_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.none_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.none_d_inl0_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.none_d_inl0_hrd0/libmg5amc_gg_ttx_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_d_inl0_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.none_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.none_d_inl0_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
 CUDACPP_BUILDDIR='build.512y_d_inl0_hrd0'
 make -f cudacpp.mk
@@ -2255,71 +2276,72 @@ HELINL=0
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.512y_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.512y_d_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gcheck_sa.cu -o build.512y_d_inl0_hrd0/gcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gCPPProcess.cu -o build.512y_d_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gcheck_sa.cu -o build.512y_d_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gCPPProcess.cu -o build.512y_d_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512y_d_inl0_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512y_d_inl0_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512y_d_inl0_hrd0/gCrossSectionKernels.o
 AVX=512y
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512y_d_inl0_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512y_d_inl0_hrd0/gBridgeKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512y_d_inl0_hrd0/gCrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -c Parameters_sm.cc -o build.512y_d_inl0_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -c read_slha.cc -o build.512y_d_inl0_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512y_d_inl0_hrd0/fbridge_cu.o
-mkdir -p ../lib/build.512y_d_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512y_d_inl0_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512y_d_inl0_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512y_d_inl0_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512y_d_inl0_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512y_d_inl0_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.512y_d_inl0_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.512y_d_inl0_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.512y_d_inl0_hrd0/MatrixElementKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.512y_d_inl0_hrd0/BridgeKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.512y_d_inl0_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.512y_d_inl0_hrd0/fbridge.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -c read_slha.cc -o build.512y_d_inl0_hrd0/read_slha.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -c Parameters_sm.cc -o build.512y_d_inl0_hrd0/Parameters_sm.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.512y_d_inl0_hrd0/RandomNumberKernels.o
+mkdir -p ../lib/build.512y_d_inl0_hrd0
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.512y_d_inl0_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.512y_d_inl0_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512y_d_inl0_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512y_d_inl0_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.512y_d_inl0_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512y_d_inl0_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512y_d_inl0_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.512y_d_inl0_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu runTest.cc -o build.512y_d_inl0_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu runTest.cc -o build.512y_d_inl0_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.512y_d_inl0_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512y_d_inl0_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512y_d_inl0_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.512y_d_inl0_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.512y_d_inl0_hrd0/libmg5amc_common.so build.512y_d_inl0_hrd0/Parameters_sm.o build.512y_d_inl0_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512y_d_inl0_hrd0/libmg5amc_gg_ttx_cuda.so build.512y_d_inl0_hrd0/gCPPProcess.o build.512y_d_inl0_hrd0/gMatrixElementKernels.o build.512y_d_inl0_hrd0/gBridgeKernels.o build.512y_d_inl0_hrd0/gCrossSectionKernels.o build.512y_d_inl0_hrd0/fbridge_cu.o -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512y_d_inl0_hrd0/libmg5amc_gg_ttx_cpp.so build.512y_d_inl0_hrd0/CPPProcess.o build.512y_d_inl0_hrd0/MatrixElementKernels.o build.512y_d_inl0_hrd0/BridgeKernels.o build.512y_d_inl0_hrd0/CrossSectionKernels.o build.512y_d_inl0_hrd0/fbridge.o -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl0_hrd0/gcheck.exe build.512y_d_inl0_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_gg_ttx_cuda build.512y_d_inl0_hrd0/gRandomNumberKernels.o build.512y_d_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl0_hrd0/fgcheck.exe build.512y_d_inl0_hrd0/fcheck_sa.o build.512y_d_inl0_hrd0/fsampler_cu.o -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_gg_ttx_cuda build.512y_d_inl0_hrd0/gRandomNumberKernels.o build.512y_d_inl0_hrd0/gRamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_d_inl0_hrd0/check.exe build.512y_d_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_gg_ttx_cpp build.512y_d_inl0_hrd0/RandomNumberKernels.o build.512y_d_inl0_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl0_hrd0/runTest.exe build.512y_d_inl0_hrd0/CPPProcess.o build.512y_d_inl0_hrd0/MatrixElementKernels.o build.512y_d_inl0_hrd0/BridgeKernels.o build.512y_d_inl0_hrd0/CrossSectionKernels.o build.512y_d_inl0_hrd0/RandomNumberKernels.o build.512y_d_inl0_hrd0/RamboSamplingKernels.o build.512y_d_inl0_hrd0/testxxx.o  build.512y_d_inl0_hrd0/testmisc.o  build.512y_d_inl0_hrd0/runTest.o build.512y_d_inl0_hrd0/gCPPProcess.o build.512y_d_inl0_hrd0/gMatrixElementKernels.o build.512y_d_inl0_hrd0/gBridgeKernels.o build.512y_d_inl0_hrd0/gCrossSectionKernels.o build.512y_d_inl0_hrd0/gRandomNumberKernels.o build.512y_d_inl0_hrd0/gRamboSamplingKernels.o build.512y_d_inl0_hrd0/testxxx_cu.o  build.512y_d_inl0_hrd0/testmisc_cu.o  build.512y_d_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_d_inl0_hrd0/fcheck.exe build.512y_d_inl0_hrd0/fcheck_sa.o build.512y_d_inl0_hrd0/fsampler.o -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_gg_ttx_cpp build.512y_d_inl0_hrd0/RandomNumberKernels.o build.512y_d_inl0_hrd0/RamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512y_d_inl0_hrd0/libmg5amc_gg_ttx_cuda.so build.512y_d_inl0_hrd0/gCPPProcess.o build.512y_d_inl0_hrd0/gMatrixElementKernels.o build.512y_d_inl0_hrd0/gBridgeKernels.o build.512y_d_inl0_hrd0/gCrossSectionKernels.o build.512y_d_inl0_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512y_d_inl0_hrd0/libmg5amc_gg_ttx_cpp.so build.512y_d_inl0_hrd0/CPPProcess.o build.512y_d_inl0_hrd0/MatrixElementKernels.o build.512y_d_inl0_hrd0/BridgeKernels.o build.512y_d_inl0_hrd0/CrossSectionKernels.o build.512y_d_inl0_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_d_inl0_hrd0/fcheck.exe build.512y_d_inl0_hrd0/fcheck_sa.o build.512y_d_inl0_hrd0/fsampler.o -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_d_inl0_hrd0'  -lgfortran -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_gg_ttx_cpp build.512y_d_inl0_hrd0/RandomNumberKernels.o build.512y_d_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl0_hrd0/gcheck.exe build.512y_d_inl0_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl0_hrd0'  -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_gg_ttx_cuda build.512y_d_inl0_hrd0/gRandomNumberKernels.o build.512y_d_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl0_hrd0/fgcheck.exe build.512y_d_inl0_hrd0/fcheck_sa.o build.512y_d_inl0_hrd0/fsampler_cu.o -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl0_hrd0'  -lgfortran -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_gg_ttx_cuda build.512y_d_inl0_hrd0/gRandomNumberKernels.o build.512y_d_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_d_inl0_hrd0/check.exe build.512y_d_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_d_inl0_hrd0'  -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_gg_ttx_cpp build.512y_d_inl0_hrd0/RandomNumberKernels.o build.512y_d_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl0_hrd0/runTest.exe build.512y_d_inl0_hrd0/CPPProcess.o build.512y_d_inl0_hrd0/MatrixElementKernels.o build.512y_d_inl0_hrd0/BridgeKernels.o build.512y_d_inl0_hrd0/CrossSectionKernels.o build.512y_d_inl0_hrd0/RandomNumberKernels.o build.512y_d_inl0_hrd0/RamboSamplingKernels.o build.512y_d_inl0_hrd0/testxxx.o  build.512y_d_inl0_hrd0/testmisc.o  build.512y_d_inl0_hrd0/runTest.o build.512y_d_inl0_hrd0/gCPPProcess.o build.512y_d_inl0_hrd0/gMatrixElementKernels.o build.512y_d_inl0_hrd0/gBridgeKernels.o build.512y_d_inl0_hrd0/gCrossSectionKernels.o build.512y_d_inl0_hrd0/gRandomNumberKernels.o build.512y_d_inl0_hrd0/gRamboSamplingKernels.o build.512y_d_inl0_hrd0/testxxx_cu.o  build.512y_d_inl0_hrd0/testmisc_cu.o  build.512y_d_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl0_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
 touch build.512y_d_inl0_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_d_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.512y_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_d_inl0_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_d_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512y_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_d_inl0_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.512y_d_inl0_hrd0/libmg5amc_gg_ttx_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_d_inl0_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512y_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_d_inl0_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:01:05
+DATE: 2022-09-24_23:48:14
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/gcheck.exe -p 2048 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/gcheck.exe -p 2048 256 4 OMP=
 Process                     = SIGMA_SM_GG_TTX_CUDA [nvcc 11.7.99 (gcc 11.2.0)] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
-EvtsPerSec[Rmb+ME]     (23) = ( 4.213796e+07                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 1.173492e+08                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 1.300122e+08                 )  sec^-1
-MeanMatrixElemValue         = ( 2.086689e+00 +- 3.413217e-03 )  GeV^0
-TOTAL       :     0.599685 sec
-real	0m0.904s
-==PROF== Profiling "sigmaKin": launch__registers_per_thread 206
-==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100%
+EvtsPerSec[Rmb+ME]     (23) = ( 5.129441e+06                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 5.719836e+06                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 5.745921e+06                 )  sec^-1
+MeanMatrixElemValue         = ( 2.086360e+00 +- 2.416141e-03 )  GeV^0
+TOTAL       :     2.985826 sec
+real	0m3.444s
+   launch__registers_per_thread N/A
+   sm__sass_average_branch_targets_threads_uniform.pct N/A
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/gcheck.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/fgcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/gcheck.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/fgcheck.exe 2 64 2
 Avg ME (C++/CUDA)   = 2.028807e+00
 Avg ME (F77/CUDA)   = 2.0288063388516817
 Relative difference = 3.258803416564443e-07
@@ -2327,12 +2349,12 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:01:11 CEST 2022 Will execute './throughputX.sh -makej -ggtt -nocpp  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:48:42 CEST 2022 Will execute './throughputX.sh -makej -ggtt -nocpp  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
 CUDACPP_BUILDDIR='build.none_d_inl1_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -2342,51 +2364,52 @@ HELINL=1
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.none_d_inl1_hrd0 for tag=none_d_inl1_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.none_d_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.none_d_inl1_hrd0/gcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.none_d_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.none_d_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.none_d_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.none_d_inl1_hrd0/gMatrixElementKernels.o
 AVX=none
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.none_d_inl1_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.none_d_inl1_hrd0/gBridgeKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.none_d_inl1_hrd0/gCrossSectionKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.none_d_inl1_hrd0/fbridge_cu.o
-mkdir -p ../lib/build.none_d_inl1_hrd0
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.none_d_inl1_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.none_d_inl1_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.none_d_inl1_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.none_d_inl1_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.none_d_inl1_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.none_d_inl1_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.none_d_inl1_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.none_d_inl1_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.none_d_inl1_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.none_d_inl1_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.none_d_inl1_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.none_d_inl1_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.none_d_inl1_hrd0/BridgeKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.none_d_inl1_hrd0/CrossSectionKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.none_d_inl1_hrd0/fbridge.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.none_d_inl1_hrd0/Parameters_sm.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.none_d_inl1_hrd0/RandomNumberKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.none_d_inl1_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.none_d_inl1_hrd0/RamboSamplingKernels.o
+mkdir -p ../lib/build.none_d_inl1_hrd0
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.none_d_inl1_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.none_d_inl1_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.none_d_inl1_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.none_d_inl1_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.none_d_inl1_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.none_d_inl1_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.none_d_inl1_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.none_d_inl1_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.none_d_inl1_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.none_d_inl1_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.none_d_inl1_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.none_d_inl1_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.none_d_inl1_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.none_d_inl1_hrd0/libmg5amc_common.so build.none_d_inl1_hrd0/Parameters_sm.o build.none_d_inl1_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.none_d_inl1_hrd0/libmg5amc_gg_ttx_cpp.so build.none_d_inl1_hrd0/CPPProcess.o build.none_d_inl1_hrd0/MatrixElementKernels.o build.none_d_inl1_hrd0/BridgeKernels.o build.none_d_inl1_hrd0/CrossSectionKernels.o build.none_d_inl1_hrd0/fbridge.o -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_d_inl1_hrd0/check.exe build.none_d_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_gg_ttx_cpp build.none_d_inl1_hrd0/RandomNumberKernels.o build.none_d_inl1_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_d_inl1_hrd0/fcheck.exe build.none_d_inl1_hrd0/fcheck_sa.o build.none_d_inl1_hrd0/fsampler.o -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_gg_ttx_cpp build.none_d_inl1_hrd0/RandomNumberKernels.o build.none_d_inl1_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.none_d_inl1_hrd0/libmg5amc_gg_ttx_cuda.so build.none_d_inl1_hrd0/gCPPProcess.o build.none_d_inl1_hrd0/gMatrixElementKernels.o build.none_d_inl1_hrd0/gBridgeKernels.o build.none_d_inl1_hrd0/gCrossSectionKernels.o build.none_d_inl1_hrd0/fbridge_cu.o -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl1_hrd0/fgcheck.exe build.none_d_inl1_hrd0/fcheck_sa.o build.none_d_inl1_hrd0/fsampler_cu.o -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_gg_ttx_cuda build.none_d_inl1_hrd0/gRandomNumberKernels.o build.none_d_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl1_hrd0/gcheck.exe build.none_d_inl1_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_gg_ttx_cuda build.none_d_inl1_hrd0/gRandomNumberKernels.o build.none_d_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl1_hrd0/runTest.exe build.none_d_inl1_hrd0/CPPProcess.o build.none_d_inl1_hrd0/MatrixElementKernels.o build.none_d_inl1_hrd0/BridgeKernels.o build.none_d_inl1_hrd0/CrossSectionKernels.o build.none_d_inl1_hrd0/RandomNumberKernels.o build.none_d_inl1_hrd0/RamboSamplingKernels.o build.none_d_inl1_hrd0/testxxx.o  build.none_d_inl1_hrd0/testmisc.o  build.none_d_inl1_hrd0/runTest.o build.none_d_inl1_hrd0/gCPPProcess.o build.none_d_inl1_hrd0/gMatrixElementKernels.o build.none_d_inl1_hrd0/gBridgeKernels.o build.none_d_inl1_hrd0/gCrossSectionKernels.o build.none_d_inl1_hrd0/gRandomNumberKernels.o build.none_d_inl1_hrd0/gRamboSamplingKernels.o build.none_d_inl1_hrd0/testxxx_cu.o  build.none_d_inl1_hrd0/testmisc_cu.o  build.none_d_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.none_d_inl1_hrd0/libmg5amc_gg_ttx_cpp.so build.none_d_inl1_hrd0/CPPProcess.o build.none_d_inl1_hrd0/MatrixElementKernels.o build.none_d_inl1_hrd0/BridgeKernels.o build.none_d_inl1_hrd0/CrossSectionKernels.o build.none_d_inl1_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_d_inl1_hrd0/fcheck.exe build.none_d_inl1_hrd0/fcheck_sa.o build.none_d_inl1_hrd0/fsampler.o -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_d_inl1_hrd0'  -lgfortran -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_gg_ttx_cpp build.none_d_inl1_hrd0/RandomNumberKernels.o build.none_d_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_d_inl1_hrd0/check.exe build.none_d_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_d_inl1_hrd0'  -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_gg_ttx_cpp build.none_d_inl1_hrd0/RandomNumberKernels.o build.none_d_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.none_d_inl1_hrd0/libmg5amc_gg_ttx_cuda.so build.none_d_inl1_hrd0/gCPPProcess.o build.none_d_inl1_hrd0/gMatrixElementKernels.o build.none_d_inl1_hrd0/gBridgeKernels.o build.none_d_inl1_hrd0/gCrossSectionKernels.o build.none_d_inl1_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl1_hrd0/fgcheck.exe build.none_d_inl1_hrd0/fcheck_sa.o build.none_d_inl1_hrd0/fsampler_cu.o -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl1_hrd0'  -lgfortran -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_gg_ttx_cuda build.none_d_inl1_hrd0/gRandomNumberKernels.o build.none_d_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl1_hrd0/gcheck.exe build.none_d_inl1_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl1_hrd0'  -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_gg_ttx_cuda build.none_d_inl1_hrd0/gRandomNumberKernels.o build.none_d_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl1_hrd0/runTest.exe build.none_d_inl1_hrd0/CPPProcess.o build.none_d_inl1_hrd0/MatrixElementKernels.o build.none_d_inl1_hrd0/BridgeKernels.o build.none_d_inl1_hrd0/CrossSectionKernels.o build.none_d_inl1_hrd0/RandomNumberKernels.o build.none_d_inl1_hrd0/RamboSamplingKernels.o build.none_d_inl1_hrd0/testxxx.o  build.none_d_inl1_hrd0/testmisc.o  build.none_d_inl1_hrd0/runTest.o build.none_d_inl1_hrd0/gCPPProcess.o build.none_d_inl1_hrd0/gMatrixElementKernels.o build.none_d_inl1_hrd0/gBridgeKernels.o build.none_d_inl1_hrd0/gCrossSectionKernels.o build.none_d_inl1_hrd0/gRandomNumberKernels.o build.none_d_inl1_hrd0/gRamboSamplingKernels.o build.none_d_inl1_hrd0/testxxx_cu.o  build.none_d_inl1_hrd0/testmisc_cu.o  build.none_d_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl1_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
 touch build.none_d_inl1_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_d_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.none_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.none_d_inl1_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_d_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.none_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.none_d_inl1_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.none_d_inl1_hrd0/libmg5amc_gg_ttx_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_d_inl1_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.none_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.none_d_inl1_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
 CUDACPP_BUILDDIR='build.512y_d_inl1_hrd0'
 make -f cudacpp.mk
@@ -2397,22 +2420,18 @@ HELINL=1
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.512y_d_inl1_hrd0 for tag=512y_d_inl1_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.512y_d_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.512y_d_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.512y_d_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.512y_d_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512y_d_inl1_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512y_d_inl1_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512y_d_inl1_hrd0/gCrossSectionKernels.o
 AVX=512y
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.512y_d_inl1_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512y_d_inl1_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512y_d_inl1_hrd0/gBridgeKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512y_d_inl1_hrd0/gCrossSectionKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512y_d_inl1_hrd0/fbridge_cu.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.512y_d_inl1_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.512y_d_inl1_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512y_d_inl1_hrd0/gRandomNumberKernels.o
-mkdir -p ../lib/build.512y_d_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512y_d_inl1_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512y_d_inl1_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512y_d_inl1_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512y_d_inl1_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.512y_d_inl1_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.512y_d_inl1_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.512y_d_inl1_hrd0/MatrixElementKernels.o
@@ -2421,47 +2440,52 @@ ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.512y_d_inl1_hrd0/fbridge.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.512y_d_inl1_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.512y_d_inl1_hrd0/RamboSamplingKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.512y_d_inl1_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512y_d_inl1_hrd0/testxxx_cu.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.512y_d_inl1_hrd0/Parameters_sm.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.512y_d_inl1_hrd0/read_slha.o
+mkdir -p ../lib/build.512y_d_inl1_hrd0
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512y_d_inl1_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.512y_d_inl1_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512y_d_inl1_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512y_d_inl1_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.512y_d_inl1_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.512y_d_inl1_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.512y_d_inl1_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.512y_d_inl1_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512y_d_inl1_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512y_d_inl1_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.512y_d_inl1_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.512y_d_inl1_hrd0/libmg5amc_common.so build.512y_d_inl1_hrd0/Parameters_sm.o build.512y_d_inl1_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512y_d_inl1_hrd0/libmg5amc_gg_ttx_cuda.so build.512y_d_inl1_hrd0/gCPPProcess.o build.512y_d_inl1_hrd0/gMatrixElementKernels.o build.512y_d_inl1_hrd0/gBridgeKernels.o build.512y_d_inl1_hrd0/gCrossSectionKernels.o build.512y_d_inl1_hrd0/fbridge_cu.o -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512y_d_inl1_hrd0/libmg5amc_gg_ttx_cpp.so build.512y_d_inl1_hrd0/CPPProcess.o build.512y_d_inl1_hrd0/MatrixElementKernels.o build.512y_d_inl1_hrd0/BridgeKernels.o build.512y_d_inl1_hrd0/CrossSectionKernels.o build.512y_d_inl1_hrd0/fbridge.o -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl1_hrd0/runTest.exe build.512y_d_inl1_hrd0/CPPProcess.o build.512y_d_inl1_hrd0/MatrixElementKernels.o build.512y_d_inl1_hrd0/BridgeKernels.o build.512y_d_inl1_hrd0/CrossSectionKernels.o build.512y_d_inl1_hrd0/RandomNumberKernels.o build.512y_d_inl1_hrd0/RamboSamplingKernels.o build.512y_d_inl1_hrd0/testxxx.o  build.512y_d_inl1_hrd0/testmisc.o  build.512y_d_inl1_hrd0/runTest.o build.512y_d_inl1_hrd0/gCPPProcess.o build.512y_d_inl1_hrd0/gMatrixElementKernels.o build.512y_d_inl1_hrd0/gBridgeKernels.o build.512y_d_inl1_hrd0/gCrossSectionKernels.o build.512y_d_inl1_hrd0/gRandomNumberKernels.o build.512y_d_inl1_hrd0/gRamboSamplingKernels.o build.512y_d_inl1_hrd0/testxxx_cu.o  build.512y_d_inl1_hrd0/testmisc_cu.o  build.512y_d_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_d_inl1_hrd0/check.exe build.512y_d_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_gg_ttx_cpp build.512y_d_inl1_hrd0/RandomNumberKernels.o build.512y_d_inl1_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_d_inl1_hrd0/fcheck.exe build.512y_d_inl1_hrd0/fcheck_sa.o build.512y_d_inl1_hrd0/fsampler.o -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_gg_ttx_cpp build.512y_d_inl1_hrd0/RandomNumberKernels.o build.512y_d_inl1_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl1_hrd0/gcheck.exe build.512y_d_inl1_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_gg_ttx_cuda build.512y_d_inl1_hrd0/gRandomNumberKernels.o build.512y_d_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl1_hrd0/fgcheck.exe build.512y_d_inl1_hrd0/fcheck_sa.o build.512y_d_inl1_hrd0/fsampler_cu.o -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_gg_ttx_cuda build.512y_d_inl1_hrd0/gRandomNumberKernels.o build.512y_d_inl1_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512y_d_inl1_hrd0/libmg5amc_gg_ttx_cuda.so build.512y_d_inl1_hrd0/gCPPProcess.o build.512y_d_inl1_hrd0/gMatrixElementKernels.o build.512y_d_inl1_hrd0/gBridgeKernels.o build.512y_d_inl1_hrd0/gCrossSectionKernels.o build.512y_d_inl1_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl1_hrd0/gcheck.exe build.512y_d_inl1_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl1_hrd0'  -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_gg_ttx_cuda build.512y_d_inl1_hrd0/gRandomNumberKernels.o build.512y_d_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl1_hrd0/fgcheck.exe build.512y_d_inl1_hrd0/fcheck_sa.o build.512y_d_inl1_hrd0/fsampler_cu.o -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl1_hrd0'  -lgfortran -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_gg_ttx_cuda build.512y_d_inl1_hrd0/gRandomNumberKernels.o build.512y_d_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512y_d_inl1_hrd0/libmg5amc_gg_ttx_cpp.so build.512y_d_inl1_hrd0/CPPProcess.o build.512y_d_inl1_hrd0/MatrixElementKernels.o build.512y_d_inl1_hrd0/BridgeKernels.o build.512y_d_inl1_hrd0/CrossSectionKernels.o build.512y_d_inl1_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_d_inl1_hrd0/fcheck.exe build.512y_d_inl1_hrd0/fcheck_sa.o build.512y_d_inl1_hrd0/fsampler.o -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_d_inl1_hrd0'  -lgfortran -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_gg_ttx_cpp build.512y_d_inl1_hrd0/RandomNumberKernels.o build.512y_d_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_d_inl1_hrd0/check.exe build.512y_d_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_d_inl1_hrd0'  -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_gg_ttx_cpp build.512y_d_inl1_hrd0/RandomNumberKernels.o build.512y_d_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl1_hrd0/runTest.exe build.512y_d_inl1_hrd0/CPPProcess.o build.512y_d_inl1_hrd0/MatrixElementKernels.o build.512y_d_inl1_hrd0/BridgeKernels.o build.512y_d_inl1_hrd0/CrossSectionKernels.o build.512y_d_inl1_hrd0/RandomNumberKernels.o build.512y_d_inl1_hrd0/RamboSamplingKernels.o build.512y_d_inl1_hrd0/testxxx.o  build.512y_d_inl1_hrd0/testmisc.o  build.512y_d_inl1_hrd0/runTest.o build.512y_d_inl1_hrd0/gCPPProcess.o build.512y_d_inl1_hrd0/gMatrixElementKernels.o build.512y_d_inl1_hrd0/gBridgeKernels.o build.512y_d_inl1_hrd0/gCrossSectionKernels.o build.512y_d_inl1_hrd0/gRandomNumberKernels.o build.512y_d_inl1_hrd0/gRamboSamplingKernels.o build.512y_d_inl1_hrd0/testxxx_cu.o  build.512y_d_inl1_hrd0/testmisc_cu.o  build.512y_d_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl1_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
 touch build.512y_d_inl1_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_d_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.512y_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_d_inl1_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_d_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512y_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_d_inl1_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.512y_d_inl1_hrd0/libmg5amc_gg_ttx_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_d_inl1_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512y_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_d_inl1_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:01:23
+DATE: 2022-09-24_23:49:05
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl1_hrd0/gcheck.exe -p 2048 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl1_hrd0/gcheck.exe -p 2048 256 4 OMP=
 Process                     = SIGMA_SM_GG_TTX_CUDA [nvcc 11.7.99 (gcc 11.2.0)] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
-EvtsPerSec[Rmb+ME]     (23) = ( 4.379785e+07                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 1.174733e+08                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 1.302486e+08                 )  sec^-1
-MeanMatrixElemValue         = ( 2.086689e+00 +- 3.413217e-03 )  GeV^0
-TOTAL       :     0.592877 sec
-real	0m0.896s
-==PROF== Profiling "sigmaKin": launch__registers_per_thread 206
-==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100%
+EvtsPerSec[Rmb+ME]     (23) = ( 5.253371e+06                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 5.869467e+06                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 5.897079e+06                 )  sec^-1
+MeanMatrixElemValue         = ( 2.086360e+00 +- 2.416141e-03 )  GeV^0
+TOTAL       :     2.962660 sec
+real	0m3.409s
+   launch__registers_per_thread N/A
+   sm__sass_average_branch_targets_threads_uniform.pct N/A
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl1_hrd0/gcheck.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl1_hrd0/fgcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl1_hrd0/gcheck.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl1_hrd0/fgcheck.exe 2 64 2
 Avg ME (C++/CUDA)   = 2.028807e+00
 Avg ME (F77/CUDA)   = 2.0288063388516817
 Relative difference = 3.258803416564443e-07
@@ -2469,12 +2493,12 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:01:29 CEST 2022 Will execute './throughputX.sh -makej -ggtt -nocpp -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:49:33 CEST 2022 Will execute './throughputX.sh -makej -ggtt -nocpp -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
 CUDACPP_BUILDDIR='build.none_f_inl0_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -2484,22 +2508,18 @@ HELINL=0
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.none_f_inl0_hrd0 for tag=none_f_inl0_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.none_f_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gcheck_sa.cu -o build.none_f_inl0_hrd0/gcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gCPPProcess.cu -o build.none_f_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gcheck_sa.cu -o build.none_f_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gCPPProcess.cu -o build.none_f_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.none_f_inl0_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gBridgeKernels.cu -o build.none_f_inl0_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.none_f_inl0_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fbridge.cc -o build.none_f_inl0_hrd0/fbridge_cu.o
 AVX=none
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.none_f_inl0_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gBridgeKernels.cu -o build.none_f_inl0_hrd0/gBridgeKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.none_f_inl0_hrd0/gCrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -c Parameters_sm.cc -o build.none_f_inl0_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -c read_slha.cc -o build.none_f_inl0_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fbridge.cc -o build.none_f_inl0_hrd0/fbridge_cu.o
-mkdir -p ../lib/build.none_f_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.none_f_inl0_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.none_f_inl0_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.none_f_inl0_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.none_f_inl0_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.none_f_inl0_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.none_f_inl0_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.none_f_inl0_hrd0/MatrixElementKernels.o
@@ -2509,26 +2529,31 @@ ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.none_f_inl0_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.none_f_inl0_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.none_f_inl0_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testxxx.cc -o build.none_f_inl0_hrd0/testxxx_cu.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testxxx.cc -o build.none_f_inl0_hrd0/testxxx_cu.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -c Parameters_sm.cc -o build.none_f_inl0_hrd0/Parameters_sm.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -c read_slha.cc -o build.none_f_inl0_hrd0/read_slha.o
+mkdir -p ../lib/build.none_f_inl0_hrd0
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.none_f_inl0_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testmisc.cc -o build.none_f_inl0_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testmisc.cc -o build.none_f_inl0_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.none_f_inl0_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu runTest.cc -o build.none_f_inl0_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu runTest.cc -o build.none_f_inl0_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.none_f_inl0_hrd0/fcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fsampler.cc -o build.none_f_inl0_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.none_f_inl0_hrd0/fsampler.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fsampler.cc -o build.none_f_inl0_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.none_f_inl0_hrd0/libmg5amc_common.so build.none_f_inl0_hrd0/Parameters_sm.o build.none_f_inl0_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.none_f_inl0_hrd0/libmg5amc_gg_ttx_cpp.so build.none_f_inl0_hrd0/CPPProcess.o build.none_f_inl0_hrd0/MatrixElementKernels.o build.none_f_inl0_hrd0/BridgeKernels.o build.none_f_inl0_hrd0/CrossSectionKernels.o build.none_f_inl0_hrd0/fbridge.o -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_f_inl0_hrd0/check.exe build.none_f_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_gg_ttx_cpp build.none_f_inl0_hrd0/RandomNumberKernels.o build.none_f_inl0_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_f_inl0_hrd0/fcheck.exe build.none_f_inl0_hrd0/fcheck_sa.o build.none_f_inl0_hrd0/fsampler.o -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_gg_ttx_cpp build.none_f_inl0_hrd0/RandomNumberKernels.o build.none_f_inl0_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.none_f_inl0_hrd0/libmg5amc_gg_ttx_cuda.so build.none_f_inl0_hrd0/gCPPProcess.o build.none_f_inl0_hrd0/gMatrixElementKernels.o build.none_f_inl0_hrd0/gBridgeKernels.o build.none_f_inl0_hrd0/gCrossSectionKernels.o build.none_f_inl0_hrd0/fbridge_cu.o -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl0_hrd0/fgcheck.exe build.none_f_inl0_hrd0/fcheck_sa.o build.none_f_inl0_hrd0/fsampler_cu.o -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_gg_ttx_cuda build.none_f_inl0_hrd0/gRandomNumberKernels.o build.none_f_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl0_hrd0/gcheck.exe build.none_f_inl0_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_gg_ttx_cuda build.none_f_inl0_hrd0/gRandomNumberKernels.o build.none_f_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl0_hrd0/runTest.exe build.none_f_inl0_hrd0/CPPProcess.o build.none_f_inl0_hrd0/MatrixElementKernels.o build.none_f_inl0_hrd0/BridgeKernels.o build.none_f_inl0_hrd0/CrossSectionKernels.o build.none_f_inl0_hrd0/RandomNumberKernels.o build.none_f_inl0_hrd0/RamboSamplingKernels.o build.none_f_inl0_hrd0/testxxx.o  build.none_f_inl0_hrd0/testmisc.o  build.none_f_inl0_hrd0/runTest.o build.none_f_inl0_hrd0/gCPPProcess.o build.none_f_inl0_hrd0/gMatrixElementKernels.o build.none_f_inl0_hrd0/gBridgeKernels.o build.none_f_inl0_hrd0/gCrossSectionKernels.o build.none_f_inl0_hrd0/gRandomNumberKernels.o build.none_f_inl0_hrd0/gRamboSamplingKernels.o build.none_f_inl0_hrd0/testxxx_cu.o  build.none_f_inl0_hrd0/testmisc_cu.o  build.none_f_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.none_f_inl0_hrd0/libmg5amc_gg_ttx_cpp.so build.none_f_inl0_hrd0/CPPProcess.o build.none_f_inl0_hrd0/MatrixElementKernels.o build.none_f_inl0_hrd0/BridgeKernels.o build.none_f_inl0_hrd0/CrossSectionKernels.o build.none_f_inl0_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_f_inl0_hrd0/check.exe build.none_f_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_f_inl0_hrd0'  -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_gg_ttx_cpp build.none_f_inl0_hrd0/RandomNumberKernels.o build.none_f_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_f_inl0_hrd0/fcheck.exe build.none_f_inl0_hrd0/fcheck_sa.o build.none_f_inl0_hrd0/fsampler.o -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_f_inl0_hrd0'  -lgfortran -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_gg_ttx_cpp build.none_f_inl0_hrd0/RandomNumberKernels.o build.none_f_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.none_f_inl0_hrd0/libmg5amc_gg_ttx_cuda.so build.none_f_inl0_hrd0/gCPPProcess.o build.none_f_inl0_hrd0/gMatrixElementKernels.o build.none_f_inl0_hrd0/gBridgeKernels.o build.none_f_inl0_hrd0/gCrossSectionKernels.o build.none_f_inl0_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl0_hrd0/fgcheck.exe build.none_f_inl0_hrd0/fcheck_sa.o build.none_f_inl0_hrd0/fsampler_cu.o -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl0_hrd0'  -lgfortran -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_gg_ttx_cuda build.none_f_inl0_hrd0/gRandomNumberKernels.o build.none_f_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl0_hrd0/gcheck.exe build.none_f_inl0_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl0_hrd0'  -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_gg_ttx_cuda build.none_f_inl0_hrd0/gRandomNumberKernels.o build.none_f_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl0_hrd0/runTest.exe build.none_f_inl0_hrd0/CPPProcess.o build.none_f_inl0_hrd0/MatrixElementKernels.o build.none_f_inl0_hrd0/BridgeKernels.o build.none_f_inl0_hrd0/CrossSectionKernels.o build.none_f_inl0_hrd0/RandomNumberKernels.o build.none_f_inl0_hrd0/RamboSamplingKernels.o build.none_f_inl0_hrd0/testxxx.o  build.none_f_inl0_hrd0/testmisc.o  build.none_f_inl0_hrd0/runTest.o build.none_f_inl0_hrd0/gCPPProcess.o build.none_f_inl0_hrd0/gMatrixElementKernels.o build.none_f_inl0_hrd0/gBridgeKernels.o build.none_f_inl0_hrd0/gCrossSectionKernels.o build.none_f_inl0_hrd0/gRandomNumberKernels.o build.none_f_inl0_hrd0/gRamboSamplingKernels.o build.none_f_inl0_hrd0/testxxx_cu.o  build.none_f_inl0_hrd0/testmisc_cu.o  build.none_f_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl0_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
 touch build.none_f_inl0_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_f_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.none_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.none_f_inl0_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_f_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.none_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.none_f_inl0_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.none_f_inl0_hrd0/libmg5amc_gg_ttx_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_f_inl0_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.none_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.none_f_inl0_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
 CUDACPP_BUILDDIR='build.512y_f_inl0_hrd0'
 make -f cudacpp.mk
@@ -2539,22 +2564,18 @@ HELINL=0
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.512y_f_inl0_hrd0 for tag=512y_f_inl0_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.512y_f_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gcheck_sa.cu -o build.512y_f_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gcheck_sa.cu -o build.512y_f_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gCPPProcess.cu -o build.512y_f_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512y_f_inl0_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512y_f_inl0_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512y_f_inl0_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512y_f_inl0_hrd0/fbridge_cu.o
 AVX=512y
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gCPPProcess.cu -o build.512y_f_inl0_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512y_f_inl0_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512y_f_inl0_hrd0/gBridgeKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512y_f_inl0_hrd0/gCrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -c read_slha.cc -o build.512y_f_inl0_hrd0/read_slha.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -c Parameters_sm.cc -o build.512y_f_inl0_hrd0/Parameters_sm.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512y_f_inl0_hrd0/fbridge_cu.o
-mkdir -p ../lib/build.512y_f_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512y_f_inl0_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512y_f_inl0_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512y_f_inl0_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512y_f_inl0_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.512y_f_inl0_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.512y_f_inl0_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.512y_f_inl0_hrd0/MatrixElementKernels.o
@@ -2562,48 +2583,53 @@ ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.512y_f_inl0_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.512y_f_inl0_hrd0/fbridge.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.512y_f_inl0_hrd0/RandomNumberKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.512y_f_inl0_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.512y_f_inl0_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512y_f_inl0_hrd0/testxxx_cu.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -c Parameters_sm.cc -o build.512y_f_inl0_hrd0/Parameters_sm.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512y_f_inl0_hrd0/testxxx_cu.o
+mkdir -p ../lib/build.512y_f_inl0_hrd0
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.512y_f_inl0_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512y_f_inl0_hrd0/testmisc_cu.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -c read_slha.cc -o build.512y_f_inl0_hrd0/read_slha.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512y_f_inl0_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.512y_f_inl0_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu runTest.cc -o build.512y_f_inl0_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu runTest.cc -o build.512y_f_inl0_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.512y_f_inl0_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512y_f_inl0_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512y_f_inl0_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.512y_f_inl0_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.512y_f_inl0_hrd0/libmg5amc_common.so build.512y_f_inl0_hrd0/Parameters_sm.o build.512y_f_inl0_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512y_f_inl0_hrd0/libmg5amc_gg_ttx_cuda.so build.512y_f_inl0_hrd0/gCPPProcess.o build.512y_f_inl0_hrd0/gMatrixElementKernels.o build.512y_f_inl0_hrd0/gBridgeKernels.o build.512y_f_inl0_hrd0/gCrossSectionKernels.o build.512y_f_inl0_hrd0/fbridge_cu.o -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512y_f_inl0_hrd0/libmg5amc_gg_ttx_cpp.so build.512y_f_inl0_hrd0/CPPProcess.o build.512y_f_inl0_hrd0/MatrixElementKernels.o build.512y_f_inl0_hrd0/BridgeKernels.o build.512y_f_inl0_hrd0/CrossSectionKernels.o build.512y_f_inl0_hrd0/fbridge.o -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl0_hrd0/runTest.exe build.512y_f_inl0_hrd0/CPPProcess.o build.512y_f_inl0_hrd0/MatrixElementKernels.o build.512y_f_inl0_hrd0/BridgeKernels.o build.512y_f_inl0_hrd0/CrossSectionKernels.o build.512y_f_inl0_hrd0/RandomNumberKernels.o build.512y_f_inl0_hrd0/RamboSamplingKernels.o build.512y_f_inl0_hrd0/testxxx.o  build.512y_f_inl0_hrd0/testmisc.o  build.512y_f_inl0_hrd0/runTest.o build.512y_f_inl0_hrd0/gCPPProcess.o build.512y_f_inl0_hrd0/gMatrixElementKernels.o build.512y_f_inl0_hrd0/gBridgeKernels.o build.512y_f_inl0_hrd0/gCrossSectionKernels.o build.512y_f_inl0_hrd0/gRandomNumberKernels.o build.512y_f_inl0_hrd0/gRamboSamplingKernels.o build.512y_f_inl0_hrd0/testxxx_cu.o  build.512y_f_inl0_hrd0/testmisc_cu.o  build.512y_f_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_f_inl0_hrd0/check.exe build.512y_f_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_gg_ttx_cpp build.512y_f_inl0_hrd0/RandomNumberKernels.o build.512y_f_inl0_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_f_inl0_hrd0/fcheck.exe build.512y_f_inl0_hrd0/fcheck_sa.o build.512y_f_inl0_hrd0/fsampler.o -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_gg_ttx_cpp build.512y_f_inl0_hrd0/RandomNumberKernels.o build.512y_f_inl0_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl0_hrd0/gcheck.exe build.512y_f_inl0_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_gg_ttx_cuda build.512y_f_inl0_hrd0/gRandomNumberKernels.o build.512y_f_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl0_hrd0/fgcheck.exe build.512y_f_inl0_hrd0/fcheck_sa.o build.512y_f_inl0_hrd0/fsampler_cu.o -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_gg_ttx_cuda build.512y_f_inl0_hrd0/gRandomNumberKernels.o build.512y_f_inl0_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512y_f_inl0_hrd0/libmg5amc_gg_ttx_cuda.so build.512y_f_inl0_hrd0/gCPPProcess.o build.512y_f_inl0_hrd0/gMatrixElementKernels.o build.512y_f_inl0_hrd0/gBridgeKernels.o build.512y_f_inl0_hrd0/gCrossSectionKernels.o build.512y_f_inl0_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512y_f_inl0_hrd0/libmg5amc_gg_ttx_cpp.so build.512y_f_inl0_hrd0/CPPProcess.o build.512y_f_inl0_hrd0/MatrixElementKernels.o build.512y_f_inl0_hrd0/BridgeKernels.o build.512y_f_inl0_hrd0/CrossSectionKernels.o build.512y_f_inl0_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_f_inl0_hrd0/fcheck.exe build.512y_f_inl0_hrd0/fcheck_sa.o build.512y_f_inl0_hrd0/fsampler.o -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_f_inl0_hrd0'  -lgfortran -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_gg_ttx_cpp build.512y_f_inl0_hrd0/RandomNumberKernels.o build.512y_f_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl0_hrd0/gcheck.exe build.512y_f_inl0_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl0_hrd0'  -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_gg_ttx_cuda build.512y_f_inl0_hrd0/gRandomNumberKernels.o build.512y_f_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl0_hrd0/fgcheck.exe build.512y_f_inl0_hrd0/fcheck_sa.o build.512y_f_inl0_hrd0/fsampler_cu.o -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl0_hrd0'  -lgfortran -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_gg_ttx_cuda build.512y_f_inl0_hrd0/gRandomNumberKernels.o build.512y_f_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_f_inl0_hrd0/check.exe build.512y_f_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_f_inl0_hrd0'  -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_gg_ttx_cpp build.512y_f_inl0_hrd0/RandomNumberKernels.o build.512y_f_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl0_hrd0/runTest.exe build.512y_f_inl0_hrd0/CPPProcess.o build.512y_f_inl0_hrd0/MatrixElementKernels.o build.512y_f_inl0_hrd0/BridgeKernels.o build.512y_f_inl0_hrd0/CrossSectionKernels.o build.512y_f_inl0_hrd0/RandomNumberKernels.o build.512y_f_inl0_hrd0/RamboSamplingKernels.o build.512y_f_inl0_hrd0/testxxx.o  build.512y_f_inl0_hrd0/testmisc.o  build.512y_f_inl0_hrd0/runTest.o build.512y_f_inl0_hrd0/gCPPProcess.o build.512y_f_inl0_hrd0/gMatrixElementKernels.o build.512y_f_inl0_hrd0/gBridgeKernels.o build.512y_f_inl0_hrd0/gCrossSectionKernels.o build.512y_f_inl0_hrd0/gRandomNumberKernels.o build.512y_f_inl0_hrd0/gRamboSamplingKernels.o build.512y_f_inl0_hrd0/testxxx_cu.o  build.512y_f_inl0_hrd0/testmisc_cu.o  build.512y_f_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl0_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
 touch build.512y_f_inl0_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_f_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.512y_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_f_inl0_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_f_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512y_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_f_inl0_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.512y_f_inl0_hrd0/libmg5amc_gg_ttx_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_f_inl0_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512y_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_f_inl0_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:01:50
+DATE: 2022-09-24_23:50:13
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/gcheck.exe -p 2048 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/gcheck.exe -p 2048 256 4 OMP=
 Process                     = SIGMA_SM_GG_TTX_CUDA [nvcc 11.7.99 (gcc 11.2.0)] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK
 FP precision                = FLOAT (NaN/abnormal=0, zero=0)
-EvtsPerSec[Rmb+ME]     (23) = ( 9.297125e+07                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 3.164994e+08                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 3.636906e+08                 )  sec^-1
-MeanMatrixElemValue         = ( 2.086718e+00 +- 3.413389e-03 )  GeV^0
-TOTAL       :     0.547981 sec
-real	0m0.838s
-==PROF== Profiling "sigmaKin": launch__registers_per_thread 123
-==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100%
+EvtsPerSec[Rmb+ME]     (23) = ( 5.461452e+07                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 1.637584e+08                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 1.754402e+08                 )  sec^-1
+MeanMatrixElemValue         = ( 2.086388e+00 +- 2.416254e-03 )  GeV^0
+TOTAL       :     2.486470 sec
+real	0m2.986s
+   launch__registers_per_thread N/A
+   sm__sass_average_branch_targets_threads_uniform.pct N/A
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/gcheck.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/fgcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/gcheck.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/fgcheck.exe 2 64 2
 Avg ME (C++/CUDA)   = 2.028811e+00
 Avg ME (F77/CUDA)   = 2.0288500845199451
 Relative difference = 1.926474173540216e-05
@@ -2611,12 +2637,12 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:01:56 CEST 2022 Will execute './throughputX.sh -makej -ggtt -nocpp -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:50:41 CEST 2022 Will execute './throughputX.sh -makej -ggtt -nocpp -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
 CUDACPP_BUILDDIR='build.none_f_inl1_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -2626,22 +2652,18 @@ HELINL=1
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.none_f_inl1_hrd0 for tag=none_f_inl1_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.none_f_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.none_f_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.none_f_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.none_f_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.none_f_inl1_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.none_f_inl1_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.none_f_inl1_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.none_f_inl1_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.none_f_inl1_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.none_f_inl1_hrd0/gRamboSamplingKernels.o
 AVX=none
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.none_f_inl1_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.none_f_inl1_hrd0/gMatrixElementKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.none_f_inl1_hrd0/gBridgeKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.none_f_inl1_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.none_f_inl1_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.none_f_inl1_hrd0/gCrossSectionKernels.o
-mkdir -p ../lib/build.none_f_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.none_f_inl1_hrd0/fbridge_cu.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.none_f_inl1_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.none_f_inl1_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.none_f_inl1_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.none_f_inl1_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.none_f_inl1_hrd0/MatrixElementKernels.o
@@ -2650,27 +2672,32 @@ ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.none_f_inl1_hrd0/fbridge.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.none_f_inl1_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.none_f_inl1_hrd0/RamboSamplingKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.none_f_inl1_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.none_f_inl1_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.none_f_inl1_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.none_f_inl1_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.none_f_inl1_hrd0/testmisc_cu.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.none_f_inl1_hrd0/Parameters_sm.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.none_f_inl1_hrd0/testmisc_cu.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.none_f_inl1_hrd0/read_slha.o
+mkdir -p ../lib/build.none_f_inl1_hrd0
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.none_f_inl1_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.none_f_inl1_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.none_f_inl1_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.none_f_inl1_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.none_f_inl1_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.none_f_inl1_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.none_f_inl1_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.none_f_inl1_hrd0/libmg5amc_common.so build.none_f_inl1_hrd0/Parameters_sm.o build.none_f_inl1_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.none_f_inl1_hrd0/libmg5amc_gg_ttx_cpp.so build.none_f_inl1_hrd0/CPPProcess.o build.none_f_inl1_hrd0/MatrixElementKernels.o build.none_f_inl1_hrd0/BridgeKernels.o build.none_f_inl1_hrd0/CrossSectionKernels.o build.none_f_inl1_hrd0/fbridge.o -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_f_inl1_hrd0/check.exe build.none_f_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_gg_ttx_cpp build.none_f_inl1_hrd0/RandomNumberKernels.o build.none_f_inl1_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_f_inl1_hrd0/fcheck.exe build.none_f_inl1_hrd0/fcheck_sa.o build.none_f_inl1_hrd0/fsampler.o -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_gg_ttx_cpp build.none_f_inl1_hrd0/RandomNumberKernels.o build.none_f_inl1_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.none_f_inl1_hrd0/libmg5amc_gg_ttx_cuda.so build.none_f_inl1_hrd0/gCPPProcess.o build.none_f_inl1_hrd0/gMatrixElementKernels.o build.none_f_inl1_hrd0/gBridgeKernels.o build.none_f_inl1_hrd0/gCrossSectionKernels.o build.none_f_inl1_hrd0/fbridge_cu.o -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl1_hrd0/fgcheck.exe build.none_f_inl1_hrd0/fcheck_sa.o build.none_f_inl1_hrd0/fsampler_cu.o -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_gg_ttx_cuda build.none_f_inl1_hrd0/gRandomNumberKernels.o build.none_f_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl1_hrd0/gcheck.exe build.none_f_inl1_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_gg_ttx_cuda build.none_f_inl1_hrd0/gRandomNumberKernels.o build.none_f_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl1_hrd0/runTest.exe build.none_f_inl1_hrd0/CPPProcess.o build.none_f_inl1_hrd0/MatrixElementKernels.o build.none_f_inl1_hrd0/BridgeKernels.o build.none_f_inl1_hrd0/CrossSectionKernels.o build.none_f_inl1_hrd0/RandomNumberKernels.o build.none_f_inl1_hrd0/RamboSamplingKernels.o build.none_f_inl1_hrd0/testxxx.o  build.none_f_inl1_hrd0/testmisc.o  build.none_f_inl1_hrd0/runTest.o build.none_f_inl1_hrd0/gCPPProcess.o build.none_f_inl1_hrd0/gMatrixElementKernels.o build.none_f_inl1_hrd0/gBridgeKernels.o build.none_f_inl1_hrd0/gCrossSectionKernels.o build.none_f_inl1_hrd0/gRandomNumberKernels.o build.none_f_inl1_hrd0/gRamboSamplingKernels.o build.none_f_inl1_hrd0/testxxx_cu.o  build.none_f_inl1_hrd0/testmisc_cu.o  build.none_f_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.none_f_inl1_hrd0/libmg5amc_gg_ttx_cpp.so build.none_f_inl1_hrd0/CPPProcess.o build.none_f_inl1_hrd0/MatrixElementKernels.o build.none_f_inl1_hrd0/BridgeKernels.o build.none_f_inl1_hrd0/CrossSectionKernels.o build.none_f_inl1_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_f_inl1_hrd0/check.exe build.none_f_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_f_inl1_hrd0'  -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_gg_ttx_cpp build.none_f_inl1_hrd0/RandomNumberKernels.o build.none_f_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_f_inl1_hrd0/fcheck.exe build.none_f_inl1_hrd0/fcheck_sa.o build.none_f_inl1_hrd0/fsampler.o -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_f_inl1_hrd0'  -lgfortran -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_gg_ttx_cpp build.none_f_inl1_hrd0/RandomNumberKernels.o build.none_f_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.none_f_inl1_hrd0/libmg5amc_gg_ttx_cuda.so build.none_f_inl1_hrd0/gCPPProcess.o build.none_f_inl1_hrd0/gMatrixElementKernels.o build.none_f_inl1_hrd0/gBridgeKernels.o build.none_f_inl1_hrd0/gCrossSectionKernels.o build.none_f_inl1_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl1_hrd0/fgcheck.exe build.none_f_inl1_hrd0/fcheck_sa.o build.none_f_inl1_hrd0/fsampler_cu.o -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl1_hrd0'  -lgfortran -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_gg_ttx_cuda build.none_f_inl1_hrd0/gRandomNumberKernels.o build.none_f_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl1_hrd0/gcheck.exe build.none_f_inl1_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl1_hrd0'  -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_gg_ttx_cuda build.none_f_inl1_hrd0/gRandomNumberKernels.o build.none_f_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl1_hrd0/runTest.exe build.none_f_inl1_hrd0/CPPProcess.o build.none_f_inl1_hrd0/MatrixElementKernels.o build.none_f_inl1_hrd0/BridgeKernels.o build.none_f_inl1_hrd0/CrossSectionKernels.o build.none_f_inl1_hrd0/RandomNumberKernels.o build.none_f_inl1_hrd0/RamboSamplingKernels.o build.none_f_inl1_hrd0/testxxx.o  build.none_f_inl1_hrd0/testmisc.o  build.none_f_inl1_hrd0/runTest.o build.none_f_inl1_hrd0/gCPPProcess.o build.none_f_inl1_hrd0/gMatrixElementKernels.o build.none_f_inl1_hrd0/gBridgeKernels.o build.none_f_inl1_hrd0/gCrossSectionKernels.o build.none_f_inl1_hrd0/gRandomNumberKernels.o build.none_f_inl1_hrd0/gRamboSamplingKernels.o build.none_f_inl1_hrd0/testxxx_cu.o  build.none_f_inl1_hrd0/testmisc_cu.o  build.none_f_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl1_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
 touch build.none_f_inl1_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_f_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.none_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.none_f_inl1_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_f_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.none_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.none_f_inl1_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.none_f_inl1_hrd0/libmg5amc_gg_ttx_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_f_inl1_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.none_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.none_f_inl1_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
 CUDACPP_BUILDDIR='build.512y_f_inl1_hrd0'
 make -f cudacpp.mk
@@ -2681,22 +2708,18 @@ HELINL=1
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.512y_f_inl1_hrd0 for tag=512y_f_inl1_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.512y_f_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.512y_f_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.512y_f_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.512y_f_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512y_f_inl1_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512y_f_inl1_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512y_f_inl1_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512y_f_inl1_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512y_f_inl1_hrd0/gRandomNumberKernels.o
 AVX=512y
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.512y_f_inl1_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512y_f_inl1_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512y_f_inl1_hrd0/gBridgeKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512y_f_inl1_hrd0/gCrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.512y_f_inl1_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.512y_f_inl1_hrd0/read_slha.o
-mkdir -p ../lib/build.512y_f_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512y_f_inl1_hrd0/fbridge_cu.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512y_f_inl1_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512y_f_inl1_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512y_f_inl1_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.512y_f_inl1_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.512y_f_inl1_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.512y_f_inl1_hrd0/MatrixElementKernels.o
@@ -2705,47 +2728,52 @@ ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.512y_f_inl1_hrd0/fbridge.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.512y_f_inl1_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.512y_f_inl1_hrd0/RamboSamplingKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.512y_f_inl1_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512y_f_inl1_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512y_f_inl1_hrd0/testxxx_cu.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.512y_f_inl1_hrd0/read_slha.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.512y_f_inl1_hrd0/Parameters_sm.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.512y_f_inl1_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512y_f_inl1_hrd0/testmisc_cu.o
+mkdir -p ../lib/build.512y_f_inl1_hrd0
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512y_f_inl1_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.512y_f_inl1_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.512y_f_inl1_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.512y_f_inl1_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.512y_f_inl1_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512y_f_inl1_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512y_f_inl1_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.512y_f_inl1_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.512y_f_inl1_hrd0/libmg5amc_common.so build.512y_f_inl1_hrd0/Parameters_sm.o build.512y_f_inl1_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512y_f_inl1_hrd0/libmg5amc_gg_ttx_cuda.so build.512y_f_inl1_hrd0/gCPPProcess.o build.512y_f_inl1_hrd0/gMatrixElementKernels.o build.512y_f_inl1_hrd0/gBridgeKernels.o build.512y_f_inl1_hrd0/gCrossSectionKernels.o build.512y_f_inl1_hrd0/fbridge_cu.o -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512y_f_inl1_hrd0/libmg5amc_gg_ttx_cpp.so build.512y_f_inl1_hrd0/CPPProcess.o build.512y_f_inl1_hrd0/MatrixElementKernels.o build.512y_f_inl1_hrd0/BridgeKernels.o build.512y_f_inl1_hrd0/CrossSectionKernels.o build.512y_f_inl1_hrd0/fbridge.o -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl1_hrd0/runTest.exe build.512y_f_inl1_hrd0/CPPProcess.o build.512y_f_inl1_hrd0/MatrixElementKernels.o build.512y_f_inl1_hrd0/BridgeKernels.o build.512y_f_inl1_hrd0/CrossSectionKernels.o build.512y_f_inl1_hrd0/RandomNumberKernels.o build.512y_f_inl1_hrd0/RamboSamplingKernels.o build.512y_f_inl1_hrd0/testxxx.o  build.512y_f_inl1_hrd0/testmisc.o  build.512y_f_inl1_hrd0/runTest.o build.512y_f_inl1_hrd0/gCPPProcess.o build.512y_f_inl1_hrd0/gMatrixElementKernels.o build.512y_f_inl1_hrd0/gBridgeKernels.o build.512y_f_inl1_hrd0/gCrossSectionKernels.o build.512y_f_inl1_hrd0/gRandomNumberKernels.o build.512y_f_inl1_hrd0/gRamboSamplingKernels.o build.512y_f_inl1_hrd0/testxxx_cu.o  build.512y_f_inl1_hrd0/testmisc_cu.o  build.512y_f_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_f_inl1_hrd0/check.exe build.512y_f_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_gg_ttx_cpp build.512y_f_inl1_hrd0/RandomNumberKernels.o build.512y_f_inl1_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_f_inl1_hrd0/fcheck.exe build.512y_f_inl1_hrd0/fcheck_sa.o build.512y_f_inl1_hrd0/fsampler.o -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_gg_ttx_cpp build.512y_f_inl1_hrd0/RandomNumberKernels.o build.512y_f_inl1_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl1_hrd0/gcheck.exe build.512y_f_inl1_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_gg_ttx_cuda build.512y_f_inl1_hrd0/gRandomNumberKernels.o build.512y_f_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl1_hrd0/fgcheck.exe build.512y_f_inl1_hrd0/fcheck_sa.o build.512y_f_inl1_hrd0/fsampler_cu.o -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_gg_ttx_cuda build.512y_f_inl1_hrd0/gRandomNumberKernels.o build.512y_f_inl1_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512y_f_inl1_hrd0/libmg5amc_gg_ttx_cuda.so build.512y_f_inl1_hrd0/gCPPProcess.o build.512y_f_inl1_hrd0/gMatrixElementKernels.o build.512y_f_inl1_hrd0/gBridgeKernels.o build.512y_f_inl1_hrd0/gCrossSectionKernels.o build.512y_f_inl1_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl1_hrd0/gcheck.exe build.512y_f_inl1_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl1_hrd0'  -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_gg_ttx_cuda build.512y_f_inl1_hrd0/gRandomNumberKernels.o build.512y_f_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl1_hrd0/fgcheck.exe build.512y_f_inl1_hrd0/fcheck_sa.o build.512y_f_inl1_hrd0/fsampler_cu.o -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl1_hrd0'  -lgfortran -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_gg_ttx_cuda build.512y_f_inl1_hrd0/gRandomNumberKernels.o build.512y_f_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512y_f_inl1_hrd0/libmg5amc_gg_ttx_cpp.so build.512y_f_inl1_hrd0/CPPProcess.o build.512y_f_inl1_hrd0/MatrixElementKernels.o build.512y_f_inl1_hrd0/BridgeKernels.o build.512y_f_inl1_hrd0/CrossSectionKernels.o build.512y_f_inl1_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_f_inl1_hrd0/fcheck.exe build.512y_f_inl1_hrd0/fcheck_sa.o build.512y_f_inl1_hrd0/fsampler.o -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_f_inl1_hrd0'  -lgfortran -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_gg_ttx_cpp build.512y_f_inl1_hrd0/RandomNumberKernels.o build.512y_f_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_f_inl1_hrd0/check.exe build.512y_f_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_f_inl1_hrd0'  -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_gg_ttx_cpp build.512y_f_inl1_hrd0/RandomNumberKernels.o build.512y_f_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl1_hrd0/runTest.exe build.512y_f_inl1_hrd0/CPPProcess.o build.512y_f_inl1_hrd0/MatrixElementKernels.o build.512y_f_inl1_hrd0/BridgeKernels.o build.512y_f_inl1_hrd0/CrossSectionKernels.o build.512y_f_inl1_hrd0/RandomNumberKernels.o build.512y_f_inl1_hrd0/RamboSamplingKernels.o build.512y_f_inl1_hrd0/testxxx.o  build.512y_f_inl1_hrd0/testmisc.o  build.512y_f_inl1_hrd0/runTest.o build.512y_f_inl1_hrd0/gCPPProcess.o build.512y_f_inl1_hrd0/gMatrixElementKernels.o build.512y_f_inl1_hrd0/gBridgeKernels.o build.512y_f_inl1_hrd0/gCrossSectionKernels.o build.512y_f_inl1_hrd0/gRandomNumberKernels.o build.512y_f_inl1_hrd0/gRamboSamplingKernels.o build.512y_f_inl1_hrd0/testxxx_cu.o  build.512y_f_inl1_hrd0/testmisc_cu.o  build.512y_f_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl1_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
 touch build.512y_f_inl1_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_f_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.512y_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_f_inl1_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_f_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512y_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_f_inl1_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.512y_f_inl1_hrd0/libmg5amc_gg_ttx_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_f_inl1_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512y_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_f_inl1_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:02:08
+DATE: 2022-09-24_23:51:04
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl1_hrd0/gcheck.exe -p 2048 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl1_hrd0/gcheck.exe -p 2048 256 4 OMP=
 Process                     = SIGMA_SM_GG_TTX_CUDA [nvcc 11.7.99 (gcc 11.2.0)] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK
 FP precision                = FLOAT (NaN/abnormal=0, zero=0)
-EvtsPerSec[Rmb+ME]     (23) = ( 9.770988e+07                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 3.160129e+08                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 3.634642e+08                 )  sec^-1
-MeanMatrixElemValue         = ( 2.086718e+00 +- 3.413389e-03 )  GeV^0
-TOTAL       :     0.543285 sec
-real	0m0.833s
-==PROF== Profiling "sigmaKin": launch__registers_per_thread 123
-==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100%
+EvtsPerSec[Rmb+ME]     (23) = ( 5.422093e+07                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 1.598137e+08                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 1.708350e+08                 )  sec^-1
+MeanMatrixElemValue         = ( 2.086388e+00 +- 2.416254e-03 )  GeV^0
+TOTAL       :     2.445733 sec
+real	0m2.932s
+   launch__registers_per_thread N/A
+   sm__sass_average_branch_targets_threads_uniform.pct N/A
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl1_hrd0/gcheck.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl1_hrd0/fgcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl1_hrd0/gcheck.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl1_hrd0/fgcheck.exe 2 64 2
 Avg ME (C++/CUDA)   = 2.028811e+00
 Avg ME (F77/CUDA)   = 2.0288500845199451
 Relative difference = 1.926474173540216e-05
@@ -2753,35 +2781,35 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:02:14 CEST 2022 Will execute './throughputX.sh -makej -ggtt -noneonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:51:31 CEST 2022 Will execute './throughputX.sh -makej -ggtt -noneonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -noneonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
 CUDACPP_BUILDDIR='build.none_d_inl0_hrd0'
 make: Nothing to be done for `all'.
 
-DATE: 2022-08-31_21:02:14
+DATE: 2022-09-24_23:51:31
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/check.exe -p 2048 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/check.exe -p 2048 256 4 OMP=
 Process                     = SIGMA_SM_GG_TTX_CPP [gcc 11.2.0] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CPP:DBL+CXS:CURHST+RMBHST+MESHST/none+NAVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = SCALAR ('none': ~vector[1], no SIMD)
-EvtsPerSec[Rmb+ME]     (23) = ( 1.804753e+05                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 1.912048e+05                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 1.912048e+05                 )  sec^-1
-MeanMatrixElemValue         = ( 2.086689e+00 +- 3.413217e-03 )  GeV^0
-TOTAL       :     5.963487 sec
-real	0m5.982s
+EvtsPerSec[Rmb+ME]     (23) = ( 1.809750e+05                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 1.917050e+05                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 1.917050e+05                 )  sec^-1
+MeanMatrixElemValue         = ( 2.086360e+00 +- 2.416141e-03 )  GeV^0
+TOTAL       :    11.811069 sec
+real	0m11.830s
 =Symbols in CPPProcess.o= (~sse4:  574) (avx2:    0) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 2.028807e+00
 Avg ME (F77/C++)    = 2.0288063388515649
 Relative difference = 3.258803992249869e-07
@@ -2789,35 +2817,35 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:02:22 CEST 2022 Will execute './throughputX.sh -makej -ggtt -noneonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:51:58 CEST 2022 Will execute './throughputX.sh -makej -ggtt -noneonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -noneonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
 CUDACPP_BUILDDIR='build.none_d_inl1_hrd0'
 make: Nothing to be done for `all'.
 
-DATE: 2022-08-31_21:02:22
+DATE: 2022-09-24_23:51:58
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl1_hrd0/check.exe -p 2048 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl1_hrd0/check.exe -p 2048 256 4 OMP=
 Process                     = SIGMA_SM_GG_TTX_CPP [gcc 11.2.0] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CPP:DBL+CXS:CURHST+RMBHST+MESHST/none+NAVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = SCALAR ('none': ~vector[1], no SIMD)
-EvtsPerSec[Rmb+ME]     (23) = ( 2.176698e+05                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 2.334977e+05                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 2.334977e+05                 )  sec^-1
-MeanMatrixElemValue         = ( 2.086689e+00 +- 3.413217e-03 )  GeV^0
-TOTAL       :     4.970779 sec
-real	0m4.989s
+EvtsPerSec[Rmb+ME]     (23) = ( 2.181181e+05                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 2.338710e+05                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 2.338710e+05                 )  sec^-1
+MeanMatrixElemValue         = ( 2.086360e+00 +- 2.416141e-03 )  GeV^0
+TOTAL       :     9.838015 sec
+real	0m9.857s
 =Symbols in CPPProcess.o= (~sse4:  654) (avx2:    0) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl1_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl1_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl1_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl1_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 2.028807e+00
 Avg ME (F77/C++)    = 2.0288063388515654
 Relative difference = 3.2588039900609506e-07
@@ -2825,35 +2853,35 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:02:29 CEST 2022 Will execute './throughputX.sh -makej -ggtt -noneonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:52:23 CEST 2022 Will execute './throughputX.sh -makej -ggtt -noneonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -noneonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
 CUDACPP_BUILDDIR='build.none_f_inl0_hrd0'
 make: Nothing to be done for `all'.
 
-DATE: 2022-08-31_21:02:29
+DATE: 2022-09-24_23:52:24
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/check.exe -p 2048 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/check.exe -p 2048 256 4 OMP=
 Process                     = SIGMA_SM_GG_TTX_CPP [gcc 11.2.0] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CPP:FLT+CXS:CURHST+RMBHST+MESHST/none+NAVBRK
 FP precision                = FLOAT (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = SCALAR ('none': ~vector[1], no SIMD)
-EvtsPerSec[Rmb+ME]     (23) = ( 1.906366e+05                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 1.999777e+05                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 1.999777e+05                 )  sec^-1
-MeanMatrixElemValue         = ( 2.086785e+00 +- 3.413819e-03 )  GeV^0
-TOTAL       :     5.607547 sec
-real	0m5.620s
+EvtsPerSec[Rmb+ME]     (23) = ( 1.912708e+05                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 2.006315e+05                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 2.006315e+05                 )  sec^-1
+MeanMatrixElemValue         = ( 2.086443e+00 +- 2.416487e-03 )  GeV^0
+TOTAL       :    11.137479 sec
+real	0m11.150s
 =Symbols in CPPProcess.o= (~sse4:  567) (avx2:    0) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 2.028820e+00
 Avg ME (F77/C++)    = 2.0288199546048418
 Relative difference = 2.2375153192025002e-08
@@ -2861,35 +2889,35 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:02:37 CEST 2022 Will execute './throughputX.sh -makej -ggtt -noneonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:52:50 CEST 2022 Will execute './throughputX.sh -makej -ggtt -noneonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -noneonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
 CUDACPP_BUILDDIR='build.none_f_inl1_hrd0'
 make: Nothing to be done for `all'.
 
-DATE: 2022-08-31_21:02:37
+DATE: 2022-09-24_23:52:50
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl1_hrd0/check.exe -p 2048 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl1_hrd0/check.exe -p 2048 256 4 OMP=
 Process                     = SIGMA_SM_GG_TTX_CPP [gcc 11.2.0] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CPP:FLT+CXS:CURHST+RMBHST+MESHST/none+NAVBRK
 FP precision                = FLOAT (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = SCALAR ('none': ~vector[1], no SIMD)
-EvtsPerSec[Rmb+ME]     (23) = ( 2.288251e+05                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 2.424429e+05                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 2.424429e+05                 )  sec^-1
-MeanMatrixElemValue         = ( 2.086785e+00 +- 3.413819e-03 )  GeV^0
-TOTAL       :     4.690572 sec
-real	0m4.703s
+EvtsPerSec[Rmb+ME]     (23) = ( 2.297118e+05                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 2.433615e+05                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 2.433615e+05                 )  sec^-1
+MeanMatrixElemValue         = ( 2.086443e+00 +- 2.416487e-03 )  GeV^0
+TOTAL       :     9.303542 sec
+real	0m9.316s
 =Symbols in CPPProcess.o= (~sse4:  685) (avx2:    0) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl1_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl1_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl1_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl1_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 2.028820e+00
 Avg ME (F77/C++)    = 2.0288199669448659
 Relative difference = 1.629278801736432e-08
@@ -2897,13 +2925,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:02:44 CEST 2022 Will execute './throughputX.sh -makej -ggtt -sse4only  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:53:14 CEST 2022 Will execute './throughputX.sh -makej -ggtt -sse4only  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -sse4only implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
 CUDACPP_BUILDDIR='build.sse4_d_inl0_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -2913,71 +2941,72 @@ HELINL=0
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.sse4_d_inl0_hrd0 for tag=sse4_d_inl0_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.sse4_d_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gcheck_sa.cu -o build.sse4_d_inl0_hrd0/gcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gCPPProcess.cu -o build.sse4_d_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gcheck_sa.cu -o build.sse4_d_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gCPPProcess.cu -o build.sse4_d_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.sse4_d_inl0_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gBridgeKernels.cu -o build.sse4_d_inl0_hrd0/gBridgeKernels.o
 AVX=sse4
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.sse4_d_inl0_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gBridgeKernels.cu -o build.sse4_d_inl0_hrd0/gBridgeKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.sse4_d_inl0_hrd0/gCrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -c read_slha.cc -o build.sse4_d_inl0_hrd0/read_slha.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -c Parameters_sm.cc -o build.sse4_d_inl0_hrd0/Parameters_sm.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fbridge.cc -o build.sse4_d_inl0_hrd0/fbridge_cu.o
-mkdir -p ../lib/build.sse4_d_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.sse4_d_inl0_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.sse4_d_inl0_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.sse4_d_inl0_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fbridge.cc -o build.sse4_d_inl0_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.sse4_d_inl0_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.sse4_d_inl0_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.sse4_d_inl0_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.sse4_d_inl0_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.sse4_d_inl0_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.sse4_d_inl0_hrd0/BridgeKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.sse4_d_inl0_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.sse4_d_inl0_hrd0/fbridge.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.sse4_d_inl0_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.sse4_d_inl0_hrd0/RandomNumberKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -c read_slha.cc -o build.sse4_d_inl0_hrd0/read_slha.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.sse4_d_inl0_hrd0/RamboSamplingKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -c Parameters_sm.cc -o build.sse4_d_inl0_hrd0/Parameters_sm.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.sse4_d_inl0_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testxxx.cc -o build.sse4_d_inl0_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testxxx.cc -o build.sse4_d_inl0_hrd0/testxxx_cu.o
+mkdir -p ../lib/build.sse4_d_inl0_hrd0
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.sse4_d_inl0_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testmisc.cc -o build.sse4_d_inl0_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testmisc.cc -o build.sse4_d_inl0_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.sse4_d_inl0_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu runTest.cc -o build.sse4_d_inl0_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu runTest.cc -o build.sse4_d_inl0_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.sse4_d_inl0_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fsampler.cc -o build.sse4_d_inl0_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fsampler.cc -o build.sse4_d_inl0_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.sse4_d_inl0_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.sse4_d_inl0_hrd0/libmg5amc_common.so build.sse4_d_inl0_hrd0/Parameters_sm.o build.sse4_d_inl0_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.sse4_d_inl0_hrd0/libmg5amc_gg_ttx_cuda.so build.sse4_d_inl0_hrd0/gCPPProcess.o build.sse4_d_inl0_hrd0/gMatrixElementKernels.o build.sse4_d_inl0_hrd0/gBridgeKernels.o build.sse4_d_inl0_hrd0/gCrossSectionKernels.o build.sse4_d_inl0_hrd0/fbridge_cu.o -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.sse4_d_inl0_hrd0/libmg5amc_gg_ttx_cpp.so build.sse4_d_inl0_hrd0/CPPProcess.o build.sse4_d_inl0_hrd0/MatrixElementKernels.o build.sse4_d_inl0_hrd0/BridgeKernels.o build.sse4_d_inl0_hrd0/CrossSectionKernels.o build.sse4_d_inl0_hrd0/fbridge.o -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl0_hrd0/runTest.exe build.sse4_d_inl0_hrd0/CPPProcess.o build.sse4_d_inl0_hrd0/MatrixElementKernels.o build.sse4_d_inl0_hrd0/BridgeKernels.o build.sse4_d_inl0_hrd0/CrossSectionKernels.o build.sse4_d_inl0_hrd0/RandomNumberKernels.o build.sse4_d_inl0_hrd0/RamboSamplingKernels.o build.sse4_d_inl0_hrd0/testxxx.o  build.sse4_d_inl0_hrd0/testmisc.o  build.sse4_d_inl0_hrd0/runTest.o build.sse4_d_inl0_hrd0/gCPPProcess.o build.sse4_d_inl0_hrd0/gMatrixElementKernels.o build.sse4_d_inl0_hrd0/gBridgeKernels.o build.sse4_d_inl0_hrd0/gCrossSectionKernels.o build.sse4_d_inl0_hrd0/gRandomNumberKernels.o build.sse4_d_inl0_hrd0/gRamboSamplingKernels.o build.sse4_d_inl0_hrd0/testxxx_cu.o  build.sse4_d_inl0_hrd0/testmisc_cu.o  build.sse4_d_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_d_inl0_hrd0/check.exe build.sse4_d_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_gg_ttx_cpp build.sse4_d_inl0_hrd0/RandomNumberKernels.o build.sse4_d_inl0_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_d_inl0_hrd0/fcheck.exe build.sse4_d_inl0_hrd0/fcheck_sa.o build.sse4_d_inl0_hrd0/fsampler.o -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_gg_ttx_cpp build.sse4_d_inl0_hrd0/RandomNumberKernels.o build.sse4_d_inl0_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl0_hrd0/gcheck.exe build.sse4_d_inl0_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_gg_ttx_cuda build.sse4_d_inl0_hrd0/gRandomNumberKernels.o build.sse4_d_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl0_hrd0/fgcheck.exe build.sse4_d_inl0_hrd0/fcheck_sa.o build.sse4_d_inl0_hrd0/fsampler_cu.o -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_gg_ttx_cuda build.sse4_d_inl0_hrd0/gRandomNumberKernels.o build.sse4_d_inl0_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.sse4_d_inl0_hrd0/libmg5amc_gg_ttx_cuda.so build.sse4_d_inl0_hrd0/gCPPProcess.o build.sse4_d_inl0_hrd0/gMatrixElementKernels.o build.sse4_d_inl0_hrd0/gBridgeKernels.o build.sse4_d_inl0_hrd0/gCrossSectionKernels.o build.sse4_d_inl0_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.sse4_d_inl0_hrd0/libmg5amc_gg_ttx_cpp.so build.sse4_d_inl0_hrd0/CPPProcess.o build.sse4_d_inl0_hrd0/MatrixElementKernels.o build.sse4_d_inl0_hrd0/BridgeKernels.o build.sse4_d_inl0_hrd0/CrossSectionKernels.o build.sse4_d_inl0_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_d_inl0_hrd0/fcheck.exe build.sse4_d_inl0_hrd0/fcheck_sa.o build.sse4_d_inl0_hrd0/fsampler.o -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_d_inl0_hrd0'  -lgfortran -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_gg_ttx_cpp build.sse4_d_inl0_hrd0/RandomNumberKernels.o build.sse4_d_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl0_hrd0/gcheck.exe build.sse4_d_inl0_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl0_hrd0'  -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_gg_ttx_cuda build.sse4_d_inl0_hrd0/gRandomNumberKernels.o build.sse4_d_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl0_hrd0/fgcheck.exe build.sse4_d_inl0_hrd0/fcheck_sa.o build.sse4_d_inl0_hrd0/fsampler_cu.o -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl0_hrd0'  -lgfortran -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_gg_ttx_cuda build.sse4_d_inl0_hrd0/gRandomNumberKernels.o build.sse4_d_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_d_inl0_hrd0/check.exe build.sse4_d_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_d_inl0_hrd0'  -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_gg_ttx_cpp build.sse4_d_inl0_hrd0/RandomNumberKernels.o build.sse4_d_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl0_hrd0/runTest.exe build.sse4_d_inl0_hrd0/CPPProcess.o build.sse4_d_inl0_hrd0/MatrixElementKernels.o build.sse4_d_inl0_hrd0/BridgeKernels.o build.sse4_d_inl0_hrd0/CrossSectionKernels.o build.sse4_d_inl0_hrd0/RandomNumberKernels.o build.sse4_d_inl0_hrd0/RamboSamplingKernels.o build.sse4_d_inl0_hrd0/testxxx.o  build.sse4_d_inl0_hrd0/testmisc.o  build.sse4_d_inl0_hrd0/runTest.o build.sse4_d_inl0_hrd0/gCPPProcess.o build.sse4_d_inl0_hrd0/gMatrixElementKernels.o build.sse4_d_inl0_hrd0/gBridgeKernels.o build.sse4_d_inl0_hrd0/gCrossSectionKernels.o build.sse4_d_inl0_hrd0/gRandomNumberKernels.o build.sse4_d_inl0_hrd0/gRamboSamplingKernels.o build.sse4_d_inl0_hrd0/testxxx_cu.o  build.sse4_d_inl0_hrd0/testmisc_cu.o  build.sse4_d_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl0_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
 touch build.sse4_d_inl0_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_d_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.sse4_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_d_inl0_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_d_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.sse4_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_d_inl0_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.sse4_d_inl0_hrd0/libmg5amc_gg_ttx_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_d_inl0_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.sse4_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_d_inl0_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:02:45
+DATE: 2022-09-24_23:53:24
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/check.exe -p 2048 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/check.exe -p 2048 256 4 OMP=
 Process                     = SIGMA_SM_GG_TTX_CPP [gcc 11.2.0] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CPP:DBL+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 2.905162e+05                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 3.204438e+05                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 3.204438e+05                 )  sec^-1
-MeanMatrixElemValue         = ( 2.086689e+00 +- 3.413217e-03 )  GeV^0
-TOTAL       :     3.760526 sec
-real	0m3.778s
+EvtsPerSec[Rmb+ME]     (23) = ( 2.921624e+05                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 3.223116e+05                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 3.223116e+05                 )  sec^-1
+MeanMatrixElemValue         = ( 2.086360e+00 +- 2.416141e-03 )  GeV^0
+TOTAL       :     7.398591 sec
+real	0m7.417s
 =Symbols in CPPProcess.o= (~sse4: 2495) (avx2:    0) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 2.028807e+00
 Avg ME (F77/C++)    = 2.0288063388515654
 Relative difference = 3.2588039900609506e-07
@@ -2985,13 +3014,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:02:51 CEST 2022 Will execute './throughputX.sh -makej -ggtt -sse4only  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:53:46 CEST 2022 Will execute './throughputX.sh -makej -ggtt -sse4only  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -sse4only implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
 CUDACPP_BUILDDIR='build.sse4_d_inl1_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -3001,71 +3030,72 @@ HELINL=1
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.sse4_d_inl1_hrd0 for tag=sse4_d_inl1_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.sse4_d_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.sse4_d_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.sse4_d_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.sse4_d_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.sse4_d_inl1_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.sse4_d_inl1_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.sse4_d_inl1_hrd0/gCrossSectionKernels.o
 AVX=sse4
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.sse4_d_inl1_hrd0/gCPPProcess.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.sse4_d_inl1_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.sse4_d_inl1_hrd0/read_slha.o
-mkdir -p ../lib/build.sse4_d_inl1_hrd0
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.sse4_d_inl1_hrd0/libmg5amc_common.so build.sse4_d_inl1_hrd0/Parameters_sm.o build.sse4_d_inl1_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.sse4_d_inl1_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.sse4_d_inl1_hrd0/gBridgeKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.sse4_d_inl1_hrd0/gCrossSectionKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.sse4_d_inl1_hrd0/fbridge_cu.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.sse4_d_inl1_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.sse4_d_inl1_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.sse4_d_inl1_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.sse4_d_inl1_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.sse4_d_inl1_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.sse4_d_inl1_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.sse4_d_inl1_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.sse4_d_inl1_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.sse4_d_inl1_hrd0/BridgeKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.sse4_d_inl1_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.sse4_d_inl1_hrd0/fbridge.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.sse4_d_inl1_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.sse4_d_inl1_hrd0/RamboSamplingKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.sse4_d_inl1_hrd0/Parameters_sm.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.sse4_d_inl1_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.sse4_d_inl1_hrd0/testxxx_cu.o
+mkdir -p ../lib/build.sse4_d_inl1_hrd0
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.sse4_d_inl1_hrd0/read_slha.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.sse4_d_inl1_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.sse4_d_inl1_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.sse4_d_inl1_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.sse4_d_inl1_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.sse4_d_inl1_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.sse4_d_inl1_hrd0/runTest_cu.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.sse4_d_inl1_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.sse4_d_inl1_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.sse4_d_inl1_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.sse4_d_inl1_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.sse4_d_inl1_hrd0/fsampler.o
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.sse4_d_inl1_hrd0/libmg5amc_gg_ttx_cuda.so build.sse4_d_inl1_hrd0/gCPPProcess.o build.sse4_d_inl1_hrd0/gMatrixElementKernels.o build.sse4_d_inl1_hrd0/gBridgeKernels.o build.sse4_d_inl1_hrd0/gCrossSectionKernels.o build.sse4_d_inl1_hrd0/fbridge_cu.o -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.sse4_d_inl1_hrd0/libmg5amc_gg_ttx_cpp.so build.sse4_d_inl1_hrd0/CPPProcess.o build.sse4_d_inl1_hrd0/MatrixElementKernels.o build.sse4_d_inl1_hrd0/BridgeKernels.o build.sse4_d_inl1_hrd0/CrossSectionKernels.o build.sse4_d_inl1_hrd0/fbridge.o -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl1_hrd0/runTest.exe build.sse4_d_inl1_hrd0/CPPProcess.o build.sse4_d_inl1_hrd0/MatrixElementKernels.o build.sse4_d_inl1_hrd0/BridgeKernels.o build.sse4_d_inl1_hrd0/CrossSectionKernels.o build.sse4_d_inl1_hrd0/RandomNumberKernels.o build.sse4_d_inl1_hrd0/RamboSamplingKernels.o build.sse4_d_inl1_hrd0/testxxx.o  build.sse4_d_inl1_hrd0/testmisc.o  build.sse4_d_inl1_hrd0/runTest.o build.sse4_d_inl1_hrd0/gCPPProcess.o build.sse4_d_inl1_hrd0/gMatrixElementKernels.o build.sse4_d_inl1_hrd0/gBridgeKernels.o build.sse4_d_inl1_hrd0/gCrossSectionKernels.o build.sse4_d_inl1_hrd0/gRandomNumberKernels.o build.sse4_d_inl1_hrd0/gRamboSamplingKernels.o build.sse4_d_inl1_hrd0/testxxx_cu.o  build.sse4_d_inl1_hrd0/testmisc_cu.o  build.sse4_d_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_d_inl1_hrd0/check.exe build.sse4_d_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_gg_ttx_cpp build.sse4_d_inl1_hrd0/RandomNumberKernels.o build.sse4_d_inl1_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_d_inl1_hrd0/fcheck.exe build.sse4_d_inl1_hrd0/fcheck_sa.o build.sse4_d_inl1_hrd0/fsampler.o -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_gg_ttx_cpp build.sse4_d_inl1_hrd0/RandomNumberKernels.o build.sse4_d_inl1_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl1_hrd0/gcheck.exe build.sse4_d_inl1_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_gg_ttx_cuda build.sse4_d_inl1_hrd0/gRandomNumberKernels.o build.sse4_d_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl1_hrd0/fgcheck.exe build.sse4_d_inl1_hrd0/fcheck_sa.o build.sse4_d_inl1_hrd0/fsampler_cu.o -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_gg_ttx_cuda build.sse4_d_inl1_hrd0/gRandomNumberKernels.o build.sse4_d_inl1_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.sse4_d_inl1_hrd0/libmg5amc_common.so build.sse4_d_inl1_hrd0/Parameters_sm.o build.sse4_d_inl1_hrd0/read_slha.o
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.sse4_d_inl1_hrd0/libmg5amc_gg_ttx_cuda.so build.sse4_d_inl1_hrd0/gCPPProcess.o build.sse4_d_inl1_hrd0/gMatrixElementKernels.o build.sse4_d_inl1_hrd0/gBridgeKernels.o build.sse4_d_inl1_hrd0/gCrossSectionKernels.o build.sse4_d_inl1_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl1_hrd0/gcheck.exe build.sse4_d_inl1_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl1_hrd0'  -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_gg_ttx_cuda build.sse4_d_inl1_hrd0/gRandomNumberKernels.o build.sse4_d_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl1_hrd0/fgcheck.exe build.sse4_d_inl1_hrd0/fcheck_sa.o build.sse4_d_inl1_hrd0/fsampler_cu.o -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl1_hrd0'  -lgfortran -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_gg_ttx_cuda build.sse4_d_inl1_hrd0/gRandomNumberKernels.o build.sse4_d_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.sse4_d_inl1_hrd0/libmg5amc_gg_ttx_cpp.so build.sse4_d_inl1_hrd0/CPPProcess.o build.sse4_d_inl1_hrd0/MatrixElementKernels.o build.sse4_d_inl1_hrd0/BridgeKernels.o build.sse4_d_inl1_hrd0/CrossSectionKernels.o build.sse4_d_inl1_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_d_inl1_hrd0/fcheck.exe build.sse4_d_inl1_hrd0/fcheck_sa.o build.sse4_d_inl1_hrd0/fsampler.o -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_d_inl1_hrd0'  -lgfortran -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_gg_ttx_cpp build.sse4_d_inl1_hrd0/RandomNumberKernels.o build.sse4_d_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_d_inl1_hrd0/check.exe build.sse4_d_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_d_inl1_hrd0'  -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_gg_ttx_cpp build.sse4_d_inl1_hrd0/RandomNumberKernels.o build.sse4_d_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl1_hrd0/runTest.exe build.sse4_d_inl1_hrd0/CPPProcess.o build.sse4_d_inl1_hrd0/MatrixElementKernels.o build.sse4_d_inl1_hrd0/BridgeKernels.o build.sse4_d_inl1_hrd0/CrossSectionKernels.o build.sse4_d_inl1_hrd0/RandomNumberKernels.o build.sse4_d_inl1_hrd0/RamboSamplingKernels.o build.sse4_d_inl1_hrd0/testxxx.o  build.sse4_d_inl1_hrd0/testmisc.o  build.sse4_d_inl1_hrd0/runTest.o build.sse4_d_inl1_hrd0/gCPPProcess.o build.sse4_d_inl1_hrd0/gMatrixElementKernels.o build.sse4_d_inl1_hrd0/gBridgeKernels.o build.sse4_d_inl1_hrd0/gCrossSectionKernels.o build.sse4_d_inl1_hrd0/gRandomNumberKernels.o build.sse4_d_inl1_hrd0/gRamboSamplingKernels.o build.sse4_d_inl1_hrd0/testxxx_cu.o  build.sse4_d_inl1_hrd0/testmisc_cu.o  build.sse4_d_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl1_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
 touch build.sse4_d_inl1_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_d_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.sse4_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_d_inl1_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_d_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.sse4_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_d_inl1_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.sse4_d_inl1_hrd0/libmg5amc_gg_ttx_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_d_inl1_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.sse4_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_d_inl1_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:02:52
+DATE: 2022-09-24_23:53:53
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl1_hrd0/check.exe -p 2048 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl1_hrd0/check.exe -p 2048 256 4 OMP=
 Process                     = SIGMA_SM_GG_TTX_CPP [gcc 11.2.0] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CPP:DBL+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 2.541101e+05                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 2.768175e+05                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 2.768175e+05                 )  sec^-1
-MeanMatrixElemValue         = ( 2.086689e+00 +- 3.413217e-03 )  GeV^0
-TOTAL       :     4.279488 sec
-real	0m4.299s
+EvtsPerSec[Rmb+ME]     (23) = ( 2.556190e+05                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 2.784071e+05                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 2.784071e+05                 )  sec^-1
+MeanMatrixElemValue         = ( 2.086360e+00 +- 2.416141e-03 )  GeV^0
+TOTAL       :     8.424424 sec
+real	0m8.443s
 =Symbols in CPPProcess.o= (~sse4: 2598) (avx2:    0) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl1_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl1_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl1_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl1_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 2.028807e+00
 Avg ME (F77/C++)    = 2.0288063388515649
 Relative difference = 3.258803992249869e-07
@@ -3073,13 +3103,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:02:59 CEST 2022 Will execute './throughputX.sh -makej -ggtt -sse4only -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:54:17 CEST 2022 Will execute './throughputX.sh -makej -ggtt -sse4only -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -sse4only implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
 CUDACPP_BUILDDIR='build.sse4_f_inl0_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -3089,71 +3119,72 @@ HELINL=0
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.sse4_f_inl0_hrd0 for tag=sse4_f_inl0_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.sse4_f_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gcheck_sa.cu -o build.sse4_f_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gcheck_sa.cu -o build.sse4_f_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gCPPProcess.cu -o build.sse4_f_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.sse4_f_inl0_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gBridgeKernels.cu -o build.sse4_f_inl0_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.sse4_f_inl0_hrd0/gCrossSectionKernels.o
 AVX=sse4
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gCPPProcess.cu -o build.sse4_f_inl0_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.sse4_f_inl0_hrd0/gMatrixElementKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gBridgeKernels.cu -o build.sse4_f_inl0_hrd0/gBridgeKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.sse4_f_inl0_hrd0/gCrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -c Parameters_sm.cc -o build.sse4_f_inl0_hrd0/Parameters_sm.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fbridge.cc -o build.sse4_f_inl0_hrd0/fbridge_cu.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -c read_slha.cc -o build.sse4_f_inl0_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.sse4_f_inl0_hrd0/gRandomNumberKernels.o
-mkdir -p ../lib/build.sse4_f_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.sse4_f_inl0_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fbridge.cc -o build.sse4_f_inl0_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.sse4_f_inl0_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.sse4_f_inl0_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.sse4_f_inl0_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.sse4_f_inl0_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.sse4_f_inl0_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.sse4_f_inl0_hrd0/BridgeKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.sse4_f_inl0_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.sse4_f_inl0_hrd0/fbridge.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -c Parameters_sm.cc -o build.sse4_f_inl0_hrd0/Parameters_sm.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -c read_slha.cc -o build.sse4_f_inl0_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.sse4_f_inl0_hrd0/RandomNumberKernels.o
+mkdir -p ../lib/build.sse4_f_inl0_hrd0
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.sse4_f_inl0_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.sse4_f_inl0_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testxxx.cc -o build.sse4_f_inl0_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testxxx.cc -o build.sse4_f_inl0_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.sse4_f_inl0_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testmisc.cc -o build.sse4_f_inl0_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testmisc.cc -o build.sse4_f_inl0_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.sse4_f_inl0_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu runTest.cc -o build.sse4_f_inl0_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu runTest.cc -o build.sse4_f_inl0_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.sse4_f_inl0_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fsampler.cc -o build.sse4_f_inl0_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fsampler.cc -o build.sse4_f_inl0_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.sse4_f_inl0_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.sse4_f_inl0_hrd0/libmg5amc_common.so build.sse4_f_inl0_hrd0/Parameters_sm.o build.sse4_f_inl0_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.sse4_f_inl0_hrd0/libmg5amc_gg_ttx_cuda.so build.sse4_f_inl0_hrd0/gCPPProcess.o build.sse4_f_inl0_hrd0/gMatrixElementKernels.o build.sse4_f_inl0_hrd0/gBridgeKernels.o build.sse4_f_inl0_hrd0/gCrossSectionKernels.o build.sse4_f_inl0_hrd0/fbridge_cu.o -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.sse4_f_inl0_hrd0/libmg5amc_gg_ttx_cpp.so build.sse4_f_inl0_hrd0/CPPProcess.o build.sse4_f_inl0_hrd0/MatrixElementKernels.o build.sse4_f_inl0_hrd0/BridgeKernels.o build.sse4_f_inl0_hrd0/CrossSectionKernels.o build.sse4_f_inl0_hrd0/fbridge.o -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl0_hrd0/runTest.exe build.sse4_f_inl0_hrd0/CPPProcess.o build.sse4_f_inl0_hrd0/MatrixElementKernels.o build.sse4_f_inl0_hrd0/BridgeKernels.o build.sse4_f_inl0_hrd0/CrossSectionKernels.o build.sse4_f_inl0_hrd0/RandomNumberKernels.o build.sse4_f_inl0_hrd0/RamboSamplingKernels.o build.sse4_f_inl0_hrd0/testxxx.o  build.sse4_f_inl0_hrd0/testmisc.o  build.sse4_f_inl0_hrd0/runTest.o build.sse4_f_inl0_hrd0/gCPPProcess.o build.sse4_f_inl0_hrd0/gMatrixElementKernels.o build.sse4_f_inl0_hrd0/gBridgeKernels.o build.sse4_f_inl0_hrd0/gCrossSectionKernels.o build.sse4_f_inl0_hrd0/gRandomNumberKernels.o build.sse4_f_inl0_hrd0/gRamboSamplingKernels.o build.sse4_f_inl0_hrd0/testxxx_cu.o  build.sse4_f_inl0_hrd0/testmisc_cu.o  build.sse4_f_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_f_inl0_hrd0/check.exe build.sse4_f_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_gg_ttx_cpp build.sse4_f_inl0_hrd0/RandomNumberKernels.o build.sse4_f_inl0_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_f_inl0_hrd0/fcheck.exe build.sse4_f_inl0_hrd0/fcheck_sa.o build.sse4_f_inl0_hrd0/fsampler.o -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_gg_ttx_cpp build.sse4_f_inl0_hrd0/RandomNumberKernels.o build.sse4_f_inl0_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl0_hrd0/gcheck.exe build.sse4_f_inl0_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_gg_ttx_cuda build.sse4_f_inl0_hrd0/gRandomNumberKernels.o build.sse4_f_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl0_hrd0/fgcheck.exe build.sse4_f_inl0_hrd0/fcheck_sa.o build.sse4_f_inl0_hrd0/fsampler_cu.o -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_gg_ttx_cuda build.sse4_f_inl0_hrd0/gRandomNumberKernels.o build.sse4_f_inl0_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.sse4_f_inl0_hrd0/libmg5amc_gg_ttx_cuda.so build.sse4_f_inl0_hrd0/gCPPProcess.o build.sse4_f_inl0_hrd0/gMatrixElementKernels.o build.sse4_f_inl0_hrd0/gBridgeKernels.o build.sse4_f_inl0_hrd0/gCrossSectionKernels.o build.sse4_f_inl0_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.sse4_f_inl0_hrd0/libmg5amc_gg_ttx_cpp.so build.sse4_f_inl0_hrd0/CPPProcess.o build.sse4_f_inl0_hrd0/MatrixElementKernels.o build.sse4_f_inl0_hrd0/BridgeKernels.o build.sse4_f_inl0_hrd0/CrossSectionKernels.o build.sse4_f_inl0_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_f_inl0_hrd0/fcheck.exe build.sse4_f_inl0_hrd0/fcheck_sa.o build.sse4_f_inl0_hrd0/fsampler.o -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_f_inl0_hrd0'  -lgfortran -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_gg_ttx_cpp build.sse4_f_inl0_hrd0/RandomNumberKernels.o build.sse4_f_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl0_hrd0/gcheck.exe build.sse4_f_inl0_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl0_hrd0'  -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_gg_ttx_cuda build.sse4_f_inl0_hrd0/gRandomNumberKernels.o build.sse4_f_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl0_hrd0/fgcheck.exe build.sse4_f_inl0_hrd0/fcheck_sa.o build.sse4_f_inl0_hrd0/fsampler_cu.o -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl0_hrd0'  -lgfortran -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_gg_ttx_cuda build.sse4_f_inl0_hrd0/gRandomNumberKernels.o build.sse4_f_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_f_inl0_hrd0/check.exe build.sse4_f_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_f_inl0_hrd0'  -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_gg_ttx_cpp build.sse4_f_inl0_hrd0/RandomNumberKernels.o build.sse4_f_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl0_hrd0/runTest.exe build.sse4_f_inl0_hrd0/CPPProcess.o build.sse4_f_inl0_hrd0/MatrixElementKernels.o build.sse4_f_inl0_hrd0/BridgeKernels.o build.sse4_f_inl0_hrd0/CrossSectionKernels.o build.sse4_f_inl0_hrd0/RandomNumberKernels.o build.sse4_f_inl0_hrd0/RamboSamplingKernels.o build.sse4_f_inl0_hrd0/testxxx.o  build.sse4_f_inl0_hrd0/testmisc.o  build.sse4_f_inl0_hrd0/runTest.o build.sse4_f_inl0_hrd0/gCPPProcess.o build.sse4_f_inl0_hrd0/gMatrixElementKernels.o build.sse4_f_inl0_hrd0/gBridgeKernels.o build.sse4_f_inl0_hrd0/gCrossSectionKernels.o build.sse4_f_inl0_hrd0/gRandomNumberKernels.o build.sse4_f_inl0_hrd0/gRamboSamplingKernels.o build.sse4_f_inl0_hrd0/testxxx_cu.o  build.sse4_f_inl0_hrd0/testmisc_cu.o  build.sse4_f_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl0_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
 touch build.sse4_f_inl0_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_f_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.sse4_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_f_inl0_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_f_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.sse4_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_f_inl0_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.sse4_f_inl0_hrd0/libmg5amc_gg_ttx_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_f_inl0_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.sse4_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_f_inl0_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:03:00
+DATE: 2022-09-24_23:54:27
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/check.exe -p 2048 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/check.exe -p 2048 256 4 OMP=
 Process                     = SIGMA_SM_GG_TTX_CPP [gcc 11.2.0] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CPP:FLT+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK
 FP precision                = FLOAT (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 4.246878e+05                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 4.763727e+05                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 4.763727e+05                 )  sec^-1
-MeanMatrixElemValue         = ( 2.086786e+00 +- 3.413831e-03 )  GeV^0
-TOTAL       :     2.575232 sec
-real	0m2.588s
+EvtsPerSec[Rmb+ME]     (23) = ( 4.263577e+05                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 4.782321e+05                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 4.782321e+05                 )  sec^-1
+MeanMatrixElemValue         = ( 2.086445e+00 +- 2.416494e-03 )  GeV^0
+TOTAL       :     5.089622 sec
+real	0m5.102s
 =Symbols in CPPProcess.o= (~sse4: 3079) (avx2:    0) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 2.028820e+00
 Avg ME (F77/C++)    = 2.0288199189817533
 Relative difference = 3.993367907359264e-08
@@ -3161,13 +3192,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:03:05 CEST 2022 Will execute './throughputX.sh -makej -ggtt -sse4only -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:54:47 CEST 2022 Will execute './throughputX.sh -makej -ggtt -sse4only -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -sse4only implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
 CUDACPP_BUILDDIR='build.sse4_f_inl1_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -3177,22 +3208,18 @@ HELINL=1
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.sse4_f_inl1_hrd0 for tag=sse4_f_inl1_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.sse4_f_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.sse4_f_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.sse4_f_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.sse4_f_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.sse4_f_inl1_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.sse4_f_inl1_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.sse4_f_inl1_hrd0/gCrossSectionKernels.o
 AVX=sse4
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.sse4_f_inl1_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.sse4_f_inl1_hrd0/gMatrixElementKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.sse4_f_inl1_hrd0/gBridgeKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.sse4_f_inl1_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.sse4_f_inl1_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.sse4_f_inl1_hrd0/gCrossSectionKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.sse4_f_inl1_hrd0/fbridge_cu.o
-mkdir -p ../lib/build.sse4_f_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.sse4_f_inl1_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.sse4_f_inl1_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.sse4_f_inl1_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.sse4_f_inl1_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.sse4_f_inl1_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.sse4_f_inl1_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.sse4_f_inl1_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.sse4_f_inl1_hrd0/MatrixElementKernels.o
@@ -3200,48 +3227,53 @@ ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.sse4_f_inl1_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.sse4_f_inl1_hrd0/fbridge.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.sse4_f_inl1_hrd0/RandomNumberKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.sse4_f_inl1_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.sse4_f_inl1_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.sse4_f_inl1_hrd0/testxxx_cu.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.sse4_f_inl1_hrd0/Parameters_sm.o
+mkdir -p ../lib/build.sse4_f_inl1_hrd0
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.sse4_f_inl1_hrd0/read_slha.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.sse4_f_inl1_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.sse4_f_inl1_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.sse4_f_inl1_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.sse4_f_inl1_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.sse4_f_inl1_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.sse4_f_inl1_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.sse4_f_inl1_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.sse4_f_inl1_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.sse4_f_inl1_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.sse4_f_inl1_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.sse4_f_inl1_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.sse4_f_inl1_hrd0/libmg5amc_common.so build.sse4_f_inl1_hrd0/Parameters_sm.o build.sse4_f_inl1_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.sse4_f_inl1_hrd0/libmg5amc_gg_ttx_cuda.so build.sse4_f_inl1_hrd0/gCPPProcess.o build.sse4_f_inl1_hrd0/gMatrixElementKernels.o build.sse4_f_inl1_hrd0/gBridgeKernels.o build.sse4_f_inl1_hrd0/gCrossSectionKernels.o build.sse4_f_inl1_hrd0/fbridge_cu.o -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.sse4_f_inl1_hrd0/libmg5amc_gg_ttx_cpp.so build.sse4_f_inl1_hrd0/CPPProcess.o build.sse4_f_inl1_hrd0/MatrixElementKernels.o build.sse4_f_inl1_hrd0/BridgeKernels.o build.sse4_f_inl1_hrd0/CrossSectionKernels.o build.sse4_f_inl1_hrd0/fbridge.o -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl1_hrd0/runTest.exe build.sse4_f_inl1_hrd0/CPPProcess.o build.sse4_f_inl1_hrd0/MatrixElementKernels.o build.sse4_f_inl1_hrd0/BridgeKernels.o build.sse4_f_inl1_hrd0/CrossSectionKernels.o build.sse4_f_inl1_hrd0/RandomNumberKernels.o build.sse4_f_inl1_hrd0/RamboSamplingKernels.o build.sse4_f_inl1_hrd0/testxxx.o  build.sse4_f_inl1_hrd0/testmisc.o  build.sse4_f_inl1_hrd0/runTest.o build.sse4_f_inl1_hrd0/gCPPProcess.o build.sse4_f_inl1_hrd0/gMatrixElementKernels.o build.sse4_f_inl1_hrd0/gBridgeKernels.o build.sse4_f_inl1_hrd0/gCrossSectionKernels.o build.sse4_f_inl1_hrd0/gRandomNumberKernels.o build.sse4_f_inl1_hrd0/gRamboSamplingKernels.o build.sse4_f_inl1_hrd0/testxxx_cu.o  build.sse4_f_inl1_hrd0/testmisc_cu.o  build.sse4_f_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_f_inl1_hrd0/check.exe build.sse4_f_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_gg_ttx_cpp build.sse4_f_inl1_hrd0/RandomNumberKernels.o build.sse4_f_inl1_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_f_inl1_hrd0/fcheck.exe build.sse4_f_inl1_hrd0/fcheck_sa.o build.sse4_f_inl1_hrd0/fsampler.o -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_gg_ttx_cpp build.sse4_f_inl1_hrd0/RandomNumberKernels.o build.sse4_f_inl1_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl1_hrd0/gcheck.exe build.sse4_f_inl1_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_gg_ttx_cuda build.sse4_f_inl1_hrd0/gRandomNumberKernels.o build.sse4_f_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl1_hrd0/fgcheck.exe build.sse4_f_inl1_hrd0/fcheck_sa.o build.sse4_f_inl1_hrd0/fsampler_cu.o -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_gg_ttx_cuda build.sse4_f_inl1_hrd0/gRandomNumberKernels.o build.sse4_f_inl1_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.sse4_f_inl1_hrd0/libmg5amc_gg_ttx_cuda.so build.sse4_f_inl1_hrd0/gCPPProcess.o build.sse4_f_inl1_hrd0/gMatrixElementKernels.o build.sse4_f_inl1_hrd0/gBridgeKernels.o build.sse4_f_inl1_hrd0/gCrossSectionKernels.o build.sse4_f_inl1_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl1_hrd0/gcheck.exe build.sse4_f_inl1_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl1_hrd0'  -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_gg_ttx_cuda build.sse4_f_inl1_hrd0/gRandomNumberKernels.o build.sse4_f_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl1_hrd0/fgcheck.exe build.sse4_f_inl1_hrd0/fcheck_sa.o build.sse4_f_inl1_hrd0/fsampler_cu.o -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl1_hrd0'  -lgfortran -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_gg_ttx_cuda build.sse4_f_inl1_hrd0/gRandomNumberKernels.o build.sse4_f_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.sse4_f_inl1_hrd0/libmg5amc_gg_ttx_cpp.so build.sse4_f_inl1_hrd0/CPPProcess.o build.sse4_f_inl1_hrd0/MatrixElementKernels.o build.sse4_f_inl1_hrd0/BridgeKernels.o build.sse4_f_inl1_hrd0/CrossSectionKernels.o build.sse4_f_inl1_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_f_inl1_hrd0/fcheck.exe build.sse4_f_inl1_hrd0/fcheck_sa.o build.sse4_f_inl1_hrd0/fsampler.o -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_f_inl1_hrd0'  -lgfortran -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_gg_ttx_cpp build.sse4_f_inl1_hrd0/RandomNumberKernels.o build.sse4_f_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_f_inl1_hrd0/check.exe build.sse4_f_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_f_inl1_hrd0'  -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_gg_ttx_cpp build.sse4_f_inl1_hrd0/RandomNumberKernels.o build.sse4_f_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl1_hrd0/runTest.exe build.sse4_f_inl1_hrd0/CPPProcess.o build.sse4_f_inl1_hrd0/MatrixElementKernels.o build.sse4_f_inl1_hrd0/BridgeKernels.o build.sse4_f_inl1_hrd0/CrossSectionKernels.o build.sse4_f_inl1_hrd0/RandomNumberKernels.o build.sse4_f_inl1_hrd0/RamboSamplingKernels.o build.sse4_f_inl1_hrd0/testxxx.o  build.sse4_f_inl1_hrd0/testmisc.o  build.sse4_f_inl1_hrd0/runTest.o build.sse4_f_inl1_hrd0/gCPPProcess.o build.sse4_f_inl1_hrd0/gMatrixElementKernels.o build.sse4_f_inl1_hrd0/gBridgeKernels.o build.sse4_f_inl1_hrd0/gCrossSectionKernels.o build.sse4_f_inl1_hrd0/gRandomNumberKernels.o build.sse4_f_inl1_hrd0/gRamboSamplingKernels.o build.sse4_f_inl1_hrd0/testxxx_cu.o  build.sse4_f_inl1_hrd0/testmisc_cu.o  build.sse4_f_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl1_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
 touch build.sse4_f_inl1_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_f_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.sse4_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_f_inl1_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_f_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.sse4_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_f_inl1_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.sse4_f_inl1_hrd0/libmg5amc_gg_ttx_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_f_inl1_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.sse4_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_f_inl1_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:03:06
+DATE: 2022-09-24_23:54:54
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl1_hrd0/check.exe -p 2048 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl1_hrd0/check.exe -p 2048 256 4 OMP=
 Process                     = SIGMA_SM_GG_TTX_CPP [gcc 11.2.0] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CPP:FLT+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK
 FP precision                = FLOAT (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 4.902071e+05                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 5.601825e+05                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 5.601825e+05                 )  sec^-1
-MeanMatrixElemValue         = ( 2.086786e+00 +- 3.413831e-03 )  GeV^0
-TOTAL       :     2.244718 sec
-real	0m2.257s
+EvtsPerSec[Rmb+ME]     (23) = ( 4.920699e+05                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 5.622565e+05                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 5.622565e+05                 )  sec^-1
+MeanMatrixElemValue         = ( 2.086445e+00 +- 2.416494e-03 )  GeV^0
+TOTAL       :     4.432247 sec
+real	0m4.445s
 =Symbols in CPPProcess.o= (~sse4: 2909) (avx2:    0) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl1_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl1_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl1_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl1_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 2.028820e+00
 Avg ME (F77/C++)    = 2.0288199420319870
 Relative difference = 2.8572279973754756e-08
@@ -3249,13 +3281,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:03:10 CEST 2022 Will execute './throughputX.sh -makej -ggtt -avx2only  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:55:13 CEST 2022 Will execute './throughputX.sh -makej -ggtt -avx2only  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -avx2only implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
 CUDACPP_BUILDDIR='build.avx2_d_inl0_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -3265,71 +3297,72 @@ HELINL=0
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.avx2_d_inl0_hrd0 for tag=avx2_d_inl0_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.avx2_d_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gcheck_sa.cu -o build.avx2_d_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gcheck_sa.cu -o build.avx2_d_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gCPPProcess.cu -o build.avx2_d_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.avx2_d_inl0_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gBridgeKernels.cu -o build.avx2_d_inl0_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.avx2_d_inl0_hrd0/gCrossSectionKernels.o
 AVX=avx2
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gCPPProcess.cu -o build.avx2_d_inl0_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.avx2_d_inl0_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gBridgeKernels.cu -o build.avx2_d_inl0_hrd0/gBridgeKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.avx2_d_inl0_hrd0/gCrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -c Parameters_sm.cc -o build.avx2_d_inl0_hrd0/Parameters_sm.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fbridge.cc -o build.avx2_d_inl0_hrd0/fbridge_cu.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -c read_slha.cc -o build.avx2_d_inl0_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.avx2_d_inl0_hrd0/gRandomNumberKernels.o
-mkdir -p ../lib/build.avx2_d_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.avx2_d_inl0_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fbridge.cc -o build.avx2_d_inl0_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.avx2_d_inl0_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.avx2_d_inl0_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.avx2_d_inl0_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.avx2_d_inl0_hrd0/CPPProcess.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.avx2_d_inl0_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.avx2_d_inl0_hrd0/BridgeKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -c Parameters_sm.cc -o build.avx2_d_inl0_hrd0/Parameters_sm.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -c read_slha.cc -o build.avx2_d_inl0_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.avx2_d_inl0_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.avx2_d_inl0_hrd0/fbridge.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.avx2_d_inl0_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.avx2_d_inl0_hrd0/RandomNumberKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.avx2_d_inl0_hrd0/RamboSamplingKernels.o
+mkdir -p ../lib/build.avx2_d_inl0_hrd0
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.avx2_d_inl0_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testxxx.cc -o build.avx2_d_inl0_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testxxx.cc -o build.avx2_d_inl0_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.avx2_d_inl0_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testmisc.cc -o build.avx2_d_inl0_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testmisc.cc -o build.avx2_d_inl0_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.avx2_d_inl0_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu runTest.cc -o build.avx2_d_inl0_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu runTest.cc -o build.avx2_d_inl0_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.avx2_d_inl0_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fsampler.cc -o build.avx2_d_inl0_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fsampler.cc -o build.avx2_d_inl0_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.avx2_d_inl0_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.avx2_d_inl0_hrd0/libmg5amc_common.so build.avx2_d_inl0_hrd0/Parameters_sm.o build.avx2_d_inl0_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.avx2_d_inl0_hrd0/libmg5amc_gg_ttx_cuda.so build.avx2_d_inl0_hrd0/gCPPProcess.o build.avx2_d_inl0_hrd0/gMatrixElementKernels.o build.avx2_d_inl0_hrd0/gBridgeKernels.o build.avx2_d_inl0_hrd0/gCrossSectionKernels.o build.avx2_d_inl0_hrd0/fbridge_cu.o -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.avx2_d_inl0_hrd0/libmg5amc_gg_ttx_cpp.so build.avx2_d_inl0_hrd0/CPPProcess.o build.avx2_d_inl0_hrd0/MatrixElementKernels.o build.avx2_d_inl0_hrd0/BridgeKernels.o build.avx2_d_inl0_hrd0/CrossSectionKernels.o build.avx2_d_inl0_hrd0/fbridge.o -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl0_hrd0/runTest.exe build.avx2_d_inl0_hrd0/CPPProcess.o build.avx2_d_inl0_hrd0/MatrixElementKernels.o build.avx2_d_inl0_hrd0/BridgeKernels.o build.avx2_d_inl0_hrd0/CrossSectionKernels.o build.avx2_d_inl0_hrd0/RandomNumberKernels.o build.avx2_d_inl0_hrd0/RamboSamplingKernels.o build.avx2_d_inl0_hrd0/testxxx.o  build.avx2_d_inl0_hrd0/testmisc.o  build.avx2_d_inl0_hrd0/runTest.o build.avx2_d_inl0_hrd0/gCPPProcess.o build.avx2_d_inl0_hrd0/gMatrixElementKernels.o build.avx2_d_inl0_hrd0/gBridgeKernels.o build.avx2_d_inl0_hrd0/gCrossSectionKernels.o build.avx2_d_inl0_hrd0/gRandomNumberKernels.o build.avx2_d_inl0_hrd0/gRamboSamplingKernels.o build.avx2_d_inl0_hrd0/testxxx_cu.o  build.avx2_d_inl0_hrd0/testmisc_cu.o  build.avx2_d_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_d_inl0_hrd0/check.exe build.avx2_d_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_gg_ttx_cpp build.avx2_d_inl0_hrd0/RandomNumberKernels.o build.avx2_d_inl0_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_d_inl0_hrd0/fcheck.exe build.avx2_d_inl0_hrd0/fcheck_sa.o build.avx2_d_inl0_hrd0/fsampler.o -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_gg_ttx_cpp build.avx2_d_inl0_hrd0/RandomNumberKernels.o build.avx2_d_inl0_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl0_hrd0/gcheck.exe build.avx2_d_inl0_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_gg_ttx_cuda build.avx2_d_inl0_hrd0/gRandomNumberKernels.o build.avx2_d_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl0_hrd0/fgcheck.exe build.avx2_d_inl0_hrd0/fcheck_sa.o build.avx2_d_inl0_hrd0/fsampler_cu.o -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_gg_ttx_cuda build.avx2_d_inl0_hrd0/gRandomNumberKernels.o build.avx2_d_inl0_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.avx2_d_inl0_hrd0/libmg5amc_gg_ttx_cuda.so build.avx2_d_inl0_hrd0/gCPPProcess.o build.avx2_d_inl0_hrd0/gMatrixElementKernels.o build.avx2_d_inl0_hrd0/gBridgeKernels.o build.avx2_d_inl0_hrd0/gCrossSectionKernels.o build.avx2_d_inl0_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.avx2_d_inl0_hrd0/libmg5amc_gg_ttx_cpp.so build.avx2_d_inl0_hrd0/CPPProcess.o build.avx2_d_inl0_hrd0/MatrixElementKernels.o build.avx2_d_inl0_hrd0/BridgeKernels.o build.avx2_d_inl0_hrd0/CrossSectionKernels.o build.avx2_d_inl0_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl0_hrd0/gcheck.exe build.avx2_d_inl0_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl0_hrd0'  -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_gg_ttx_cuda build.avx2_d_inl0_hrd0/gRandomNumberKernels.o build.avx2_d_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl0_hrd0/fgcheck.exe build.avx2_d_inl0_hrd0/fcheck_sa.o build.avx2_d_inl0_hrd0/fsampler_cu.o -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl0_hrd0'  -lgfortran -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_gg_ttx_cuda build.avx2_d_inl0_hrd0/gRandomNumberKernels.o build.avx2_d_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_d_inl0_hrd0/fcheck.exe build.avx2_d_inl0_hrd0/fcheck_sa.o build.avx2_d_inl0_hrd0/fsampler.o -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_d_inl0_hrd0'  -lgfortran -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_gg_ttx_cpp build.avx2_d_inl0_hrd0/RandomNumberKernels.o build.avx2_d_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_d_inl0_hrd0/check.exe build.avx2_d_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_d_inl0_hrd0'  -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_gg_ttx_cpp build.avx2_d_inl0_hrd0/RandomNumberKernels.o build.avx2_d_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl0_hrd0/runTest.exe build.avx2_d_inl0_hrd0/CPPProcess.o build.avx2_d_inl0_hrd0/MatrixElementKernels.o build.avx2_d_inl0_hrd0/BridgeKernels.o build.avx2_d_inl0_hrd0/CrossSectionKernels.o build.avx2_d_inl0_hrd0/RandomNumberKernels.o build.avx2_d_inl0_hrd0/RamboSamplingKernels.o build.avx2_d_inl0_hrd0/testxxx.o  build.avx2_d_inl0_hrd0/testmisc.o  build.avx2_d_inl0_hrd0/runTest.o build.avx2_d_inl0_hrd0/gCPPProcess.o build.avx2_d_inl0_hrd0/gMatrixElementKernels.o build.avx2_d_inl0_hrd0/gBridgeKernels.o build.avx2_d_inl0_hrd0/gCrossSectionKernels.o build.avx2_d_inl0_hrd0/gRandomNumberKernels.o build.avx2_d_inl0_hrd0/gRamboSamplingKernels.o build.avx2_d_inl0_hrd0/testxxx_cu.o  build.avx2_d_inl0_hrd0/testmisc_cu.o  build.avx2_d_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl0_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
 touch build.avx2_d_inl0_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_d_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.avx2_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_d_inl0_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_d_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.avx2_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_d_inl0_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.avx2_d_inl0_hrd0/libmg5amc_gg_ttx_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_d_inl0_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.avx2_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_d_inl0_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:03:12
+DATE: 2022-09-24_23:55:23
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/check.exe -p 2048 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/check.exe -p 2048 256 4 OMP=
 Process                     = SIGMA_SM_GG_TTX_CPP [gcc 11.2.0] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CPP:DBL+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 4.747704e+05                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 5.573789e+05                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 5.573789e+05                 )  sec^-1
-MeanMatrixElemValue         = ( 2.086689e+00 +- 3.413217e-03 )  GeV^0
-TOTAL       :     2.361100 sec
-real	0m2.379s
+EvtsPerSec[Rmb+ME]     (23) = ( 4.761652e+05                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 5.591178e+05                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 5.591178e+05                 )  sec^-1
+MeanMatrixElemValue         = ( 2.086360e+00 +- 2.416141e-03 )  GeV^0
+TOTAL       :     4.625033 sec
+real	0m4.643s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2: 2242) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 2.028807e+00
 Avg ME (F77/C++)    = 2.0288063388516204
 Relative difference = 3.2588037186351226e-07
@@ -3337,13 +3370,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:03:16 CEST 2022 Will execute './throughputX.sh -makej -ggtt -avx2only  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:55:43 CEST 2022 Will execute './throughputX.sh -makej -ggtt -avx2only  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -avx2only implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
 CUDACPP_BUILDDIR='build.avx2_d_inl1_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -3353,71 +3386,72 @@ HELINL=1
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.avx2_d_inl1_hrd0 for tag=avx2_d_inl1_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.avx2_d_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.avx2_d_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.avx2_d_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.avx2_d_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.avx2_d_inl1_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.avx2_d_inl1_hrd0/gBridgeKernels.o
 AVX=avx2
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.avx2_d_inl1_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.avx2_d_inl1_hrd0/gMatrixElementKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.avx2_d_inl1_hrd0/gBridgeKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.avx2_d_inl1_hrd0/Parameters_sm.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.avx2_d_inl1_hrd0/gCrossSectionKernels.o
-mkdir -p ../lib/build.avx2_d_inl1_hrd0
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.avx2_d_inl1_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.avx2_d_inl1_hrd0/fbridge_cu.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.avx2_d_inl1_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.avx2_d_inl1_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.avx2_d_inl1_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.avx2_d_inl1_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.avx2_d_inl1_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.avx2_d_inl1_hrd0/gRamboSamplingKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.avx2_d_inl1_hrd0/check_sa.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.avx2_d_inl1_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.avx2_d_inl1_hrd0/CPPProcess.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.avx2_d_inl1_hrd0/read_slha.o
+mkdir -p ../lib/build.avx2_d_inl1_hrd0
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.avx2_d_inl1_hrd0/Parameters_sm.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.avx2_d_inl1_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.avx2_d_inl1_hrd0/BridgeKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.avx2_d_inl1_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.avx2_d_inl1_hrd0/fbridge.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.avx2_d_inl1_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.avx2_d_inl1_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.avx2_d_inl1_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.avx2_d_inl1_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.avx2_d_inl1_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.avx2_d_inl1_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.avx2_d_inl1_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.avx2_d_inl1_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.avx2_d_inl1_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.avx2_d_inl1_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.avx2_d_inl1_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.avx2_d_inl1_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.avx2_d_inl1_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.avx2_d_inl1_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.avx2_d_inl1_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.avx2_d_inl1_hrd0/libmg5amc_common.so build.avx2_d_inl1_hrd0/Parameters_sm.o build.avx2_d_inl1_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.avx2_d_inl1_hrd0/libmg5amc_gg_ttx_cuda.so build.avx2_d_inl1_hrd0/gCPPProcess.o build.avx2_d_inl1_hrd0/gMatrixElementKernels.o build.avx2_d_inl1_hrd0/gBridgeKernels.o build.avx2_d_inl1_hrd0/gCrossSectionKernels.o build.avx2_d_inl1_hrd0/fbridge_cu.o -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.avx2_d_inl1_hrd0/libmg5amc_gg_ttx_cpp.so build.avx2_d_inl1_hrd0/CPPProcess.o build.avx2_d_inl1_hrd0/MatrixElementKernels.o build.avx2_d_inl1_hrd0/BridgeKernels.o build.avx2_d_inl1_hrd0/CrossSectionKernels.o build.avx2_d_inl1_hrd0/fbridge.o -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl1_hrd0/runTest.exe build.avx2_d_inl1_hrd0/CPPProcess.o build.avx2_d_inl1_hrd0/MatrixElementKernels.o build.avx2_d_inl1_hrd0/BridgeKernels.o build.avx2_d_inl1_hrd0/CrossSectionKernels.o build.avx2_d_inl1_hrd0/RandomNumberKernels.o build.avx2_d_inl1_hrd0/RamboSamplingKernels.o build.avx2_d_inl1_hrd0/testxxx.o  build.avx2_d_inl1_hrd0/testmisc.o  build.avx2_d_inl1_hrd0/runTest.o build.avx2_d_inl1_hrd0/gCPPProcess.o build.avx2_d_inl1_hrd0/gMatrixElementKernels.o build.avx2_d_inl1_hrd0/gBridgeKernels.o build.avx2_d_inl1_hrd0/gCrossSectionKernels.o build.avx2_d_inl1_hrd0/gRandomNumberKernels.o build.avx2_d_inl1_hrd0/gRamboSamplingKernels.o build.avx2_d_inl1_hrd0/testxxx_cu.o  build.avx2_d_inl1_hrd0/testmisc_cu.o  build.avx2_d_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_d_inl1_hrd0/check.exe build.avx2_d_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_gg_ttx_cpp build.avx2_d_inl1_hrd0/RandomNumberKernels.o build.avx2_d_inl1_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_d_inl1_hrd0/fcheck.exe build.avx2_d_inl1_hrd0/fcheck_sa.o build.avx2_d_inl1_hrd0/fsampler.o -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_gg_ttx_cpp build.avx2_d_inl1_hrd0/RandomNumberKernels.o build.avx2_d_inl1_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl1_hrd0/gcheck.exe build.avx2_d_inl1_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_gg_ttx_cuda build.avx2_d_inl1_hrd0/gRandomNumberKernels.o build.avx2_d_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl1_hrd0/fgcheck.exe build.avx2_d_inl1_hrd0/fcheck_sa.o build.avx2_d_inl1_hrd0/fsampler_cu.o -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_gg_ttx_cuda build.avx2_d_inl1_hrd0/gRandomNumberKernels.o build.avx2_d_inl1_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.avx2_d_inl1_hrd0/libmg5amc_gg_ttx_cuda.so build.avx2_d_inl1_hrd0/gCPPProcess.o build.avx2_d_inl1_hrd0/gMatrixElementKernels.o build.avx2_d_inl1_hrd0/gBridgeKernels.o build.avx2_d_inl1_hrd0/gCrossSectionKernels.o build.avx2_d_inl1_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl1_hrd0/gcheck.exe build.avx2_d_inl1_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl1_hrd0'  -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_gg_ttx_cuda build.avx2_d_inl1_hrd0/gRandomNumberKernels.o build.avx2_d_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl1_hrd0/fgcheck.exe build.avx2_d_inl1_hrd0/fcheck_sa.o build.avx2_d_inl1_hrd0/fsampler_cu.o -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl1_hrd0'  -lgfortran -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_gg_ttx_cuda build.avx2_d_inl1_hrd0/gRandomNumberKernels.o build.avx2_d_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.avx2_d_inl1_hrd0/libmg5amc_gg_ttx_cpp.so build.avx2_d_inl1_hrd0/CPPProcess.o build.avx2_d_inl1_hrd0/MatrixElementKernels.o build.avx2_d_inl1_hrd0/BridgeKernels.o build.avx2_d_inl1_hrd0/CrossSectionKernels.o build.avx2_d_inl1_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_d_inl1_hrd0/fcheck.exe build.avx2_d_inl1_hrd0/fcheck_sa.o build.avx2_d_inl1_hrd0/fsampler.o -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_d_inl1_hrd0'  -lgfortran -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_gg_ttx_cpp build.avx2_d_inl1_hrd0/RandomNumberKernels.o build.avx2_d_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_d_inl1_hrd0/check.exe build.avx2_d_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_d_inl1_hrd0'  -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_gg_ttx_cpp build.avx2_d_inl1_hrd0/RandomNumberKernels.o build.avx2_d_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl1_hrd0/runTest.exe build.avx2_d_inl1_hrd0/CPPProcess.o build.avx2_d_inl1_hrd0/MatrixElementKernels.o build.avx2_d_inl1_hrd0/BridgeKernels.o build.avx2_d_inl1_hrd0/CrossSectionKernels.o build.avx2_d_inl1_hrd0/RandomNumberKernels.o build.avx2_d_inl1_hrd0/RamboSamplingKernels.o build.avx2_d_inl1_hrd0/testxxx.o  build.avx2_d_inl1_hrd0/testmisc.o  build.avx2_d_inl1_hrd0/runTest.o build.avx2_d_inl1_hrd0/gCPPProcess.o build.avx2_d_inl1_hrd0/gMatrixElementKernels.o build.avx2_d_inl1_hrd0/gBridgeKernels.o build.avx2_d_inl1_hrd0/gCrossSectionKernels.o build.avx2_d_inl1_hrd0/gRandomNumberKernels.o build.avx2_d_inl1_hrd0/gRamboSamplingKernels.o build.avx2_d_inl1_hrd0/testxxx_cu.o  build.avx2_d_inl1_hrd0/testmisc_cu.o  build.avx2_d_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl1_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
 touch build.avx2_d_inl1_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_d_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.avx2_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_d_inl1_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_d_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.avx2_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_d_inl1_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.avx2_d_inl1_hrd0/libmg5amc_gg_ttx_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_d_inl1_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.avx2_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_d_inl1_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:03:17
+DATE: 2022-09-24_23:55:50
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl1_hrd0/check.exe -p 2048 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl1_hrd0/check.exe -p 2048 256 4 OMP=
 Process                     = SIGMA_SM_GG_TTX_CPP [gcc 11.2.0] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CPP:DBL+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 4.015994e+05                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 4.593042e+05                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 4.593042e+05                 )  sec^-1
-MeanMatrixElemValue         = ( 2.086689e+00 +- 3.413217e-03 )  GeV^0
-TOTAL       :     2.762822 sec
-real	0m2.781s
+EvtsPerSec[Rmb+ME]     (23) = ( 4.032487e+05                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 4.615785e+05                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 4.615785e+05                 )  sec^-1
+MeanMatrixElemValue         = ( 2.086360e+00 +- 2.416141e-03 )  GeV^0
+TOTAL       :     5.421593 sec
+real	0m5.440s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2: 2689) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl1_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl1_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl1_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl1_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 2.028807e+00
 Avg ME (F77/C++)    = 2.0288063388516204
 Relative difference = 3.2588037186351226e-07
@@ -3425,13 +3459,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:03:22 CEST 2022 Will execute './throughputX.sh -makej -ggtt -avx2only -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:56:11 CEST 2022 Will execute './throughputX.sh -makej -ggtt -avx2only -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -avx2only implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
 CUDACPP_BUILDDIR='build.avx2_f_inl0_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -3441,71 +3475,72 @@ HELINL=0
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.avx2_f_inl0_hrd0 for tag=avx2_f_inl0_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.avx2_f_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gcheck_sa.cu -o build.avx2_f_inl0_hrd0/gcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gCPPProcess.cu -o build.avx2_f_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gcheck_sa.cu -o build.avx2_f_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gCPPProcess.cu -o build.avx2_f_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.avx2_f_inl0_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gBridgeKernels.cu -o build.avx2_f_inl0_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.avx2_f_inl0_hrd0/gCrossSectionKernels.o
 AVX=avx2
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.avx2_f_inl0_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gBridgeKernels.cu -o build.avx2_f_inl0_hrd0/gBridgeKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.avx2_f_inl0_hrd0/gCrossSectionKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fbridge.cc -o build.avx2_f_inl0_hrd0/fbridge_cu.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -c Parameters_sm.cc -o build.avx2_f_inl0_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -c read_slha.cc -o build.avx2_f_inl0_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.avx2_f_inl0_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.avx2_f_inl0_hrd0/gRamboSamplingKernels.o
-mkdir -p ../lib/build.avx2_f_inl0_hrd0
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fbridge.cc -o build.avx2_f_inl0_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.avx2_f_inl0_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.avx2_f_inl0_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.avx2_f_inl0_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.avx2_f_inl0_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.avx2_f_inl0_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.avx2_f_inl0_hrd0/BridgeKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.avx2_f_inl0_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.avx2_f_inl0_hrd0/fbridge.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.avx2_f_inl0_hrd0/RandomNumberKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -c Parameters_sm.cc -o build.avx2_f_inl0_hrd0/Parameters_sm.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.avx2_f_inl0_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.avx2_f_inl0_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testxxx.cc -o build.avx2_f_inl0_hrd0/testxxx_cu.o
+mkdir -p ../lib/build.avx2_f_inl0_hrd0
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -c read_slha.cc -o build.avx2_f_inl0_hrd0/read_slha.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testxxx.cc -o build.avx2_f_inl0_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.avx2_f_inl0_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testmisc.cc -o build.avx2_f_inl0_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testmisc.cc -o build.avx2_f_inl0_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.avx2_f_inl0_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu runTest.cc -o build.avx2_f_inl0_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu runTest.cc -o build.avx2_f_inl0_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.avx2_f_inl0_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fsampler.cc -o build.avx2_f_inl0_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fsampler.cc -o build.avx2_f_inl0_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.avx2_f_inl0_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.avx2_f_inl0_hrd0/libmg5amc_common.so build.avx2_f_inl0_hrd0/Parameters_sm.o build.avx2_f_inl0_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.avx2_f_inl0_hrd0/libmg5amc_gg_ttx_cuda.so build.avx2_f_inl0_hrd0/gCPPProcess.o build.avx2_f_inl0_hrd0/gMatrixElementKernels.o build.avx2_f_inl0_hrd0/gBridgeKernels.o build.avx2_f_inl0_hrd0/gCrossSectionKernels.o build.avx2_f_inl0_hrd0/fbridge_cu.o -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.avx2_f_inl0_hrd0/libmg5amc_gg_ttx_cpp.so build.avx2_f_inl0_hrd0/CPPProcess.o build.avx2_f_inl0_hrd0/MatrixElementKernels.o build.avx2_f_inl0_hrd0/BridgeKernels.o build.avx2_f_inl0_hrd0/CrossSectionKernels.o build.avx2_f_inl0_hrd0/fbridge.o -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl0_hrd0/runTest.exe build.avx2_f_inl0_hrd0/CPPProcess.o build.avx2_f_inl0_hrd0/MatrixElementKernels.o build.avx2_f_inl0_hrd0/BridgeKernels.o build.avx2_f_inl0_hrd0/CrossSectionKernels.o build.avx2_f_inl0_hrd0/RandomNumberKernels.o build.avx2_f_inl0_hrd0/RamboSamplingKernels.o build.avx2_f_inl0_hrd0/testxxx.o  build.avx2_f_inl0_hrd0/testmisc.o  build.avx2_f_inl0_hrd0/runTest.o build.avx2_f_inl0_hrd0/gCPPProcess.o build.avx2_f_inl0_hrd0/gMatrixElementKernels.o build.avx2_f_inl0_hrd0/gBridgeKernels.o build.avx2_f_inl0_hrd0/gCrossSectionKernels.o build.avx2_f_inl0_hrd0/gRandomNumberKernels.o build.avx2_f_inl0_hrd0/gRamboSamplingKernels.o build.avx2_f_inl0_hrd0/testxxx_cu.o  build.avx2_f_inl0_hrd0/testmisc_cu.o  build.avx2_f_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_f_inl0_hrd0/check.exe build.avx2_f_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_gg_ttx_cpp build.avx2_f_inl0_hrd0/RandomNumberKernels.o build.avx2_f_inl0_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_f_inl0_hrd0/fcheck.exe build.avx2_f_inl0_hrd0/fcheck_sa.o build.avx2_f_inl0_hrd0/fsampler.o -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_gg_ttx_cpp build.avx2_f_inl0_hrd0/RandomNumberKernels.o build.avx2_f_inl0_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl0_hrd0/gcheck.exe build.avx2_f_inl0_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_gg_ttx_cuda build.avx2_f_inl0_hrd0/gRandomNumberKernels.o build.avx2_f_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl0_hrd0/fgcheck.exe build.avx2_f_inl0_hrd0/fcheck_sa.o build.avx2_f_inl0_hrd0/fsampler_cu.o -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_gg_ttx_cuda build.avx2_f_inl0_hrd0/gRandomNumberKernels.o build.avx2_f_inl0_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.avx2_f_inl0_hrd0/libmg5amc_gg_ttx_cuda.so build.avx2_f_inl0_hrd0/gCPPProcess.o build.avx2_f_inl0_hrd0/gMatrixElementKernels.o build.avx2_f_inl0_hrd0/gBridgeKernels.o build.avx2_f_inl0_hrd0/gCrossSectionKernels.o build.avx2_f_inl0_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.avx2_f_inl0_hrd0/libmg5amc_gg_ttx_cpp.so build.avx2_f_inl0_hrd0/CPPProcess.o build.avx2_f_inl0_hrd0/MatrixElementKernels.o build.avx2_f_inl0_hrd0/BridgeKernels.o build.avx2_f_inl0_hrd0/CrossSectionKernels.o build.avx2_f_inl0_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_f_inl0_hrd0/fcheck.exe build.avx2_f_inl0_hrd0/fcheck_sa.o build.avx2_f_inl0_hrd0/fsampler.o -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_f_inl0_hrd0'  -lgfortran -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_gg_ttx_cpp build.avx2_f_inl0_hrd0/RandomNumberKernels.o build.avx2_f_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl0_hrd0/gcheck.exe build.avx2_f_inl0_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl0_hrd0'  -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_gg_ttx_cuda build.avx2_f_inl0_hrd0/gRandomNumberKernels.o build.avx2_f_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl0_hrd0/fgcheck.exe build.avx2_f_inl0_hrd0/fcheck_sa.o build.avx2_f_inl0_hrd0/fsampler_cu.o -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl0_hrd0'  -lgfortran -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_gg_ttx_cuda build.avx2_f_inl0_hrd0/gRandomNumberKernels.o build.avx2_f_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_f_inl0_hrd0/check.exe build.avx2_f_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_f_inl0_hrd0'  -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_gg_ttx_cpp build.avx2_f_inl0_hrd0/RandomNumberKernels.o build.avx2_f_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl0_hrd0/runTest.exe build.avx2_f_inl0_hrd0/CPPProcess.o build.avx2_f_inl0_hrd0/MatrixElementKernels.o build.avx2_f_inl0_hrd0/BridgeKernels.o build.avx2_f_inl0_hrd0/CrossSectionKernels.o build.avx2_f_inl0_hrd0/RandomNumberKernels.o build.avx2_f_inl0_hrd0/RamboSamplingKernels.o build.avx2_f_inl0_hrd0/testxxx.o  build.avx2_f_inl0_hrd0/testmisc.o  build.avx2_f_inl0_hrd0/runTest.o build.avx2_f_inl0_hrd0/gCPPProcess.o build.avx2_f_inl0_hrd0/gMatrixElementKernels.o build.avx2_f_inl0_hrd0/gBridgeKernels.o build.avx2_f_inl0_hrd0/gCrossSectionKernels.o build.avx2_f_inl0_hrd0/gRandomNumberKernels.o build.avx2_f_inl0_hrd0/gRamboSamplingKernels.o build.avx2_f_inl0_hrd0/testxxx_cu.o  build.avx2_f_inl0_hrd0/testmisc_cu.o  build.avx2_f_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl0_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
 touch build.avx2_f_inl0_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_f_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.avx2_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_f_inl0_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_f_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.avx2_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_f_inl0_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.avx2_f_inl0_hrd0/libmg5amc_gg_ttx_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_f_inl0_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.avx2_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_f_inl0_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:03:23
+DATE: 2022-09-24_23:56:20
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/check.exe -p 2048 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/check.exe -p 2048 256 4 OMP=
 Process                     = SIGMA_SM_GG_TTX_CPP [gcc 11.2.0] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CPP:FLT+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK
 FP precision                = FLOAT (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 8.220231e+05                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 1.035333e+06                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 1.035333e+06                 )  sec^-1
-MeanMatrixElemValue         = ( 2.086781e+00 +- 3.413783e-03 )  GeV^0
-TOTAL       :     1.382140 sec
-real	0m1.394s
+EvtsPerSec[Rmb+ME]     (23) = ( 8.250837e+05                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 1.038209e+06                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 1.038209e+06                 )  sec^-1
+MeanMatrixElemValue         = ( 2.086441e+00 +- 2.416476e-03 )  GeV^0
+TOTAL       :     2.713217 sec
+real	0m2.726s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2: 2699) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 2.028819e+00
 Avg ME (F77/C++)    = 2.0288187353871763
 Relative difference = 1.3042702362938956e-07
@@ -3513,13 +3548,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:03:27 CEST 2022 Will execute './throughputX.sh -makej -ggtt -avx2only -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:56:38 CEST 2022 Will execute './throughputX.sh -makej -ggtt -avx2only -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -avx2only implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
 CUDACPP_BUILDDIR='build.avx2_f_inl1_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -3529,71 +3564,72 @@ HELINL=1
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.avx2_f_inl1_hrd0 for tag=avx2_f_inl1_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.avx2_f_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.avx2_f_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.avx2_f_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.avx2_f_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.avx2_f_inl1_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.avx2_f_inl1_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.avx2_f_inl1_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.avx2_f_inl1_hrd0/fbridge_cu.o
 AVX=avx2
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.avx2_f_inl1_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.avx2_f_inl1_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.avx2_f_inl1_hrd0/gBridgeKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.avx2_f_inl1_hrd0/gCrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.avx2_f_inl1_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.avx2_f_inl1_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.avx2_f_inl1_hrd0/fbridge_cu.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.avx2_f_inl1_hrd0/gRandomNumberKernels.o
-mkdir -p ../lib/build.avx2_f_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.avx2_f_inl1_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.avx2_f_inl1_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.avx2_f_inl1_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.avx2_f_inl1_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.avx2_f_inl1_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.avx2_f_inl1_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.avx2_f_inl1_hrd0/BridgeKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.avx2_f_inl1_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.avx2_f_inl1_hrd0/fbridge.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.avx2_f_inl1_hrd0/RandomNumberKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.avx2_f_inl1_hrd0/Parameters_sm.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.avx2_f_inl1_hrd0/read_slha.o
+mkdir -p ../lib/build.avx2_f_inl1_hrd0
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.avx2_f_inl1_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.avx2_f_inl1_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.avx2_f_inl1_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.avx2_f_inl1_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.avx2_f_inl1_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.avx2_f_inl1_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.avx2_f_inl1_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.avx2_f_inl1_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.avx2_f_inl1_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.avx2_f_inl1_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.avx2_f_inl1_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.avx2_f_inl1_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.avx2_f_inl1_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.avx2_f_inl1_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.avx2_f_inl1_hrd0/libmg5amc_common.so build.avx2_f_inl1_hrd0/Parameters_sm.o build.avx2_f_inl1_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.avx2_f_inl1_hrd0/libmg5amc_gg_ttx_cuda.so build.avx2_f_inl1_hrd0/gCPPProcess.o build.avx2_f_inl1_hrd0/gMatrixElementKernels.o build.avx2_f_inl1_hrd0/gBridgeKernels.o build.avx2_f_inl1_hrd0/gCrossSectionKernels.o build.avx2_f_inl1_hrd0/fbridge_cu.o -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.avx2_f_inl1_hrd0/libmg5amc_gg_ttx_cpp.so build.avx2_f_inl1_hrd0/CPPProcess.o build.avx2_f_inl1_hrd0/MatrixElementKernels.o build.avx2_f_inl1_hrd0/BridgeKernels.o build.avx2_f_inl1_hrd0/CrossSectionKernels.o build.avx2_f_inl1_hrd0/fbridge.o -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl1_hrd0/runTest.exe build.avx2_f_inl1_hrd0/CPPProcess.o build.avx2_f_inl1_hrd0/MatrixElementKernels.o build.avx2_f_inl1_hrd0/BridgeKernels.o build.avx2_f_inl1_hrd0/CrossSectionKernels.o build.avx2_f_inl1_hrd0/RandomNumberKernels.o build.avx2_f_inl1_hrd0/RamboSamplingKernels.o build.avx2_f_inl1_hrd0/testxxx.o  build.avx2_f_inl1_hrd0/testmisc.o  build.avx2_f_inl1_hrd0/runTest.o build.avx2_f_inl1_hrd0/gCPPProcess.o build.avx2_f_inl1_hrd0/gMatrixElementKernels.o build.avx2_f_inl1_hrd0/gBridgeKernels.o build.avx2_f_inl1_hrd0/gCrossSectionKernels.o build.avx2_f_inl1_hrd0/gRandomNumberKernels.o build.avx2_f_inl1_hrd0/gRamboSamplingKernels.o build.avx2_f_inl1_hrd0/testxxx_cu.o  build.avx2_f_inl1_hrd0/testmisc_cu.o  build.avx2_f_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_f_inl1_hrd0/check.exe build.avx2_f_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_gg_ttx_cpp build.avx2_f_inl1_hrd0/RandomNumberKernels.o build.avx2_f_inl1_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_f_inl1_hrd0/fcheck.exe build.avx2_f_inl1_hrd0/fcheck_sa.o build.avx2_f_inl1_hrd0/fsampler.o -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_gg_ttx_cpp build.avx2_f_inl1_hrd0/RandomNumberKernels.o build.avx2_f_inl1_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl1_hrd0/gcheck.exe build.avx2_f_inl1_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_gg_ttx_cuda build.avx2_f_inl1_hrd0/gRandomNumberKernels.o build.avx2_f_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl1_hrd0/fgcheck.exe build.avx2_f_inl1_hrd0/fcheck_sa.o build.avx2_f_inl1_hrd0/fsampler_cu.o -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_gg_ttx_cuda build.avx2_f_inl1_hrd0/gRandomNumberKernels.o build.avx2_f_inl1_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.avx2_f_inl1_hrd0/libmg5amc_gg_ttx_cuda.so build.avx2_f_inl1_hrd0/gCPPProcess.o build.avx2_f_inl1_hrd0/gMatrixElementKernels.o build.avx2_f_inl1_hrd0/gBridgeKernels.o build.avx2_f_inl1_hrd0/gCrossSectionKernels.o build.avx2_f_inl1_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl1_hrd0/gcheck.exe build.avx2_f_inl1_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl1_hrd0'  -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_gg_ttx_cuda build.avx2_f_inl1_hrd0/gRandomNumberKernels.o build.avx2_f_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl1_hrd0/fgcheck.exe build.avx2_f_inl1_hrd0/fcheck_sa.o build.avx2_f_inl1_hrd0/fsampler_cu.o -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl1_hrd0'  -lgfortran -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_gg_ttx_cuda build.avx2_f_inl1_hrd0/gRandomNumberKernels.o build.avx2_f_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.avx2_f_inl1_hrd0/libmg5amc_gg_ttx_cpp.so build.avx2_f_inl1_hrd0/CPPProcess.o build.avx2_f_inl1_hrd0/MatrixElementKernels.o build.avx2_f_inl1_hrd0/BridgeKernels.o build.avx2_f_inl1_hrd0/CrossSectionKernels.o build.avx2_f_inl1_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_f_inl1_hrd0/fcheck.exe build.avx2_f_inl1_hrd0/fcheck_sa.o build.avx2_f_inl1_hrd0/fsampler.o -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_f_inl1_hrd0'  -lgfortran -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_gg_ttx_cpp build.avx2_f_inl1_hrd0/RandomNumberKernels.o build.avx2_f_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_f_inl1_hrd0/check.exe build.avx2_f_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_f_inl1_hrd0'  -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_gg_ttx_cpp build.avx2_f_inl1_hrd0/RandomNumberKernels.o build.avx2_f_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl1_hrd0/runTest.exe build.avx2_f_inl1_hrd0/CPPProcess.o build.avx2_f_inl1_hrd0/MatrixElementKernels.o build.avx2_f_inl1_hrd0/BridgeKernels.o build.avx2_f_inl1_hrd0/CrossSectionKernels.o build.avx2_f_inl1_hrd0/RandomNumberKernels.o build.avx2_f_inl1_hrd0/RamboSamplingKernels.o build.avx2_f_inl1_hrd0/testxxx.o  build.avx2_f_inl1_hrd0/testmisc.o  build.avx2_f_inl1_hrd0/runTest.o build.avx2_f_inl1_hrd0/gCPPProcess.o build.avx2_f_inl1_hrd0/gMatrixElementKernels.o build.avx2_f_inl1_hrd0/gBridgeKernels.o build.avx2_f_inl1_hrd0/gCrossSectionKernels.o build.avx2_f_inl1_hrd0/gRandomNumberKernels.o build.avx2_f_inl1_hrd0/gRamboSamplingKernels.o build.avx2_f_inl1_hrd0/testxxx_cu.o  build.avx2_f_inl1_hrd0/testmisc_cu.o  build.avx2_f_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl1_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
 touch build.avx2_f_inl1_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_f_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.avx2_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_f_inl1_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_f_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.avx2_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_f_inl1_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.avx2_f_inl1_hrd0/libmg5amc_gg_ttx_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_f_inl1_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.avx2_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_f_inl1_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:03:28
+DATE: 2022-09-24_23:56:46
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl1_hrd0/check.exe -p 2048 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl1_hrd0/check.exe -p 2048 256 4 OMP=
 Process                     = SIGMA_SM_GG_TTX_CPP [gcc 11.2.0] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CPP:FLT+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK
 FP precision                = FLOAT (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 5.953858e+05                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 7.014107e+05                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 7.014107e+05                 )  sec^-1
-MeanMatrixElemValue         = ( 2.086781e+00 +- 3.413783e-03 )  GeV^0
-TOTAL       :     1.867927 sec
-real	0m1.881s
+EvtsPerSec[Rmb+ME]     (23) = ( 6.075163e+05                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 7.171640e+05                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 7.171640e+05                 )  sec^-1
+MeanMatrixElemValue         = ( 2.086441e+00 +- 2.416476e-03 )  GeV^0
+TOTAL       :     3.623609 sec
+real	0m3.636s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2: 3659) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl1_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl1_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl1_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl1_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 2.028819e+00
 Avg ME (F77/C++)    = 2.0288187726400793
 Relative difference = 1.1206515744782328e-07
@@ -3601,35 +3637,35 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:03:32 CEST 2022 Will execute './throughputX.sh -makej -ggtt -512yonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:57:05 CEST 2022 Will execute './throughputX.sh -makej -ggtt -512yonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -512yonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
 CUDACPP_BUILDDIR='build.512y_d_inl0_hrd0'
 make: Nothing to be done for `all'.
 
-DATE: 2022-08-31_21:03:32
+DATE: 2022-09-24_23:57:05
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/check.exe -p 2048 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/check.exe -p 2048 256 4 OMP=
 Process                     = SIGMA_SM_GG_TTX_CPP [gcc 11.2.0] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 5.196312e+05                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 6.212749e+05                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 6.212749e+05                 )  sec^-1
-MeanMatrixElemValue         = ( 2.086689e+00 +- 3.413217e-03 )  GeV^0
-TOTAL       :     2.169834 sec
-real	0m2.188s
+EvtsPerSec[Rmb+ME]     (23) = ( 5.230509e+05                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 6.252618e+05                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 6.252618e+05                 )  sec^-1
+MeanMatrixElemValue         = ( 2.086360e+00 +- 2.416141e-03 )  GeV^0
+TOTAL       :     4.229862 sec
+real	0m4.248s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2: 2037) (512y:   84) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 2.028807e+00
 Avg ME (F77/C++)    = 2.0288063388516204
 Relative difference = 3.2588037186351226e-07
@@ -3637,35 +3673,35 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:03:36 CEST 2022 Will execute './throughputX.sh -makej -ggtt -512yonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:57:24 CEST 2022 Will execute './throughputX.sh -makej -ggtt -512yonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -512yonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
 CUDACPP_BUILDDIR='build.512y_d_inl1_hrd0'
 make: Nothing to be done for `all'.
 
-DATE: 2022-08-31_21:03:37
+DATE: 2022-09-24_23:57:24
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl1_hrd0/check.exe -p 2048 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl1_hrd0/check.exe -p 2048 256 4 OMP=
 Process                     = SIGMA_SM_GG_TTX_CPP [gcc 11.2.0] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 4.134789e+05                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 4.756002e+05                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 4.756002e+05                 )  sec^-1
-MeanMatrixElemValue         = ( 2.086689e+00 +- 3.413217e-03 )  GeV^0
-TOTAL       :     2.687319 sec
-real	0m2.705s
+EvtsPerSec[Rmb+ME]     (23) = ( 4.182760e+05                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 4.812773e+05                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 4.812773e+05                 )  sec^-1
+MeanMatrixElemValue         = ( 2.086360e+00 +- 2.416141e-03 )  GeV^0
+TOTAL       :     5.235064 sec
+real	0m5.253s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2: 2294) (512y:  160) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl1_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl1_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl1_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl1_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 2.028807e+00
 Avg ME (F77/C++)    = 2.0288063388516204
 Relative difference = 3.2588037186351226e-07
@@ -3673,35 +3709,35 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:03:41 CEST 2022 Will execute './throughputX.sh -makej -ggtt -512yonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:57:45 CEST 2022 Will execute './throughputX.sh -makej -ggtt -512yonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -512yonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
 CUDACPP_BUILDDIR='build.512y_f_inl0_hrd0'
 make: Nothing to be done for `all'.
 
-DATE: 2022-08-31_21:03:42
+DATE: 2022-09-24_23:57:45
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/check.exe -p 2048 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/check.exe -p 2048 256 4 OMP=
 Process                     = SIGMA_SM_GG_TTX_CPP [gcc 11.2.0] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK
 FP precision                = FLOAT (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 8.698494e+05                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 1.112862e+06                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 1.112862e+06                 )  sec^-1
-MeanMatrixElemValue         = ( 2.086781e+00 +- 3.413783e-03 )  GeV^0
-TOTAL       :     1.311406 sec
-real	0m1.324s
+EvtsPerSec[Rmb+ME]     (23) = ( 8.724911e+05                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 1.115452e+06                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 1.115452e+06                 )  sec^-1
+MeanMatrixElemValue         = ( 2.086441e+00 +- 2.416476e-03 )  GeV^0
+TOTAL       :     2.574162 sec
+real	0m2.587s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2: 2547) (512y:   11) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 2.028819e+00
 Avg ME (F77/C++)    = 2.0288187353871763
 Relative difference = 1.3042702362938956e-07
@@ -3709,35 +3745,35 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:03:45 CEST 2022 Will execute './throughputX.sh -makej -ggtt -512yonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:58:03 CEST 2022 Will execute './throughputX.sh -makej -ggtt -512yonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -512yonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
 CUDACPP_BUILDDIR='build.512y_f_inl1_hrd0'
 make: Nothing to be done for `all'.
 
-DATE: 2022-08-31_21:03:45
+DATE: 2022-09-24_23:58:03
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl1_hrd0/check.exe -p 2048 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl1_hrd0/check.exe -p 2048 256 4 OMP=
 Process                     = SIGMA_SM_GG_TTX_CPP [gcc 11.2.0] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK
 FP precision                = FLOAT (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 6.015246e+05                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 7.098980e+05                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 7.098980e+05                 )  sec^-1
-MeanMatrixElemValue         = ( 2.086781e+00 +- 3.413783e-03 )  GeV^0
-TOTAL       :     1.848059 sec
-real	0m1.860s
+EvtsPerSec[Rmb+ME]     (23) = ( 6.084022e+05                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 7.174323e+05                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 7.174323e+05                 )  sec^-1
+MeanMatrixElemValue         = ( 2.086441e+00 +- 2.416476e-03 )  GeV^0
+TOTAL       :     3.616546 sec
+real	0m3.629s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2: 3380) (512y:    1) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl1_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl1_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl1_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl1_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 2.028819e+00
 Avg ME (F77/C++)    = 2.0288187726400793
 Relative difference = 1.1206515744782328e-07
@@ -3745,13 +3781,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:03:49 CEST 2022 Will execute './throughputX.sh -makej -ggtt -512zonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:58:21 CEST 2022 Will execute './throughputX.sh -makej -ggtt -512zonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -512zonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
 CUDACPP_BUILDDIR='build.512z_d_inl0_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -3761,71 +3797,72 @@ HELINL=0
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.512z_d_inl0_hrd0 for tag=512z_d_inl0_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.512z_d_inl0_hrd0
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gcheck_sa.cu -o build.512z_d_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gCPPProcess.cu -o build.512z_d_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512z_d_inl0_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512z_d_inl0_hrd0/gBridgeKernels.o
 AVX=512z
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gcheck_sa.cu -o build.512z_d_inl0_hrd0/gcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gCPPProcess.cu -o build.512z_d_inl0_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512z_d_inl0_hrd0/gMatrixElementKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512z_d_inl0_hrd0/gBridgeKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -c Parameters_sm.cc -o build.512z_d_inl0_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -c read_slha.cc -o build.512z_d_inl0_hrd0/read_slha.o
-mkdir -p ../lib/build.512z_d_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512z_d_inl0_hrd0/gCrossSectionKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512z_d_inl0_hrd0/fbridge_cu.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512z_d_inl0_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512z_d_inl0_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512z_d_inl0_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512z_d_inl0_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512z_d_inl0_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512z_d_inl0_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.512z_d_inl0_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.512z_d_inl0_hrd0/CPPProcess.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.512z_d_inl0_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.512z_d_inl0_hrd0/BridgeKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -c Parameters_sm.cc -o build.512z_d_inl0_hrd0/Parameters_sm.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -c read_slha.cc -o build.512z_d_inl0_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.512z_d_inl0_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.512z_d_inl0_hrd0/fbridge.o
+mkdir -p ../lib/build.512z_d_inl0_hrd0
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.512z_d_inl0_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.512z_d_inl0_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.512z_d_inl0_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512z_d_inl0_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512z_d_inl0_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.512z_d_inl0_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512z_d_inl0_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512z_d_inl0_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.512z_d_inl0_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu runTest.cc -o build.512z_d_inl0_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu runTest.cc -o build.512z_d_inl0_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.512z_d_inl0_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512z_d_inl0_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512z_d_inl0_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.512z_d_inl0_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.512z_d_inl0_hrd0/libmg5amc_common.so build.512z_d_inl0_hrd0/Parameters_sm.o build.512z_d_inl0_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512z_d_inl0_hrd0/libmg5amc_gg_ttx_cuda.so build.512z_d_inl0_hrd0/gCPPProcess.o build.512z_d_inl0_hrd0/gMatrixElementKernels.o build.512z_d_inl0_hrd0/gBridgeKernels.o build.512z_d_inl0_hrd0/gCrossSectionKernels.o build.512z_d_inl0_hrd0/fbridge_cu.o -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512z_d_inl0_hrd0/libmg5amc_gg_ttx_cpp.so build.512z_d_inl0_hrd0/CPPProcess.o build.512z_d_inl0_hrd0/MatrixElementKernels.o build.512z_d_inl0_hrd0/BridgeKernels.o build.512z_d_inl0_hrd0/CrossSectionKernels.o build.512z_d_inl0_hrd0/fbridge.o -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl0_hrd0/runTest.exe build.512z_d_inl0_hrd0/CPPProcess.o build.512z_d_inl0_hrd0/MatrixElementKernels.o build.512z_d_inl0_hrd0/BridgeKernels.o build.512z_d_inl0_hrd0/CrossSectionKernels.o build.512z_d_inl0_hrd0/RandomNumberKernels.o build.512z_d_inl0_hrd0/RamboSamplingKernels.o build.512z_d_inl0_hrd0/testxxx.o  build.512z_d_inl0_hrd0/testmisc.o  build.512z_d_inl0_hrd0/runTest.o build.512z_d_inl0_hrd0/gCPPProcess.o build.512z_d_inl0_hrd0/gMatrixElementKernels.o build.512z_d_inl0_hrd0/gBridgeKernels.o build.512z_d_inl0_hrd0/gCrossSectionKernels.o build.512z_d_inl0_hrd0/gRandomNumberKernels.o build.512z_d_inl0_hrd0/gRamboSamplingKernels.o build.512z_d_inl0_hrd0/testxxx_cu.o  build.512z_d_inl0_hrd0/testmisc_cu.o  build.512z_d_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_d_inl0_hrd0/check.exe build.512z_d_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_gg_ttx_cpp build.512z_d_inl0_hrd0/RandomNumberKernels.o build.512z_d_inl0_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_d_inl0_hrd0/fcheck.exe build.512z_d_inl0_hrd0/fcheck_sa.o build.512z_d_inl0_hrd0/fsampler.o -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_gg_ttx_cpp build.512z_d_inl0_hrd0/RandomNumberKernels.o build.512z_d_inl0_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl0_hrd0/gcheck.exe build.512z_d_inl0_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_gg_ttx_cuda build.512z_d_inl0_hrd0/gRandomNumberKernels.o build.512z_d_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl0_hrd0/fgcheck.exe build.512z_d_inl0_hrd0/fcheck_sa.o build.512z_d_inl0_hrd0/fsampler_cu.o -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_gg_ttx_cuda build.512z_d_inl0_hrd0/gRandomNumberKernels.o build.512z_d_inl0_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512z_d_inl0_hrd0/libmg5amc_gg_ttx_cuda.so build.512z_d_inl0_hrd0/gCPPProcess.o build.512z_d_inl0_hrd0/gMatrixElementKernels.o build.512z_d_inl0_hrd0/gBridgeKernels.o build.512z_d_inl0_hrd0/gCrossSectionKernels.o build.512z_d_inl0_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512z_d_inl0_hrd0/libmg5amc_gg_ttx_cpp.so build.512z_d_inl0_hrd0/CPPProcess.o build.512z_d_inl0_hrd0/MatrixElementKernels.o build.512z_d_inl0_hrd0/BridgeKernels.o build.512z_d_inl0_hrd0/CrossSectionKernels.o build.512z_d_inl0_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_d_inl0_hrd0/fcheck.exe build.512z_d_inl0_hrd0/fcheck_sa.o build.512z_d_inl0_hrd0/fsampler.o -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_d_inl0_hrd0'  -lgfortran -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_gg_ttx_cpp build.512z_d_inl0_hrd0/RandomNumberKernels.o build.512z_d_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl0_hrd0/gcheck.exe build.512z_d_inl0_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl0_hrd0'  -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_gg_ttx_cuda build.512z_d_inl0_hrd0/gRandomNumberKernels.o build.512z_d_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl0_hrd0/fgcheck.exe build.512z_d_inl0_hrd0/fcheck_sa.o build.512z_d_inl0_hrd0/fsampler_cu.o -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl0_hrd0'  -lgfortran -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_gg_ttx_cuda build.512z_d_inl0_hrd0/gRandomNumberKernels.o build.512z_d_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_d_inl0_hrd0/check.exe build.512z_d_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_d_inl0_hrd0'  -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_gg_ttx_cpp build.512z_d_inl0_hrd0/RandomNumberKernels.o build.512z_d_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl0_hrd0/runTest.exe build.512z_d_inl0_hrd0/CPPProcess.o build.512z_d_inl0_hrd0/MatrixElementKernels.o build.512z_d_inl0_hrd0/BridgeKernels.o build.512z_d_inl0_hrd0/CrossSectionKernels.o build.512z_d_inl0_hrd0/RandomNumberKernels.o build.512z_d_inl0_hrd0/RamboSamplingKernels.o build.512z_d_inl0_hrd0/testxxx.o  build.512z_d_inl0_hrd0/testmisc.o  build.512z_d_inl0_hrd0/runTest.o build.512z_d_inl0_hrd0/gCPPProcess.o build.512z_d_inl0_hrd0/gMatrixElementKernels.o build.512z_d_inl0_hrd0/gBridgeKernels.o build.512z_d_inl0_hrd0/gCrossSectionKernels.o build.512z_d_inl0_hrd0/gRandomNumberKernels.o build.512z_d_inl0_hrd0/gRamboSamplingKernels.o build.512z_d_inl0_hrd0/testxxx_cu.o  build.512z_d_inl0_hrd0/testmisc_cu.o  build.512z_d_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl0_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
 touch build.512z_d_inl0_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_d_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.512z_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_d_inl0_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_d_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512z_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_d_inl0_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.512z_d_inl0_hrd0/libmg5amc_gg_ttx_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_d_inl0_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512z_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_d_inl0_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:03:51
+DATE: 2022-09-24_23:58:31
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/check.exe -p 2048 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/check.exe -p 2048 256 4 OMP=
 Process                     = SIGMA_SM_GG_TTX_CPP [gcc 11.2.0] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 3.339284e+05                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 3.732275e+05                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 3.732275e+05                 )  sec^-1
-MeanMatrixElemValue         = ( 2.086689e+00 +- 3.413217e-03 )  GeV^0
-TOTAL       :     3.292598 sec
-real	0m3.311s
+EvtsPerSec[Rmb+ME]     (23) = ( 3.350916e+05                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 3.745238e+05                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 3.745238e+05                 )  sec^-1
+MeanMatrixElemValue         = ( 2.086360e+00 +- 2.416141e-03 )  GeV^0
+TOTAL       :     6.479745 sec
+real	0m6.498s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2: 1031) (512y:   94) (512z: 1634)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 2.028807e+00
 Avg ME (F77/C++)    = 2.0288063388516204
 Relative difference = 3.2588037186351226e-07
@@ -3833,13 +3870,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:03:56 CEST 2022 Will execute './throughputX.sh -makej -ggtt -512zonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:58:53 CEST 2022 Will execute './throughputX.sh -makej -ggtt -512zonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -512zonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
 CUDACPP_BUILDDIR='build.512z_d_inl1_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -3849,71 +3886,72 @@ HELINL=1
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.512z_d_inl1_hrd0 for tag=512z_d_inl1_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.512z_d_inl1_hrd0
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.512z_d_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.512z_d_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512z_d_inl1_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512z_d_inl1_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512z_d_inl1_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512z_d_inl1_hrd0/fbridge_cu.o
 AVX=512z
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.512z_d_inl1_hrd0/gcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.512z_d_inl1_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512z_d_inl1_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512z_d_inl1_hrd0/gBridgeKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512z_d_inl1_hrd0/gCrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.512z_d_inl1_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.512z_d_inl1_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512z_d_inl1_hrd0/fbridge_cu.o
-mkdir -p ../lib/build.512z_d_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512z_d_inl1_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512z_d_inl1_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512z_d_inl1_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512z_d_inl1_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.512z_d_inl1_hrd0/check_sa.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.512z_d_inl1_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.512z_d_inl1_hrd0/CPPProcess.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.512z_d_inl1_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.512z_d_inl1_hrd0/BridgeKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.512z_d_inl1_hrd0/CrossSectionKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.512z_d_inl1_hrd0/fbridge.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.512z_d_inl1_hrd0/RandomNumberKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.512z_d_inl1_hrd0/Parameters_sm.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.512z_d_inl1_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.512z_d_inl1_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.512z_d_inl1_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512z_d_inl1_hrd0/testxxx_cu.o
+mkdir -p ../lib/build.512z_d_inl1_hrd0
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512z_d_inl1_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.512z_d_inl1_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512z_d_inl1_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512z_d_inl1_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.512z_d_inl1_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.512z_d_inl1_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.512z_d_inl1_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.512z_d_inl1_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512z_d_inl1_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512z_d_inl1_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.512z_d_inl1_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.512z_d_inl1_hrd0/libmg5amc_common.so build.512z_d_inl1_hrd0/Parameters_sm.o build.512z_d_inl1_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512z_d_inl1_hrd0/libmg5amc_gg_ttx_cuda.so build.512z_d_inl1_hrd0/gCPPProcess.o build.512z_d_inl1_hrd0/gMatrixElementKernels.o build.512z_d_inl1_hrd0/gBridgeKernels.o build.512z_d_inl1_hrd0/gCrossSectionKernels.o build.512z_d_inl1_hrd0/fbridge_cu.o -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512z_d_inl1_hrd0/libmg5amc_gg_ttx_cpp.so build.512z_d_inl1_hrd0/CPPProcess.o build.512z_d_inl1_hrd0/MatrixElementKernels.o build.512z_d_inl1_hrd0/BridgeKernels.o build.512z_d_inl1_hrd0/CrossSectionKernels.o build.512z_d_inl1_hrd0/fbridge.o -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl1_hrd0/runTest.exe build.512z_d_inl1_hrd0/CPPProcess.o build.512z_d_inl1_hrd0/MatrixElementKernels.o build.512z_d_inl1_hrd0/BridgeKernels.o build.512z_d_inl1_hrd0/CrossSectionKernels.o build.512z_d_inl1_hrd0/RandomNumberKernels.o build.512z_d_inl1_hrd0/RamboSamplingKernels.o build.512z_d_inl1_hrd0/testxxx.o  build.512z_d_inl1_hrd0/testmisc.o  build.512z_d_inl1_hrd0/runTest.o build.512z_d_inl1_hrd0/gCPPProcess.o build.512z_d_inl1_hrd0/gMatrixElementKernels.o build.512z_d_inl1_hrd0/gBridgeKernels.o build.512z_d_inl1_hrd0/gCrossSectionKernels.o build.512z_d_inl1_hrd0/gRandomNumberKernels.o build.512z_d_inl1_hrd0/gRamboSamplingKernels.o build.512z_d_inl1_hrd0/testxxx_cu.o  build.512z_d_inl1_hrd0/testmisc_cu.o  build.512z_d_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_d_inl1_hrd0/check.exe build.512z_d_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_gg_ttx_cpp build.512z_d_inl1_hrd0/RandomNumberKernels.o build.512z_d_inl1_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_d_inl1_hrd0/fcheck.exe build.512z_d_inl1_hrd0/fcheck_sa.o build.512z_d_inl1_hrd0/fsampler.o -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_gg_ttx_cpp build.512z_d_inl1_hrd0/RandomNumberKernels.o build.512z_d_inl1_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl1_hrd0/gcheck.exe build.512z_d_inl1_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_gg_ttx_cuda build.512z_d_inl1_hrd0/gRandomNumberKernels.o build.512z_d_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl1_hrd0/fgcheck.exe build.512z_d_inl1_hrd0/fcheck_sa.o build.512z_d_inl1_hrd0/fsampler_cu.o -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_gg_ttx_cuda build.512z_d_inl1_hrd0/gRandomNumberKernels.o build.512z_d_inl1_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512z_d_inl1_hrd0/libmg5amc_gg_ttx_cuda.so build.512z_d_inl1_hrd0/gCPPProcess.o build.512z_d_inl1_hrd0/gMatrixElementKernels.o build.512z_d_inl1_hrd0/gBridgeKernels.o build.512z_d_inl1_hrd0/gCrossSectionKernels.o build.512z_d_inl1_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl1_hrd0/gcheck.exe build.512z_d_inl1_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl1_hrd0'  -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_gg_ttx_cuda build.512z_d_inl1_hrd0/gRandomNumberKernels.o build.512z_d_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl1_hrd0/fgcheck.exe build.512z_d_inl1_hrd0/fcheck_sa.o build.512z_d_inl1_hrd0/fsampler_cu.o -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl1_hrd0'  -lgfortran -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_gg_ttx_cuda build.512z_d_inl1_hrd0/gRandomNumberKernels.o build.512z_d_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512z_d_inl1_hrd0/libmg5amc_gg_ttx_cpp.so build.512z_d_inl1_hrd0/CPPProcess.o build.512z_d_inl1_hrd0/MatrixElementKernels.o build.512z_d_inl1_hrd0/BridgeKernels.o build.512z_d_inl1_hrd0/CrossSectionKernels.o build.512z_d_inl1_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_d_inl1_hrd0/fcheck.exe build.512z_d_inl1_hrd0/fcheck_sa.o build.512z_d_inl1_hrd0/fsampler.o -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_d_inl1_hrd0'  -lgfortran -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_gg_ttx_cpp build.512z_d_inl1_hrd0/RandomNumberKernels.o build.512z_d_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_d_inl1_hrd0/check.exe build.512z_d_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_d_inl1_hrd0'  -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_gg_ttx_cpp build.512z_d_inl1_hrd0/RandomNumberKernels.o build.512z_d_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl1_hrd0/runTest.exe build.512z_d_inl1_hrd0/CPPProcess.o build.512z_d_inl1_hrd0/MatrixElementKernels.o build.512z_d_inl1_hrd0/BridgeKernels.o build.512z_d_inl1_hrd0/CrossSectionKernels.o build.512z_d_inl1_hrd0/RandomNumberKernels.o build.512z_d_inl1_hrd0/RamboSamplingKernels.o build.512z_d_inl1_hrd0/testxxx.o  build.512z_d_inl1_hrd0/testmisc.o  build.512z_d_inl1_hrd0/runTest.o build.512z_d_inl1_hrd0/gCPPProcess.o build.512z_d_inl1_hrd0/gMatrixElementKernels.o build.512z_d_inl1_hrd0/gBridgeKernels.o build.512z_d_inl1_hrd0/gCrossSectionKernels.o build.512z_d_inl1_hrd0/gRandomNumberKernels.o build.512z_d_inl1_hrd0/gRamboSamplingKernels.o build.512z_d_inl1_hrd0/testxxx_cu.o  build.512z_d_inl1_hrd0/testmisc_cu.o  build.512z_d_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl1_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
 touch build.512z_d_inl1_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_d_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.512z_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_d_inl1_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_d_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512z_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_d_inl1_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.512z_d_inl1_hrd0/libmg5amc_gg_ttx_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_d_inl1_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512z_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_d_inl1_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:03:57
+DATE: 2022-09-24_23:59:01
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl1_hrd0/check.exe -p 2048 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl1_hrd0/check.exe -p 2048 256 4 OMP=
 Process                     = SIGMA_SM_GG_TTX_CPP [gcc 11.2.0] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 3.100956e+05                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 3.437735e+05                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 3.437735e+05                 )  sec^-1
-MeanMatrixElemValue         = ( 2.086689e+00 +- 3.413217e-03 )  GeV^0
-TOTAL       :     3.533605 sec
-real	0m3.552s
+EvtsPerSec[Rmb+ME]     (23) = ( 3.130805e+05                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 3.472055e+05                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 3.472055e+05                 )  sec^-1
+MeanMatrixElemValue         = ( 2.086360e+00 +- 2.416141e-03 )  GeV^0
+TOTAL       :     6.919415 sec
+real	0m6.938s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2: 1591) (512y:  255) (512z: 1652)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl1_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl1_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl1_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl1_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 2.028807e+00
 Avg ME (F77/C++)    = 2.0288063388516204
 Relative difference = 3.2588037186351226e-07
@@ -3921,13 +3959,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:04:03 CEST 2022 Will execute './throughputX.sh -makej -ggtt -512zonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:59:23 CEST 2022 Will execute './throughputX.sh -makej -ggtt -512zonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -512zonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
 CUDACPP_BUILDDIR='build.512z_f_inl0_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -3937,71 +3975,72 @@ HELINL=0
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.512z_f_inl0_hrd0 for tag=512z_f_inl0_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.512z_f_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gcheck_sa.cu -o build.512z_f_inl0_hrd0/gcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gCPPProcess.cu -o build.512z_f_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gcheck_sa.cu -o build.512z_f_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gCPPProcess.cu -o build.512z_f_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512z_f_inl0_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512z_f_inl0_hrd0/gBridgeKernels.o
 AVX=512z
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512z_f_inl0_hrd0/gMatrixElementKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512z_f_inl0_hrd0/gBridgeKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -c Parameters_sm.cc -o build.512z_f_inl0_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -c read_slha.cc -o build.512z_f_inl0_hrd0/read_slha.o
-mkdir -p ../lib/build.512z_f_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512z_f_inl0_hrd0/gCrossSectionKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512z_f_inl0_hrd0/fbridge_cu.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512z_f_inl0_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512z_f_inl0_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512z_f_inl0_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512z_f_inl0_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512z_f_inl0_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512z_f_inl0_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.512z_f_inl0_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.512z_f_inl0_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.512z_f_inl0_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.512z_f_inl0_hrd0/BridgeKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.512z_f_inl0_hrd0/CrossSectionKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.512z_f_inl0_hrd0/fbridge.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -c read_slha.cc -o build.512z_f_inl0_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.512z_f_inl0_hrd0/RandomNumberKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -c Parameters_sm.cc -o build.512z_f_inl0_hrd0/Parameters_sm.o
+mkdir -p ../lib/build.512z_f_inl0_hrd0
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.512z_f_inl0_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.512z_f_inl0_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512z_f_inl0_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512z_f_inl0_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.512z_f_inl0_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512z_f_inl0_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512z_f_inl0_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.512z_f_inl0_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu runTest.cc -o build.512z_f_inl0_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu runTest.cc -o build.512z_f_inl0_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.512z_f_inl0_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512z_f_inl0_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512z_f_inl0_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.512z_f_inl0_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.512z_f_inl0_hrd0/libmg5amc_common.so build.512z_f_inl0_hrd0/Parameters_sm.o build.512z_f_inl0_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512z_f_inl0_hrd0/libmg5amc_gg_ttx_cuda.so build.512z_f_inl0_hrd0/gCPPProcess.o build.512z_f_inl0_hrd0/gMatrixElementKernels.o build.512z_f_inl0_hrd0/gBridgeKernels.o build.512z_f_inl0_hrd0/gCrossSectionKernels.o build.512z_f_inl0_hrd0/fbridge_cu.o -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512z_f_inl0_hrd0/libmg5amc_gg_ttx_cpp.so build.512z_f_inl0_hrd0/CPPProcess.o build.512z_f_inl0_hrd0/MatrixElementKernels.o build.512z_f_inl0_hrd0/BridgeKernels.o build.512z_f_inl0_hrd0/CrossSectionKernels.o build.512z_f_inl0_hrd0/fbridge.o -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl0_hrd0/runTest.exe build.512z_f_inl0_hrd0/CPPProcess.o build.512z_f_inl0_hrd0/MatrixElementKernels.o build.512z_f_inl0_hrd0/BridgeKernels.o build.512z_f_inl0_hrd0/CrossSectionKernels.o build.512z_f_inl0_hrd0/RandomNumberKernels.o build.512z_f_inl0_hrd0/RamboSamplingKernels.o build.512z_f_inl0_hrd0/testxxx.o  build.512z_f_inl0_hrd0/testmisc.o  build.512z_f_inl0_hrd0/runTest.o build.512z_f_inl0_hrd0/gCPPProcess.o build.512z_f_inl0_hrd0/gMatrixElementKernels.o build.512z_f_inl0_hrd0/gBridgeKernels.o build.512z_f_inl0_hrd0/gCrossSectionKernels.o build.512z_f_inl0_hrd0/gRandomNumberKernels.o build.512z_f_inl0_hrd0/gRamboSamplingKernels.o build.512z_f_inl0_hrd0/testxxx_cu.o  build.512z_f_inl0_hrd0/testmisc_cu.o  build.512z_f_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_f_inl0_hrd0/check.exe build.512z_f_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_gg_ttx_cpp build.512z_f_inl0_hrd0/RandomNumberKernels.o build.512z_f_inl0_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_f_inl0_hrd0/fcheck.exe build.512z_f_inl0_hrd0/fcheck_sa.o build.512z_f_inl0_hrd0/fsampler.o -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_gg_ttx_cpp build.512z_f_inl0_hrd0/RandomNumberKernels.o build.512z_f_inl0_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl0_hrd0/gcheck.exe build.512z_f_inl0_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_gg_ttx_cuda build.512z_f_inl0_hrd0/gRandomNumberKernels.o build.512z_f_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl0_hrd0/fgcheck.exe build.512z_f_inl0_hrd0/fcheck_sa.o build.512z_f_inl0_hrd0/fsampler_cu.o -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_gg_ttx_cuda build.512z_f_inl0_hrd0/gRandomNumberKernels.o build.512z_f_inl0_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512z_f_inl0_hrd0/libmg5amc_gg_ttx_cuda.so build.512z_f_inl0_hrd0/gCPPProcess.o build.512z_f_inl0_hrd0/gMatrixElementKernels.o build.512z_f_inl0_hrd0/gBridgeKernels.o build.512z_f_inl0_hrd0/gCrossSectionKernels.o build.512z_f_inl0_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512z_f_inl0_hrd0/libmg5amc_gg_ttx_cpp.so build.512z_f_inl0_hrd0/CPPProcess.o build.512z_f_inl0_hrd0/MatrixElementKernels.o build.512z_f_inl0_hrd0/BridgeKernels.o build.512z_f_inl0_hrd0/CrossSectionKernels.o build.512z_f_inl0_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_f_inl0_hrd0/fcheck.exe build.512z_f_inl0_hrd0/fcheck_sa.o build.512z_f_inl0_hrd0/fsampler.o -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_f_inl0_hrd0'  -lgfortran -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_gg_ttx_cpp build.512z_f_inl0_hrd0/RandomNumberKernels.o build.512z_f_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl0_hrd0/gcheck.exe build.512z_f_inl0_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl0_hrd0'  -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_gg_ttx_cuda build.512z_f_inl0_hrd0/gRandomNumberKernels.o build.512z_f_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl0_hrd0/fgcheck.exe build.512z_f_inl0_hrd0/fcheck_sa.o build.512z_f_inl0_hrd0/fsampler_cu.o -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl0_hrd0'  -lgfortran -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_gg_ttx_cuda build.512z_f_inl0_hrd0/gRandomNumberKernels.o build.512z_f_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_f_inl0_hrd0/check.exe build.512z_f_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_f_inl0_hrd0'  -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_gg_ttx_cpp build.512z_f_inl0_hrd0/RandomNumberKernels.o build.512z_f_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl0_hrd0/runTest.exe build.512z_f_inl0_hrd0/CPPProcess.o build.512z_f_inl0_hrd0/MatrixElementKernels.o build.512z_f_inl0_hrd0/BridgeKernels.o build.512z_f_inl0_hrd0/CrossSectionKernels.o build.512z_f_inl0_hrd0/RandomNumberKernels.o build.512z_f_inl0_hrd0/RamboSamplingKernels.o build.512z_f_inl0_hrd0/testxxx.o  build.512z_f_inl0_hrd0/testmisc.o  build.512z_f_inl0_hrd0/runTest.o build.512z_f_inl0_hrd0/gCPPProcess.o build.512z_f_inl0_hrd0/gMatrixElementKernels.o build.512z_f_inl0_hrd0/gBridgeKernels.o build.512z_f_inl0_hrd0/gCrossSectionKernels.o build.512z_f_inl0_hrd0/gRandomNumberKernels.o build.512z_f_inl0_hrd0/gRamboSamplingKernels.o build.512z_f_inl0_hrd0/testxxx_cu.o  build.512z_f_inl0_hrd0/testmisc_cu.o  build.512z_f_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl0_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
 touch build.512z_f_inl0_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_f_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.512z_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_f_inl0_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_f_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512z_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_f_inl0_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.512z_f_inl0_hrd0/libmg5amc_gg_ttx_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_f_inl0_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512z_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_f_inl0_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:04:04
+DATE: 2022-09-24_23:59:33
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/check.exe -p 2048 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/check.exe -p 2048 256 4 OMP=
 Process                     = SIGMA_SM_GG_TTX_CPP [gcc 11.2.0] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK
 FP precision                = FLOAT (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 6.508285e+05                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 7.762139e+05                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 7.762139e+05                 )  sec^-1
-MeanMatrixElemValue         = ( 2.086782e+00 +- 3.413783e-03 )  GeV^0
-TOTAL       :     1.717989 sec
-real	0m1.730s
+EvtsPerSec[Rmb+ME]     (23) = ( 6.550747e+05                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 7.813071e+05                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 7.813071e+05                 )  sec^-1
+MeanMatrixElemValue         = ( 2.086442e+00 +- 2.416476e-03 )  GeV^0
+TOTAL       :     3.372698 sec
+real	0m3.385s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2: 1611) (512y:   21) (512z: 1839)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 2.028819e+00
 Avg ME (F77/C++)    = 2.0288188729900867
 Relative difference = 6.260288042122908e-08
@@ -4009,13 +4048,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:04:08 CEST 2022 Will execute './throughputX.sh -makej -ggtt -512zonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sat Sep 24 23:59:51 CEST 2022 Will execute './throughputX.sh -makej -ggtt -512zonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -512zonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx
 CUDACPP_BUILDDIR='build.512z_f_inl1_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -4025,22 +4064,18 @@ HELINL=1
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.512z_f_inl1_hrd0 for tag=512z_f_inl1_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.512z_f_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.512z_f_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.512z_f_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.512z_f_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512z_f_inl1_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512z_f_inl1_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512z_f_inl1_hrd0/gCrossSectionKernels.o
 AVX=512z
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.512z_f_inl1_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512z_f_inl1_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512z_f_inl1_hrd0/gBridgeKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.512z_f_inl1_hrd0/Parameters_sm.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512z_f_inl1_hrd0/gCrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.512z_f_inl1_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512z_f_inl1_hrd0/fbridge_cu.o
-mkdir -p ../lib/build.512z_f_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512z_f_inl1_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512z_f_inl1_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512z_f_inl1_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512z_f_inl1_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512z_f_inl1_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.512z_f_inl1_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.512z_f_inl1_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.512z_f_inl1_hrd0/MatrixElementKernels.o
@@ -4048,48 +4083,53 @@ ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.512z_f_inl1_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.512z_f_inl1_hrd0/fbridge.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.512z_f_inl1_hrd0/RandomNumberKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.512z_f_inl1_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.512z_f_inl1_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512z_f_inl1_hrd0/testxxx_cu.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.512z_f_inl1_hrd0/Parameters_sm.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512z_f_inl1_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.512z_f_inl1_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512z_f_inl1_hrd0/testmisc_cu.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.512z_f_inl1_hrd0/read_slha.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512z_f_inl1_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.512z_f_inl1_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.512z_f_inl1_hrd0/runTest_cu.o
+mkdir -p ../lib/build.512z_f_inl1_hrd0
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.512z_f_inl1_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.512z_f_inl1_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512z_f_inl1_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512z_f_inl1_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.512z_f_inl1_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.512z_f_inl1_hrd0/libmg5amc_common.so build.512z_f_inl1_hrd0/Parameters_sm.o build.512z_f_inl1_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512z_f_inl1_hrd0/libmg5amc_gg_ttx_cuda.so build.512z_f_inl1_hrd0/gCPPProcess.o build.512z_f_inl1_hrd0/gMatrixElementKernels.o build.512z_f_inl1_hrd0/gBridgeKernels.o build.512z_f_inl1_hrd0/gCrossSectionKernels.o build.512z_f_inl1_hrd0/fbridge_cu.o -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512z_f_inl1_hrd0/libmg5amc_gg_ttx_cpp.so build.512z_f_inl1_hrd0/CPPProcess.o build.512z_f_inl1_hrd0/MatrixElementKernels.o build.512z_f_inl1_hrd0/BridgeKernels.o build.512z_f_inl1_hrd0/CrossSectionKernels.o build.512z_f_inl1_hrd0/fbridge.o -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl1_hrd0/runTest.exe build.512z_f_inl1_hrd0/CPPProcess.o build.512z_f_inl1_hrd0/MatrixElementKernels.o build.512z_f_inl1_hrd0/BridgeKernels.o build.512z_f_inl1_hrd0/CrossSectionKernels.o build.512z_f_inl1_hrd0/RandomNumberKernels.o build.512z_f_inl1_hrd0/RamboSamplingKernels.o build.512z_f_inl1_hrd0/testxxx.o  build.512z_f_inl1_hrd0/testmisc.o  build.512z_f_inl1_hrd0/runTest.o build.512z_f_inl1_hrd0/gCPPProcess.o build.512z_f_inl1_hrd0/gMatrixElementKernels.o build.512z_f_inl1_hrd0/gBridgeKernels.o build.512z_f_inl1_hrd0/gCrossSectionKernels.o build.512z_f_inl1_hrd0/gRandomNumberKernels.o build.512z_f_inl1_hrd0/gRamboSamplingKernels.o build.512z_f_inl1_hrd0/testxxx_cu.o  build.512z_f_inl1_hrd0/testmisc_cu.o  build.512z_f_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_f_inl1_hrd0/check.exe build.512z_f_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_gg_ttx_cpp build.512z_f_inl1_hrd0/RandomNumberKernels.o build.512z_f_inl1_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_f_inl1_hrd0/fcheck.exe build.512z_f_inl1_hrd0/fcheck_sa.o build.512z_f_inl1_hrd0/fsampler.o -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_gg_ttx_cpp build.512z_f_inl1_hrd0/RandomNumberKernels.o build.512z_f_inl1_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl1_hrd0/gcheck.exe build.512z_f_inl1_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_gg_ttx_cuda build.512z_f_inl1_hrd0/gRandomNumberKernels.o build.512z_f_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl1_hrd0/fgcheck.exe build.512z_f_inl1_hrd0/fcheck_sa.o build.512z_f_inl1_hrd0/fsampler_cu.o -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_gg_ttx_cuda build.512z_f_inl1_hrd0/gRandomNumberKernels.o build.512z_f_inl1_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512z_f_inl1_hrd0/libmg5amc_gg_ttx_cuda.so build.512z_f_inl1_hrd0/gCPPProcess.o build.512z_f_inl1_hrd0/gMatrixElementKernels.o build.512z_f_inl1_hrd0/gBridgeKernels.o build.512z_f_inl1_hrd0/gCrossSectionKernels.o build.512z_f_inl1_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl1_hrd0/gcheck.exe build.512z_f_inl1_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl1_hrd0'  -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_gg_ttx_cuda build.512z_f_inl1_hrd0/gRandomNumberKernels.o build.512z_f_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl1_hrd0/fgcheck.exe build.512z_f_inl1_hrd0/fcheck_sa.o build.512z_f_inl1_hrd0/fsampler_cu.o -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl1_hrd0'  -lgfortran -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_gg_ttx_cuda build.512z_f_inl1_hrd0/gRandomNumberKernels.o build.512z_f_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512z_f_inl1_hrd0/libmg5amc_gg_ttx_cpp.so build.512z_f_inl1_hrd0/CPPProcess.o build.512z_f_inl1_hrd0/MatrixElementKernels.o build.512z_f_inl1_hrd0/BridgeKernels.o build.512z_f_inl1_hrd0/CrossSectionKernels.o build.512z_f_inl1_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_f_inl1_hrd0/fcheck.exe build.512z_f_inl1_hrd0/fcheck_sa.o build.512z_f_inl1_hrd0/fsampler.o -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_f_inl1_hrd0'  -lgfortran -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_gg_ttx_cpp build.512z_f_inl1_hrd0/RandomNumberKernels.o build.512z_f_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_f_inl1_hrd0/check.exe build.512z_f_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_f_inl1_hrd0'  -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_gg_ttx_cpp build.512z_f_inl1_hrd0/RandomNumberKernels.o build.512z_f_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl1_hrd0/runTest.exe build.512z_f_inl1_hrd0/CPPProcess.o build.512z_f_inl1_hrd0/MatrixElementKernels.o build.512z_f_inl1_hrd0/BridgeKernels.o build.512z_f_inl1_hrd0/CrossSectionKernels.o build.512z_f_inl1_hrd0/RandomNumberKernels.o build.512z_f_inl1_hrd0/RamboSamplingKernels.o build.512z_f_inl1_hrd0/testxxx.o  build.512z_f_inl1_hrd0/testmisc.o  build.512z_f_inl1_hrd0/runTest.o build.512z_f_inl1_hrd0/gCPPProcess.o build.512z_f_inl1_hrd0/gMatrixElementKernels.o build.512z_f_inl1_hrd0/gBridgeKernels.o build.512z_f_inl1_hrd0/gCrossSectionKernels.o build.512z_f_inl1_hrd0/gRandomNumberKernels.o build.512z_f_inl1_hrd0/gRamboSamplingKernels.o build.512z_f_inl1_hrd0/testxxx_cu.o  build.512z_f_inl1_hrd0/testmisc_cu.o  build.512z_f_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl1_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx'
 touch build.512z_f_inl1_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_f_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.512z_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_f_inl1_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_f_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512z_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_f_inl1_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.512z_f_inl1_hrd0/libmg5amc_gg_ttx_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_f_inl1_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512z_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttx_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_f_inl1_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:04:09
+DATE: 2022-09-25_00:00:01
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl1_hrd0/check.exe -p 2048 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl1_hrd0/check.exe -p 2048 256 4 OMP=
 Process                     = SIGMA_SM_GG_TTX_CPP [gcc 11.2.0] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK
 FP precision                = FLOAT (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 4.947286e+05                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 5.637861e+05                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 5.637861e+05                 )  sec^-1
-MeanMatrixElemValue         = ( 2.086782e+00 +- 3.413783e-03 )  GeV^0
-TOTAL       :     2.226116 sec
-real	0m2.238s
+EvtsPerSec[Rmb+ME]     (23) = ( 4.955980e+05                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 5.647409e+05                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 5.647409e+05                 )  sec^-1
+MeanMatrixElemValue         = ( 2.086442e+00 +- 2.416476e-03 )  GeV^0
+TOTAL       :     4.403926 sec
+real	0m4.416s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2: 3432) (512y:    0) (512z: 2011)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl1_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl1_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl1_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl1_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 2.028819e+00
 Avg ME (F77/C++)    = 2.0288188448175788
 Relative difference = 7.648904172103859e-08
@@ -4097,12 +4137,12 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:04:13 CEST 2022 Will execute './throughputX.sh -makej -ggttg -nocpp  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:00:20 CEST 2022 Will execute './throughputX.sh -makej -ggttg -nocpp  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
 CUDACPP_BUILDDIR='build.none_d_inl0_hrd0'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -w -cpp  -c myamp.f -I../../Source/ -fopenmp -o myamp.o
 cd ../../Source; make
@@ -4121,7 +4161,9 @@ ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfort
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -std=c++11 -Wall -Wshadow -Wextra -c counters.cpp -o counters.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -w -cpp  -c -DMG5AMC_MEEXPORTER_CUDACPP auto_dsig1.f -I../../Source/ -fopenmp -o auto_dsig1_cudacpp.o
 make -f cudacpp.mk
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/Source'
+OMPFLAGS=
+AVX=none
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/Source'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o StringCast.o StringCast.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o ranmar.o ranmar.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o alfas_functions.o alfas_functions.f
@@ -4132,14 +4174,12 @@ ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfort
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o ran1.o ran1.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o rw_events.o rw_events.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o rw_routines.o rw_routines.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o kin_functions.o kin_functions.f
-OMPFLAGS=
-AVX=none
 FPTYPE=d
 HELINL=0
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.none_d_inl0_hrd0 for tag=none_d_inl0_hrd0_hasCurand (USEBUILDDIR is set = 1)
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o kin_functions.o kin_functions.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o open_file.o open_file.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o basecode.o basecode.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o setrun.o setrun.f
@@ -4152,122 +4192,123 @@ cd PDF; make
 cd MODEL; make    
 cd CERNLIB; make
 cd BIAS/dummy; make
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/Source/BIAS/dummy'
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o dummy.o dummy.f
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/Source/DHELAS'
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/Source/DHELAS'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o aloha_functions.o aloha_functions.f
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/Source/CERNLIB'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o abend.o abend.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o VVV1_0.o VVV1_0.f
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/Source/PDF'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o Ctq6Pdf.o Ctq6Pdf.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o VVVV3P0_1.o VVVV3P0_1.f
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/Source/CERNLIB'
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o abend.o abend.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o FFV1_1.o FFV1_1.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o VVVV4P0_1.o VVVV4P0_1.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o dlsqp2.o dlsqp2.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o FFV1P0_3.o FFV1P0_3.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o lenocc.o lenocc.f
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/Source/MODEL'
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/Source/MODEL'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o couplings.o couplings.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o mtlprt.o mtlprt.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o lha_read.o lha_read.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o mtlset.o mtlset.f
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/Source/PDF'
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o Ctq6Pdf.o Ctq6Pdf.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o FFV1_0.o FFV1_0.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o radmul.o radmul.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o FFV1_2.o FFV1_2.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o VVVV1P0_1.o VVVV1P0_1.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o printout.o printout.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o pdfwrap.o pdfwrap.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I.. -c -o rw_para.o rw_para.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o lenocc.o lenocc.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o opendata.o opendata.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o lha_read.o lha_read.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o FFV1_1.o FFV1_1.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o mtlprt.o mtlprt.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o pdf.o pdf.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o printout.o printout.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o PhotonFlux.o PhotonFlux.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o model_functions.o model_functions.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o mtlset.o mtlset.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o radmul.o radmul.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o pdg2pdf.o pdg2pdf.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o VVV1P0_1.o VVV1P0_1.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I.. -c -o rw_para.o rw_para.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o model_functions.o model_functions.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o couplings1.o couplings1.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o couplings2.o couplings2.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o VVVV4P0_1.o VVVV4P0_1.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o NNPDFDriver.o NNPDFDriver.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o FFV1P0_3.o FFV1P0_3.f
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/Source/BIAS/dummy'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o dummy.o dummy.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o FFV1_0.o FFV1_0.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o eepdf.o eepdf.f
-ar cru  ../../../lib/libbias.a  dummy.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o couplings2.o couplings2.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o gridpdfaux.o gridpdfaux.f
-ranlib  ../../../lib/libbias.a
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o FFV1_2.o FFV1_2.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o VVVV1P0_1.o VVVV1P0_1.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o dfint.o dfint.f
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/Source/BIAS/dummy'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o VVV1P0_1.o VVV1P0_1.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o kerset.o kerset.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o ElectroweakFluxDriver.o ElectroweakFluxDriver.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o ElectroweakFlux.o ElectroweakFlux.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o DiscreteSampler.o DiscreteSampler.f
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
 mkdir -p build.none_d_inl0_hrd0
 make -C ../../src  -f cudacpp_src.mk
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gcheck_sa.cu -o build.none_d_inl0_hrd0/gcheck_sa.o
+ar cru  ../../../lib/libbias.a  dummy.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gcheck_sa.cu -o build.none_d_inl0_hrd0/gcheck_sa.o
+ranlib  ../../../lib/libbias.a
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/Source/BIAS/dummy'
 AVX=none
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gCPPProcess.cu -o build.none_d_inl0_hrd0/gCPPProcess.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.none_d_inl0_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gCPPProcess.cu -o build.none_d_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.none_d_inl0_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gBridgeKernels.cu -o build.none_d_inl0_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.none_d_inl0_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fbridge.cc -o build.none_d_inl0_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.none_d_inl0_hrd0/gRandomNumberKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o DiscreteSampler.o DiscreteSampler.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -c Parameters_sm.cc -o build.none_d_inl0_hrd0/Parameters_sm.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -c read_slha.cc -o build.none_d_inl0_hrd0/read_slha.o
 mkdir -p ../lib/build.none_d_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gBridgeKernels.cu -o build.none_d_inl0_hrd0/gBridgeKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.none_d_inl0_hrd0/gCrossSectionKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fbridge.cc -o build.none_d_inl0_hrd0/fbridge_cu.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.none_d_inl0_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.none_d_inl0_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.none_d_inl0_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.none_d_inl0_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.none_d_inl0_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.none_d_inl0_hrd0/MatrixElementKernels.o
-ar cru  ../../lib/libcernlib.a  abend.o dlsqp2.o lenocc.o mtlprt.o mtlset.o radmul.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.none_d_inl0_hrd0/BridgeKernels.o
-ranlib  ../../lib/libcernlib.a
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.none_d_inl0_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.none_d_inl0_hrd0/fbridge.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/Source/CERNLIB'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.none_d_inl0_hrd0/RandomNumberKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.none_d_inl0_hrd0/libmg5amc_common.so build.none_d_inl0_hrd0/Parameters_sm.o build.none_d_inl0_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.none_d_inl0_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.none_d_inl0_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testxxx.cc -o build.none_d_inl0_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testxxx.cc -o build.none_d_inl0_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.none_d_inl0_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testmisc.cc -o build.none_d_inl0_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testmisc.cc -o build.none_d_inl0_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.none_d_inl0_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu runTest.cc -o build.none_d_inl0_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu runTest.cc -o build.none_d_inl0_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.none_d_inl0_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fsampler.cc -o build.none_d_inl0_hrd0/fsampler_cu.o
-ar cru  ../../lib/libpdf.a  Ctq6Pdf.o pdfwrap.o opendata.o pdf.o PhotonFlux.o pdg2pdf.o NNPDFDriver.o eepdf.o gridpdfaux.o dfint.o kerset.o ElectroweakFluxDriver.o ElectroweakFlux.o
-ranlib  ../../lib/libpdf.a
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/Source/PDF'
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fsampler.cc -o build.none_d_inl0_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.none_d_inl0_hrd0/fsampler.o
+ar cru  ../../lib/libpdf.a  Ctq6Pdf.o pdfwrap.o opendata.o pdf.o PhotonFlux.o pdg2pdf.o NNPDFDriver.o eepdf.o gridpdfaux.o dfint.o kerset.o ElectroweakFluxDriver.o ElectroweakFlux.o
 ar cru  ../../lib/libmodel.a  couplings.o lha_read.o printout.o rw_para.o model_functions.o couplings1.o couplings2.o
+ranlib  ../../lib/libpdf.a
 ranlib  ../../lib/libmodel.a
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/Source/MODEL'
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.none_d_inl0_hrd0/libmg5amc_gg_ttxg_cpp.so build.none_d_inl0_hrd0/CPPProcess.o build.none_d_inl0_hrd0/MatrixElementKernels.o build.none_d_inl0_hrd0/BridgeKernels.o build.none_d_inl0_hrd0/CrossSectionKernels.o build.none_d_inl0_hrd0/fbridge.o -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common
+ar cru  ../../lib/libcernlib.a  abend.o dlsqp2.o lenocc.o mtlprt.o mtlset.o radmul.o
 ar cru  ../lib/libgeneric.a  alfas_functions.o transpole.o invarients.o hfill.o pawgraphs.o ran1.o rw_events.o rw_routines.o kin_functions.o open_file.o basecode.o setrun.o run_printout.o dgauss.o readgrid.o getissud.o
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/Source/MODEL'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/Source/PDF'
+ranlib  ../../lib/libcernlib.a
 ranlib  ../lib/libgeneric.a
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_d_inl0_hrd0/check.exe build.none_d_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_gg_ttxg_cpp build.none_d_inl0_hrd0/RandomNumberKernels.o build.none_d_inl0_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_d_inl0_hrd0/fcheck.exe build.none_d_inl0_hrd0/fcheck_sa.o build.none_d_inl0_hrd0/fsampler.o -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_gg_ttxg_cpp build.none_d_inl0_hrd0/RandomNumberKernels.o build.none_d_inl0_hrd0/RamboSamplingKernels.o
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/Source/CERNLIB'
 ar cru  ../../lib/libdhelas.a  aloha_functions.o VVV1_0.o VVVV3P0_1.o FFV1_1.o VVVV4P0_1.o FFV1P0_3.o FFV1_0.o FFV1_2.o VVVV1P0_1.o VVV1P0_1.o
 ranlib  ../../lib/libdhelas.a
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/Source/DHELAS'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/Source/DHELAS'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.none_d_inl0_hrd0/libmg5amc_common.so build.none_d_inl0_hrd0/Parameters_sm.o build.none_d_inl0_hrd0/read_slha.o
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.none_d_inl0_hrd0/libmg5amc_gg_ttxg_cpp.so build.none_d_inl0_hrd0/CPPProcess.o build.none_d_inl0_hrd0/MatrixElementKernels.o build.none_d_inl0_hrd0/BridgeKernels.o build.none_d_inl0_hrd0/CrossSectionKernels.o build.none_d_inl0_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_d_inl0_hrd0/check.exe build.none_d_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_d_inl0_hrd0'  -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_gg_ttxg_cpp build.none_d_inl0_hrd0/RandomNumberKernels.o build.none_d_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_d_inl0_hrd0/fcheck.exe build.none_d_inl0_hrd0/fcheck_sa.o build.none_d_inl0_hrd0/fsampler.o -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_d_inl0_hrd0'  -lgfortran -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_gg_ttxg_cpp build.none_d_inl0_hrd0/RandomNumberKernels.o build.none_d_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o dsample.o dsample.f
 ar cru  ../lib/libdsample.a  dsample.o ranmar.o DiscreteSampler.o StringCast.o
 ranlib  ../lib/libdsample.a
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/Source'
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/Source'
 touch .libs
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -w -cpp  -c genps.f -I../../Source/ -fopenmp -o genps.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -w -cpp  -c driver.f -I../../Source/ -fopenmp -o driver.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -w -cpp  -c auto_dsig.f -I../../Source/ -fopenmp -o auto_dsig.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -w -cpp   -c matrix1.f -I../../Source/ -fopenmp
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -w -cpp  -c -DMG5AMC_MEEXPORTER_CUDACPP driver.f -I../../Source/ -fopenmp -o driver_cudacpp.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o madevent myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver.o  auto_dsig1.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.none_d_inl0_hrd0/libmg5amc_gg_ttxg_cuda.so build.none_d_inl0_hrd0/gCPPProcess.o build.none_d_inl0_hrd0/gMatrixElementKernels.o build.none_d_inl0_hrd0/gBridgeKernels.o build.none_d_inl0_hrd0/gCrossSectionKernels.o build.none_d_inl0_hrd0/fbridge_cu.o -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl0_hrd0/fgcheck.exe build.none_d_inl0_hrd0/fcheck_sa.o build.none_d_inl0_hrd0/fsampler_cu.o -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_gg_ttxg_cuda build.none_d_inl0_hrd0/gRandomNumberKernels.o build.none_d_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl0_hrd0/gcheck.exe build.none_d_inl0_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_gg_ttxg_cuda build.none_d_inl0_hrd0/gRandomNumberKernels.o build.none_d_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl0_hrd0/runTest.exe build.none_d_inl0_hrd0/CPPProcess.o build.none_d_inl0_hrd0/MatrixElementKernels.o build.none_d_inl0_hrd0/BridgeKernels.o build.none_d_inl0_hrd0/CrossSectionKernels.o build.none_d_inl0_hrd0/RandomNumberKernels.o build.none_d_inl0_hrd0/RamboSamplingKernels.o build.none_d_inl0_hrd0/testxxx.o  build.none_d_inl0_hrd0/testmisc.o  build.none_d_inl0_hrd0/runTest.o build.none_d_inl0_hrd0/gCPPProcess.o build.none_d_inl0_hrd0/gMatrixElementKernels.o build.none_d_inl0_hrd0/gBridgeKernels.o build.none_d_inl0_hrd0/gCrossSectionKernels.o build.none_d_inl0_hrd0/gRandomNumberKernels.o build.none_d_inl0_hrd0/gRamboSamplingKernels.o build.none_d_inl0_hrd0/testxxx_cu.o  build.none_d_inl0_hrd0/testmisc_cu.o  build.none_d_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o madevent myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver.o  auto_dsig1.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -lstdc++  -Wl,--no-relax 
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.none_d_inl0_hrd0/libmg5amc_gg_ttxg_cuda.so build.none_d_inl0_hrd0/gCPPProcess.o build.none_d_inl0_hrd0/gMatrixElementKernels.o build.none_d_inl0_hrd0/gBridgeKernels.o build.none_d_inl0_hrd0/gCrossSectionKernels.o build.none_d_inl0_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl0_hrd0/gcheck.exe build.none_d_inl0_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl0_hrd0'  -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_gg_ttxg_cuda build.none_d_inl0_hrd0/gRandomNumberKernels.o build.none_d_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl0_hrd0/fgcheck.exe build.none_d_inl0_hrd0/fcheck_sa.o build.none_d_inl0_hrd0/fsampler_cu.o -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl0_hrd0'  -lgfortran -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_gg_ttxg_cuda build.none_d_inl0_hrd0/gRandomNumberKernels.o build.none_d_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl0_hrd0/runTest.exe build.none_d_inl0_hrd0/CPPProcess.o build.none_d_inl0_hrd0/MatrixElementKernels.o build.none_d_inl0_hrd0/BridgeKernels.o build.none_d_inl0_hrd0/CrossSectionKernels.o build.none_d_inl0_hrd0/RandomNumberKernels.o build.none_d_inl0_hrd0/RamboSamplingKernels.o build.none_d_inl0_hrd0/testxxx.o  build.none_d_inl0_hrd0/testmisc.o  build.none_d_inl0_hrd0/runTest.o build.none_d_inl0_hrd0/gCPPProcess.o build.none_d_inl0_hrd0/gMatrixElementKernels.o build.none_d_inl0_hrd0/gBridgeKernels.o build.none_d_inl0_hrd0/gCrossSectionKernels.o build.none_d_inl0_hrd0/gRandomNumberKernels.o build.none_d_inl0_hrd0/gRamboSamplingKernels.o build.none_d_inl0_hrd0/testxxx_cu.o  build.none_d_inl0_hrd0/testmisc_cu.o  build.none_d_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl0_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
 touch build.none_d_inl0_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_d_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.none_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.none_d_inl0_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_d_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.none_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.none_d_inl0_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.none_d_inl0_hrd0/libmg5amc_gg_ttxg_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_d_inl0_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.none_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.none_d_inl0_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
 CUDACPP_BUILDDIR='build.512y_d_inl0_hrd0'
 make -f cudacpp.mk
@@ -4278,22 +4319,18 @@ HELINL=0
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.512y_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.512y_d_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gcheck_sa.cu -o build.512y_d_inl0_hrd0/gcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gCPPProcess.cu -o build.512y_d_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gcheck_sa.cu -o build.512y_d_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gCPPProcess.cu -o build.512y_d_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512y_d_inl0_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512y_d_inl0_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512y_d_inl0_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512y_d_inl0_hrd0/fbridge_cu.o
 AVX=512y
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512y_d_inl0_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512y_d_inl0_hrd0/gBridgeKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -c read_slha.cc -o build.512y_d_inl0_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512y_d_inl0_hrd0/gCrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -c Parameters_sm.cc -o build.512y_d_inl0_hrd0/Parameters_sm.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512y_d_inl0_hrd0/fbridge_cu.o
-mkdir -p ../lib/build.512y_d_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512y_d_inl0_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512y_d_inl0_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512y_d_inl0_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512y_d_inl0_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.512y_d_inl0_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.512y_d_inl0_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.512y_d_inl0_hrd0/MatrixElementKernels.o
@@ -4303,57 +4340,62 @@ ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.512y_d_inl0_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.512y_d_inl0_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.512y_d_inl0_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512y_d_inl0_hrd0/testxxx_cu.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512y_d_inl0_hrd0/testxxx_cu.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -c Parameters_sm.cc -o build.512y_d_inl0_hrd0/Parameters_sm.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -c read_slha.cc -o build.512y_d_inl0_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.512y_d_inl0_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512y_d_inl0_hrd0/testmisc_cu.o
+mkdir -p ../lib/build.512y_d_inl0_hrd0
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512y_d_inl0_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.512y_d_inl0_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu runTest.cc -o build.512y_d_inl0_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu runTest.cc -o build.512y_d_inl0_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.512y_d_inl0_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512y_d_inl0_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512y_d_inl0_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.512y_d_inl0_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.512y_d_inl0_hrd0/libmg5amc_common.so build.512y_d_inl0_hrd0/Parameters_sm.o build.512y_d_inl0_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512y_d_inl0_hrd0/libmg5amc_gg_ttxg_cuda.so build.512y_d_inl0_hrd0/gCPPProcess.o build.512y_d_inl0_hrd0/gMatrixElementKernels.o build.512y_d_inl0_hrd0/gBridgeKernels.o build.512y_d_inl0_hrd0/gCrossSectionKernels.o build.512y_d_inl0_hrd0/fbridge_cu.o -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512y_d_inl0_hrd0/libmg5amc_gg_ttxg_cpp.so build.512y_d_inl0_hrd0/CPPProcess.o build.512y_d_inl0_hrd0/MatrixElementKernels.o build.512y_d_inl0_hrd0/BridgeKernels.o build.512y_d_inl0_hrd0/CrossSectionKernels.o build.512y_d_inl0_hrd0/fbridge.o -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl0_hrd0/runTest.exe build.512y_d_inl0_hrd0/CPPProcess.o build.512y_d_inl0_hrd0/MatrixElementKernels.o build.512y_d_inl0_hrd0/BridgeKernels.o build.512y_d_inl0_hrd0/CrossSectionKernels.o build.512y_d_inl0_hrd0/RandomNumberKernels.o build.512y_d_inl0_hrd0/RamboSamplingKernels.o build.512y_d_inl0_hrd0/testxxx.o  build.512y_d_inl0_hrd0/testmisc.o  build.512y_d_inl0_hrd0/runTest.o build.512y_d_inl0_hrd0/gCPPProcess.o build.512y_d_inl0_hrd0/gMatrixElementKernels.o build.512y_d_inl0_hrd0/gBridgeKernels.o build.512y_d_inl0_hrd0/gCrossSectionKernels.o build.512y_d_inl0_hrd0/gRandomNumberKernels.o build.512y_d_inl0_hrd0/gRamboSamplingKernels.o build.512y_d_inl0_hrd0/testxxx_cu.o  build.512y_d_inl0_hrd0/testmisc_cu.o  build.512y_d_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_d_inl0_hrd0/check.exe build.512y_d_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_gg_ttxg_cpp build.512y_d_inl0_hrd0/RandomNumberKernels.o build.512y_d_inl0_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_d_inl0_hrd0/fcheck.exe build.512y_d_inl0_hrd0/fcheck_sa.o build.512y_d_inl0_hrd0/fsampler.o -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_gg_ttxg_cpp build.512y_d_inl0_hrd0/RandomNumberKernels.o build.512y_d_inl0_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl0_hrd0/gcheck.exe build.512y_d_inl0_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_gg_ttxg_cuda build.512y_d_inl0_hrd0/gRandomNumberKernels.o build.512y_d_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl0_hrd0/fgcheck.exe build.512y_d_inl0_hrd0/fcheck_sa.o build.512y_d_inl0_hrd0/fsampler_cu.o -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_gg_ttxg_cuda build.512y_d_inl0_hrd0/gRandomNumberKernels.o build.512y_d_inl0_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512y_d_inl0_hrd0/libmg5amc_gg_ttxg_cuda.so build.512y_d_inl0_hrd0/gCPPProcess.o build.512y_d_inl0_hrd0/gMatrixElementKernels.o build.512y_d_inl0_hrd0/gBridgeKernels.o build.512y_d_inl0_hrd0/gCrossSectionKernels.o build.512y_d_inl0_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512y_d_inl0_hrd0/libmg5amc_gg_ttxg_cpp.so build.512y_d_inl0_hrd0/CPPProcess.o build.512y_d_inl0_hrd0/MatrixElementKernels.o build.512y_d_inl0_hrd0/BridgeKernels.o build.512y_d_inl0_hrd0/CrossSectionKernels.o build.512y_d_inl0_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_d_inl0_hrd0/fcheck.exe build.512y_d_inl0_hrd0/fcheck_sa.o build.512y_d_inl0_hrd0/fsampler.o -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_d_inl0_hrd0'  -lgfortran -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_gg_ttxg_cpp build.512y_d_inl0_hrd0/RandomNumberKernels.o build.512y_d_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl0_hrd0/gcheck.exe build.512y_d_inl0_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl0_hrd0'  -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_gg_ttxg_cuda build.512y_d_inl0_hrd0/gRandomNumberKernels.o build.512y_d_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl0_hrd0/fgcheck.exe build.512y_d_inl0_hrd0/fcheck_sa.o build.512y_d_inl0_hrd0/fsampler_cu.o -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl0_hrd0'  -lgfortran -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_gg_ttxg_cuda build.512y_d_inl0_hrd0/gRandomNumberKernels.o build.512y_d_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_d_inl0_hrd0/check.exe build.512y_d_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_d_inl0_hrd0'  -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_gg_ttxg_cpp build.512y_d_inl0_hrd0/RandomNumberKernels.o build.512y_d_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl0_hrd0/runTest.exe build.512y_d_inl0_hrd0/CPPProcess.o build.512y_d_inl0_hrd0/MatrixElementKernels.o build.512y_d_inl0_hrd0/BridgeKernels.o build.512y_d_inl0_hrd0/CrossSectionKernels.o build.512y_d_inl0_hrd0/RandomNumberKernels.o build.512y_d_inl0_hrd0/RamboSamplingKernels.o build.512y_d_inl0_hrd0/testxxx.o  build.512y_d_inl0_hrd0/testmisc.o  build.512y_d_inl0_hrd0/runTest.o build.512y_d_inl0_hrd0/gCPPProcess.o build.512y_d_inl0_hrd0/gMatrixElementKernels.o build.512y_d_inl0_hrd0/gBridgeKernels.o build.512y_d_inl0_hrd0/gCrossSectionKernels.o build.512y_d_inl0_hrd0/gRandomNumberKernels.o build.512y_d_inl0_hrd0/gRamboSamplingKernels.o build.512y_d_inl0_hrd0/testxxx_cu.o  build.512y_d_inl0_hrd0/testmisc_cu.o  build.512y_d_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl0_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
 touch build.512y_d_inl0_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_d_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.512y_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_d_inl0_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_d_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512y_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_d_inl0_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.512y_d_inl0_hrd0/libmg5amc_gg_ttxg_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_d_inl0_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512y_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_d_inl0_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:04:41
+DATE: 2022-09-25_00:01:07
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl0_hrd0/gcheck.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl0_hrd0/gcheck.exe -p 64 256 20 OMP=
 Process                     = SIGMA_SM_GG_TTXG_CUDA [nvcc 11.7.99 (gcc 11.2.0)] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
-EvtsPerSec[Rmb+ME]     (23) = ( 8.256339e+06                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 1.021874e+07                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 1.038726e+07                 )  sec^-1
-MeanMatrixElemValue         = ( 2.360828e+02 +- 1.906418e+02 )  GeV^-2
-TOTAL       :     0.517727 sec
-real	0m0.796s
-==PROF== Profiling "sigmaKin": launch__registers_per_thread 255
-==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100%
+EvtsPerSec[Rmb+ME]     (23) = ( 6.231145e+05                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 6.352549e+05                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 6.358883e+05                 )  sec^-1
+MeanMatrixElemValue         = ( 4.103783e+02 +- 2.727382e+02 )  GeV^-2
+TOTAL       :     2.975374 sec
+real	0m3.426s
+   launch__registers_per_thread N/A
+   sm__sass_average_branch_targets_threads_uniform.pct N/A
 .........................................................................
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl0_hrd0/gcheck.exe -p 2048 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl0_hrd0/gcheck.exe -p 2048 256 2 OMP=
 Process                     = SIGMA_SM_GG_TTXG_CUDA [nvcc 11.7.99 (gcc 11.2.0)] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
-EvtsPerSec[Rmb+ME]     (23) = ( 1.090234e+07                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 1.328725e+07                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 1.342965e+07                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 8.012864e+05                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 8.177720e+05                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 8.183093e+05                 )  sec^-1
 MeanMatrixElemValue         = ( 6.080992e+03 +- 5.406078e+03 )  GeV^-2
-TOTAL       :     0.723254 sec
-real	0m1.033s
+TOTAL       :     4.453117 sec
+real	0m4.926s
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl0_hrd0/gcheck.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl0_hrd0/fgcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl0_hrd0/gcheck.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl0_hrd0/fgcheck.exe 2 64 2
 Avg ME (C++/CUDA)   = 1.413122e+00
 Avg ME (F77/CUDA)   = 1.4131213684418646
 Relative difference = 4.4692399902091566e-07
@@ -4361,12 +4403,12 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:04:49 CEST 2022 Will execute './throughputX.sh -makej -ggttg -nocpp  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:01:40 CEST 2022 Will execute './throughputX.sh -makej -ggttg -nocpp  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
 CUDACPP_BUILDDIR='build.none_d_inl1_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -4376,22 +4418,18 @@ HELINL=1
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.none_d_inl1_hrd0 for tag=none_d_inl1_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.none_d_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.none_d_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.none_d_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.none_d_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.none_d_inl1_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.none_d_inl1_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.none_d_inl1_hrd0/gCrossSectionKernels.o
 AVX=none
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.none_d_inl1_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.none_d_inl1_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.none_d_inl1_hrd0/gBridgeKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.none_d_inl1_hrd0/gCrossSectionKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.none_d_inl1_hrd0/fbridge_cu.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.none_d_inl1_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.none_d_inl1_hrd0/read_slha.o
-mkdir -p ../lib/build.none_d_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.none_d_inl1_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.none_d_inl1_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.none_d_inl1_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.none_d_inl1_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.none_d_inl1_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.none_d_inl1_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.none_d_inl1_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.none_d_inl1_hrd0/MatrixElementKernels.o
@@ -4401,26 +4439,31 @@ ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.none_d_inl1_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.none_d_inl1_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.none_d_inl1_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.none_d_inl1_hrd0/testxxx_cu.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.none_d_inl1_hrd0/Parameters_sm.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.none_d_inl1_hrd0/read_slha.o
+mkdir -p ../lib/build.none_d_inl1_hrd0
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.none_d_inl1_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.none_d_inl1_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.none_d_inl1_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.none_d_inl1_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.none_d_inl1_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.none_d_inl1_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.none_d_inl1_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.none_d_inl1_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.none_d_inl1_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.none_d_inl1_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.none_d_inl1_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.none_d_inl1_hrd0/libmg5amc_common.so build.none_d_inl1_hrd0/Parameters_sm.o build.none_d_inl1_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.none_d_inl1_hrd0/libmg5amc_gg_ttxg_cpp.so build.none_d_inl1_hrd0/CPPProcess.o build.none_d_inl1_hrd0/MatrixElementKernels.o build.none_d_inl1_hrd0/BridgeKernels.o build.none_d_inl1_hrd0/CrossSectionKernels.o build.none_d_inl1_hrd0/fbridge.o -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_d_inl1_hrd0/check.exe build.none_d_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_gg_ttxg_cpp build.none_d_inl1_hrd0/RandomNumberKernels.o build.none_d_inl1_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_d_inl1_hrd0/fcheck.exe build.none_d_inl1_hrd0/fcheck_sa.o build.none_d_inl1_hrd0/fsampler.o -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_gg_ttxg_cpp build.none_d_inl1_hrd0/RandomNumberKernels.o build.none_d_inl1_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.none_d_inl1_hrd0/libmg5amc_gg_ttxg_cuda.so build.none_d_inl1_hrd0/gCPPProcess.o build.none_d_inl1_hrd0/gMatrixElementKernels.o build.none_d_inl1_hrd0/gBridgeKernels.o build.none_d_inl1_hrd0/gCrossSectionKernels.o build.none_d_inl1_hrd0/fbridge_cu.o -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl1_hrd0/fgcheck.exe build.none_d_inl1_hrd0/fcheck_sa.o build.none_d_inl1_hrd0/fsampler_cu.o -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_gg_ttxg_cuda build.none_d_inl1_hrd0/gRandomNumberKernels.o build.none_d_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl1_hrd0/gcheck.exe build.none_d_inl1_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_gg_ttxg_cuda build.none_d_inl1_hrd0/gRandomNumberKernels.o build.none_d_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl1_hrd0/runTest.exe build.none_d_inl1_hrd0/CPPProcess.o build.none_d_inl1_hrd0/MatrixElementKernels.o build.none_d_inl1_hrd0/BridgeKernels.o build.none_d_inl1_hrd0/CrossSectionKernels.o build.none_d_inl1_hrd0/RandomNumberKernels.o build.none_d_inl1_hrd0/RamboSamplingKernels.o build.none_d_inl1_hrd0/testxxx.o  build.none_d_inl1_hrd0/testmisc.o  build.none_d_inl1_hrd0/runTest.o build.none_d_inl1_hrd0/gCPPProcess.o build.none_d_inl1_hrd0/gMatrixElementKernels.o build.none_d_inl1_hrd0/gBridgeKernels.o build.none_d_inl1_hrd0/gCrossSectionKernels.o build.none_d_inl1_hrd0/gRandomNumberKernels.o build.none_d_inl1_hrd0/gRamboSamplingKernels.o build.none_d_inl1_hrd0/testxxx_cu.o  build.none_d_inl1_hrd0/testmisc_cu.o  build.none_d_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.none_d_inl1_hrd0/libmg5amc_gg_ttxg_cpp.so build.none_d_inl1_hrd0/CPPProcess.o build.none_d_inl1_hrd0/MatrixElementKernels.o build.none_d_inl1_hrd0/BridgeKernels.o build.none_d_inl1_hrd0/CrossSectionKernels.o build.none_d_inl1_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_d_inl1_hrd0/check.exe build.none_d_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_d_inl1_hrd0'  -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_gg_ttxg_cpp build.none_d_inl1_hrd0/RandomNumberKernels.o build.none_d_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_d_inl1_hrd0/fcheck.exe build.none_d_inl1_hrd0/fcheck_sa.o build.none_d_inl1_hrd0/fsampler.o -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_d_inl1_hrd0'  -lgfortran -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_gg_ttxg_cpp build.none_d_inl1_hrd0/RandomNumberKernels.o build.none_d_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.none_d_inl1_hrd0/libmg5amc_gg_ttxg_cuda.so build.none_d_inl1_hrd0/gCPPProcess.o build.none_d_inl1_hrd0/gMatrixElementKernels.o build.none_d_inl1_hrd0/gBridgeKernels.o build.none_d_inl1_hrd0/gCrossSectionKernels.o build.none_d_inl1_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl1_hrd0/runTest.exe build.none_d_inl1_hrd0/CPPProcess.o build.none_d_inl1_hrd0/MatrixElementKernels.o build.none_d_inl1_hrd0/BridgeKernels.o build.none_d_inl1_hrd0/CrossSectionKernels.o build.none_d_inl1_hrd0/RandomNumberKernels.o build.none_d_inl1_hrd0/RamboSamplingKernels.o build.none_d_inl1_hrd0/testxxx.o  build.none_d_inl1_hrd0/testmisc.o  build.none_d_inl1_hrd0/runTest.o build.none_d_inl1_hrd0/gCPPProcess.o build.none_d_inl1_hrd0/gMatrixElementKernels.o build.none_d_inl1_hrd0/gBridgeKernels.o build.none_d_inl1_hrd0/gCrossSectionKernels.o build.none_d_inl1_hrd0/gRandomNumberKernels.o build.none_d_inl1_hrd0/gRamboSamplingKernels.o build.none_d_inl1_hrd0/testxxx_cu.o  build.none_d_inl1_hrd0/testmisc_cu.o  build.none_d_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl1_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl1_hrd0/gcheck.exe build.none_d_inl1_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl1_hrd0'  -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_gg_ttxg_cuda build.none_d_inl1_hrd0/gRandomNumberKernels.o build.none_d_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl1_hrd0/fgcheck.exe build.none_d_inl1_hrd0/fcheck_sa.o build.none_d_inl1_hrd0/fsampler_cu.o -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl1_hrd0'  -lgfortran -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_gg_ttxg_cuda build.none_d_inl1_hrd0/gRandomNumberKernels.o build.none_d_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
 touch build.none_d_inl1_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_d_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.none_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.none_d_inl1_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_d_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.none_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.none_d_inl1_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.none_d_inl1_hrd0/libmg5amc_gg_ttxg_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_d_inl1_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.none_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.none_d_inl1_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
 CUDACPP_BUILDDIR='build.512y_d_inl1_hrd0'
 make -f cudacpp.mk
@@ -4431,82 +4474,83 @@ HELINL=1
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.512y_d_inl1_hrd0 for tag=512y_d_inl1_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.512y_d_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.512y_d_inl1_hrd0/gcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.512y_d_inl1_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512y_d_inl1_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.512y_d_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.512y_d_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512y_d_inl1_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512y_d_inl1_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512y_d_inl1_hrd0/gCrossSectionKernels.o
 AVX=512y
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512y_d_inl1_hrd0/gBridgeKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512y_d_inl1_hrd0/gCrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.512y_d_inl1_hrd0/Parameters_sm.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512y_d_inl1_hrd0/fbridge_cu.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.512y_d_inl1_hrd0/read_slha.o
-mkdir -p ../lib/build.512y_d_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512y_d_inl1_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512y_d_inl1_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512y_d_inl1_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512y_d_inl1_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512y_d_inl1_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.512y_d_inl1_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.512y_d_inl1_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.512y_d_inl1_hrd0/MatrixElementKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.512y_d_inl1_hrd0/Parameters_sm.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.512y_d_inl1_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.512y_d_inl1_hrd0/BridgeKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.512y_d_inl1_hrd0/CrossSectionKernels.o
+mkdir -p ../lib/build.512y_d_inl1_hrd0
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.512y_d_inl1_hrd0/fbridge.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.512y_d_inl1_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.512y_d_inl1_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.512y_d_inl1_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512y_d_inl1_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512y_d_inl1_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.512y_d_inl1_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512y_d_inl1_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512y_d_inl1_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.512y_d_inl1_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.512y_d_inl1_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.512y_d_inl1_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.512y_d_inl1_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512y_d_inl1_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512y_d_inl1_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.512y_d_inl1_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.512y_d_inl1_hrd0/libmg5amc_common.so build.512y_d_inl1_hrd0/Parameters_sm.o build.512y_d_inl1_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512y_d_inl1_hrd0/libmg5amc_gg_ttxg_cuda.so build.512y_d_inl1_hrd0/gCPPProcess.o build.512y_d_inl1_hrd0/gMatrixElementKernels.o build.512y_d_inl1_hrd0/gBridgeKernels.o build.512y_d_inl1_hrd0/gCrossSectionKernels.o build.512y_d_inl1_hrd0/fbridge_cu.o -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512y_d_inl1_hrd0/libmg5amc_gg_ttxg_cpp.so build.512y_d_inl1_hrd0/CPPProcess.o build.512y_d_inl1_hrd0/MatrixElementKernels.o build.512y_d_inl1_hrd0/BridgeKernels.o build.512y_d_inl1_hrd0/CrossSectionKernels.o build.512y_d_inl1_hrd0/fbridge.o -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl1_hrd0/runTest.exe build.512y_d_inl1_hrd0/CPPProcess.o build.512y_d_inl1_hrd0/MatrixElementKernels.o build.512y_d_inl1_hrd0/BridgeKernels.o build.512y_d_inl1_hrd0/CrossSectionKernels.o build.512y_d_inl1_hrd0/RandomNumberKernels.o build.512y_d_inl1_hrd0/RamboSamplingKernels.o build.512y_d_inl1_hrd0/testxxx.o  build.512y_d_inl1_hrd0/testmisc.o  build.512y_d_inl1_hrd0/runTest.o build.512y_d_inl1_hrd0/gCPPProcess.o build.512y_d_inl1_hrd0/gMatrixElementKernels.o build.512y_d_inl1_hrd0/gBridgeKernels.o build.512y_d_inl1_hrd0/gCrossSectionKernels.o build.512y_d_inl1_hrd0/gRandomNumberKernels.o build.512y_d_inl1_hrd0/gRamboSamplingKernels.o build.512y_d_inl1_hrd0/testxxx_cu.o  build.512y_d_inl1_hrd0/testmisc_cu.o  build.512y_d_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_d_inl1_hrd0/check.exe build.512y_d_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_gg_ttxg_cpp build.512y_d_inl1_hrd0/RandomNumberKernels.o build.512y_d_inl1_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_d_inl1_hrd0/fcheck.exe build.512y_d_inl1_hrd0/fcheck_sa.o build.512y_d_inl1_hrd0/fsampler.o -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_gg_ttxg_cpp build.512y_d_inl1_hrd0/RandomNumberKernels.o build.512y_d_inl1_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl1_hrd0/gcheck.exe build.512y_d_inl1_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_gg_ttxg_cuda build.512y_d_inl1_hrd0/gRandomNumberKernels.o build.512y_d_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl1_hrd0/fgcheck.exe build.512y_d_inl1_hrd0/fcheck_sa.o build.512y_d_inl1_hrd0/fsampler_cu.o -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_gg_ttxg_cuda build.512y_d_inl1_hrd0/gRandomNumberKernels.o build.512y_d_inl1_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512y_d_inl1_hrd0/libmg5amc_gg_ttxg_cuda.so build.512y_d_inl1_hrd0/gCPPProcess.o build.512y_d_inl1_hrd0/gMatrixElementKernels.o build.512y_d_inl1_hrd0/gBridgeKernels.o build.512y_d_inl1_hrd0/gCrossSectionKernels.o build.512y_d_inl1_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl1_hrd0/gcheck.exe build.512y_d_inl1_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl1_hrd0'  -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_gg_ttxg_cuda build.512y_d_inl1_hrd0/gRandomNumberKernels.o build.512y_d_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl1_hrd0/fgcheck.exe build.512y_d_inl1_hrd0/fcheck_sa.o build.512y_d_inl1_hrd0/fsampler_cu.o -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl1_hrd0'  -lgfortran -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_gg_ttxg_cuda build.512y_d_inl1_hrd0/gRandomNumberKernels.o build.512y_d_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512y_d_inl1_hrd0/libmg5amc_gg_ttxg_cpp.so build.512y_d_inl1_hrd0/CPPProcess.o build.512y_d_inl1_hrd0/MatrixElementKernels.o build.512y_d_inl1_hrd0/BridgeKernels.o build.512y_d_inl1_hrd0/CrossSectionKernels.o build.512y_d_inl1_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_d_inl1_hrd0/check.exe build.512y_d_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_d_inl1_hrd0'  -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_gg_ttxg_cpp build.512y_d_inl1_hrd0/RandomNumberKernels.o build.512y_d_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_d_inl1_hrd0/fcheck.exe build.512y_d_inl1_hrd0/fcheck_sa.o build.512y_d_inl1_hrd0/fsampler.o -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_d_inl1_hrd0'  -lgfortran -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_gg_ttxg_cpp build.512y_d_inl1_hrd0/RandomNumberKernels.o build.512y_d_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl1_hrd0/runTest.exe build.512y_d_inl1_hrd0/CPPProcess.o build.512y_d_inl1_hrd0/MatrixElementKernels.o build.512y_d_inl1_hrd0/BridgeKernels.o build.512y_d_inl1_hrd0/CrossSectionKernels.o build.512y_d_inl1_hrd0/RandomNumberKernels.o build.512y_d_inl1_hrd0/RamboSamplingKernels.o build.512y_d_inl1_hrd0/testxxx.o  build.512y_d_inl1_hrd0/testmisc.o  build.512y_d_inl1_hrd0/runTest.o build.512y_d_inl1_hrd0/gCPPProcess.o build.512y_d_inl1_hrd0/gMatrixElementKernels.o build.512y_d_inl1_hrd0/gBridgeKernels.o build.512y_d_inl1_hrd0/gCrossSectionKernels.o build.512y_d_inl1_hrd0/gRandomNumberKernels.o build.512y_d_inl1_hrd0/gRamboSamplingKernels.o build.512y_d_inl1_hrd0/testxxx_cu.o  build.512y_d_inl1_hrd0/testmisc_cu.o  build.512y_d_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl1_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
 touch build.512y_d_inl1_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_d_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.512y_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_d_inl1_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_d_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512y_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_d_inl1_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.512y_d_inl1_hrd0/libmg5amc_gg_ttxg_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_d_inl1_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512y_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_d_inl1_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:05:01
+DATE: 2022-09-25_00:02:05
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl1_hrd0/gcheck.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl1_hrd0/gcheck.exe -p 64 256 20 OMP=
 Process                     = SIGMA_SM_GG_TTXG_CUDA [nvcc 11.7.99 (gcc 11.2.0)] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
-EvtsPerSec[Rmb+ME]     (23) = ( 8.386714e+06                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 1.005902e+07                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 1.020741e+07                 )  sec^-1
-MeanMatrixElemValue         = ( 2.360828e+02 +- 1.906418e+02 )  GeV^-2
-TOTAL       :     0.504212 sec
-real	0m0.784s
-==PROF== Profiling "sigmaKin": launch__registers_per_thread 255
-==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100%
+EvtsPerSec[Rmb+ME]     (23) = ( 6.086875e+05                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 6.190766e+05                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 6.195779e+05                 )  sec^-1
+MeanMatrixElemValue         = ( 4.103783e+02 +- 2.727382e+02 )  GeV^-2
+TOTAL       :     2.960896 sec
+real	0m3.392s
+   launch__registers_per_thread N/A
+   sm__sass_average_branch_targets_threads_uniform.pct N/A
 .........................................................................
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl1_hrd0/gcheck.exe -p 2048 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl1_hrd0/gcheck.exe -p 2048 256 2 OMP=
 Process                     = SIGMA_SM_GG_TTXG_CUDA [nvcc 11.7.99 (gcc 11.2.0)] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
-EvtsPerSec[Rmb+ME]     (23) = ( 1.089950e+07                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 1.327718e+07                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 1.342074e+07                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 8.013845e+05                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 8.177757e+05                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 8.183168e+05                 )  sec^-1
 MeanMatrixElemValue         = ( 6.080992e+03 +- 5.406078e+03 )  GeV^-2
-TOTAL       :     0.723589 sec
-real	0m1.033s
+TOTAL       :     4.436200 sec
+real	0m4.911s
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl1_hrd0/gcheck.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl1_hrd0/fgcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl1_hrd0/gcheck.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl1_hrd0/fgcheck.exe 2 64 2
 Avg ME (C++/CUDA)   = 1.413122e+00
 Avg ME (F77/CUDA)   = 1.4131213684418646
 Relative difference = 4.4692399902091566e-07
@@ -4514,12 +4558,12 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:05:08 CEST 2022 Will execute './throughputX.sh -makej -ggttg -nocpp -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:02:38 CEST 2022 Will execute './throughputX.sh -makej -ggttg -nocpp -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
 CUDACPP_BUILDDIR='build.none_f_inl0_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -4529,51 +4573,52 @@ HELINL=0
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.none_f_inl0_hrd0 for tag=none_f_inl0_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.none_f_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gcheck_sa.cu -o build.none_f_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gcheck_sa.cu -o build.none_f_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gCPPProcess.cu -o build.none_f_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.none_f_inl0_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gBridgeKernels.cu -o build.none_f_inl0_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.none_f_inl0_hrd0/gCrossSectionKernels.o
 AVX=none
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gCPPProcess.cu -o build.none_f_inl0_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.none_f_inl0_hrd0/gMatrixElementKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gBridgeKernels.cu -o build.none_f_inl0_hrd0/gBridgeKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -c Parameters_sm.cc -o build.none_f_inl0_hrd0/Parameters_sm.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.none_f_inl0_hrd0/gCrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -c read_slha.cc -o build.none_f_inl0_hrd0/read_slha.o
-mkdir -p ../lib/build.none_f_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fbridge.cc -o build.none_f_inl0_hrd0/fbridge_cu.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.none_f_inl0_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.none_f_inl0_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fbridge.cc -o build.none_f_inl0_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.none_f_inl0_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.none_f_inl0_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.none_f_inl0_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.none_f_inl0_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.none_f_inl0_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.none_f_inl0_hrd0/BridgeKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.none_f_inl0_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.none_f_inl0_hrd0/fbridge.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -c Parameters_sm.cc -o build.none_f_inl0_hrd0/Parameters_sm.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.none_f_inl0_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.none_f_inl0_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.none_f_inl0_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testxxx.cc -o build.none_f_inl0_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testxxx.cc -o build.none_f_inl0_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.none_f_inl0_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testmisc.cc -o build.none_f_inl0_hrd0/testmisc_cu.o
+mkdir -p ../lib/build.none_f_inl0_hrd0
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -c read_slha.cc -o build.none_f_inl0_hrd0/read_slha.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testmisc.cc -o build.none_f_inl0_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.none_f_inl0_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu runTest.cc -o build.none_f_inl0_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu runTest.cc -o build.none_f_inl0_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.none_f_inl0_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fsampler.cc -o build.none_f_inl0_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fsampler.cc -o build.none_f_inl0_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.none_f_inl0_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.none_f_inl0_hrd0/libmg5amc_common.so build.none_f_inl0_hrd0/Parameters_sm.o build.none_f_inl0_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.none_f_inl0_hrd0/libmg5amc_gg_ttxg_cpp.so build.none_f_inl0_hrd0/CPPProcess.o build.none_f_inl0_hrd0/MatrixElementKernels.o build.none_f_inl0_hrd0/BridgeKernels.o build.none_f_inl0_hrd0/CrossSectionKernels.o build.none_f_inl0_hrd0/fbridge.o -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_f_inl0_hrd0/check.exe build.none_f_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_gg_ttxg_cpp build.none_f_inl0_hrd0/RandomNumberKernels.o build.none_f_inl0_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_f_inl0_hrd0/fcheck.exe build.none_f_inl0_hrd0/fcheck_sa.o build.none_f_inl0_hrd0/fsampler.o -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_gg_ttxg_cpp build.none_f_inl0_hrd0/RandomNumberKernels.o build.none_f_inl0_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.none_f_inl0_hrd0/libmg5amc_gg_ttxg_cuda.so build.none_f_inl0_hrd0/gCPPProcess.o build.none_f_inl0_hrd0/gMatrixElementKernels.o build.none_f_inl0_hrd0/gBridgeKernels.o build.none_f_inl0_hrd0/gCrossSectionKernels.o build.none_f_inl0_hrd0/fbridge_cu.o -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl0_hrd0/fgcheck.exe build.none_f_inl0_hrd0/fcheck_sa.o build.none_f_inl0_hrd0/fsampler_cu.o -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_gg_ttxg_cuda build.none_f_inl0_hrd0/gRandomNumberKernels.o build.none_f_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl0_hrd0/gcheck.exe build.none_f_inl0_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_gg_ttxg_cuda build.none_f_inl0_hrd0/gRandomNumberKernels.o build.none_f_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl0_hrd0/runTest.exe build.none_f_inl0_hrd0/CPPProcess.o build.none_f_inl0_hrd0/MatrixElementKernels.o build.none_f_inl0_hrd0/BridgeKernels.o build.none_f_inl0_hrd0/CrossSectionKernels.o build.none_f_inl0_hrd0/RandomNumberKernels.o build.none_f_inl0_hrd0/RamboSamplingKernels.o build.none_f_inl0_hrd0/testxxx.o  build.none_f_inl0_hrd0/testmisc.o  build.none_f_inl0_hrd0/runTest.o build.none_f_inl0_hrd0/gCPPProcess.o build.none_f_inl0_hrd0/gMatrixElementKernels.o build.none_f_inl0_hrd0/gBridgeKernels.o build.none_f_inl0_hrd0/gCrossSectionKernels.o build.none_f_inl0_hrd0/gRandomNumberKernels.o build.none_f_inl0_hrd0/gRamboSamplingKernels.o build.none_f_inl0_hrd0/testxxx_cu.o  build.none_f_inl0_hrd0/testmisc_cu.o  build.none_f_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.none_f_inl0_hrd0/libmg5amc_gg_ttxg_cpp.so build.none_f_inl0_hrd0/CPPProcess.o build.none_f_inl0_hrd0/MatrixElementKernels.o build.none_f_inl0_hrd0/BridgeKernels.o build.none_f_inl0_hrd0/CrossSectionKernels.o build.none_f_inl0_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_f_inl0_hrd0/check.exe build.none_f_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_f_inl0_hrd0'  -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_gg_ttxg_cpp build.none_f_inl0_hrd0/RandomNumberKernels.o build.none_f_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_f_inl0_hrd0/fcheck.exe build.none_f_inl0_hrd0/fcheck_sa.o build.none_f_inl0_hrd0/fsampler.o -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_f_inl0_hrd0'  -lgfortran -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_gg_ttxg_cpp build.none_f_inl0_hrd0/RandomNumberKernels.o build.none_f_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.none_f_inl0_hrd0/libmg5amc_gg_ttxg_cuda.so build.none_f_inl0_hrd0/gCPPProcess.o build.none_f_inl0_hrd0/gMatrixElementKernels.o build.none_f_inl0_hrd0/gBridgeKernels.o build.none_f_inl0_hrd0/gCrossSectionKernels.o build.none_f_inl0_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl0_hrd0/fgcheck.exe build.none_f_inl0_hrd0/fcheck_sa.o build.none_f_inl0_hrd0/fsampler_cu.o -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl0_hrd0'  -lgfortran -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_gg_ttxg_cuda build.none_f_inl0_hrd0/gRandomNumberKernels.o build.none_f_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl0_hrd0/gcheck.exe build.none_f_inl0_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl0_hrd0'  -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_gg_ttxg_cuda build.none_f_inl0_hrd0/gRandomNumberKernels.o build.none_f_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl0_hrd0/runTest.exe build.none_f_inl0_hrd0/CPPProcess.o build.none_f_inl0_hrd0/MatrixElementKernels.o build.none_f_inl0_hrd0/BridgeKernels.o build.none_f_inl0_hrd0/CrossSectionKernels.o build.none_f_inl0_hrd0/RandomNumberKernels.o build.none_f_inl0_hrd0/RamboSamplingKernels.o build.none_f_inl0_hrd0/testxxx.o  build.none_f_inl0_hrd0/testmisc.o  build.none_f_inl0_hrd0/runTest.o build.none_f_inl0_hrd0/gCPPProcess.o build.none_f_inl0_hrd0/gMatrixElementKernels.o build.none_f_inl0_hrd0/gBridgeKernels.o build.none_f_inl0_hrd0/gCrossSectionKernels.o build.none_f_inl0_hrd0/gRandomNumberKernels.o build.none_f_inl0_hrd0/gRamboSamplingKernels.o build.none_f_inl0_hrd0/testxxx_cu.o  build.none_f_inl0_hrd0/testmisc_cu.o  build.none_f_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl0_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
 touch build.none_f_inl0_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_f_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.none_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.none_f_inl0_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_f_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.none_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.none_f_inl0_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.none_f_inl0_hrd0/libmg5amc_gg_ttxg_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_f_inl0_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.none_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.none_f_inl0_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
 CUDACPP_BUILDDIR='build.512y_f_inl0_hrd0'
 make -f cudacpp.mk
@@ -4584,82 +4629,83 @@ HELINL=0
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.512y_f_inl0_hrd0 for tag=512y_f_inl0_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.512y_f_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gcheck_sa.cu -o build.512y_f_inl0_hrd0/gcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gCPPProcess.cu -o build.512y_f_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gcheck_sa.cu -o build.512y_f_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gCPPProcess.cu -o build.512y_f_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512y_f_inl0_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512y_f_inl0_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512y_f_inl0_hrd0/gCrossSectionKernels.o
 AVX=512y
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512y_f_inl0_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512y_f_inl0_hrd0/gBridgeKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512y_f_inl0_hrd0/gCrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -c Parameters_sm.cc -o build.512y_f_inl0_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -c read_slha.cc -o build.512y_f_inl0_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512y_f_inl0_hrd0/fbridge_cu.o
-mkdir -p ../lib/build.512y_f_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512y_f_inl0_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512y_f_inl0_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512y_f_inl0_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512y_f_inl0_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512y_f_inl0_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.512y_f_inl0_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.512y_f_inl0_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.512y_f_inl0_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.512y_f_inl0_hrd0/BridgeKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.512y_f_inl0_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.512y_f_inl0_hrd0/fbridge.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.512y_f_inl0_hrd0/RandomNumberKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -c Parameters_sm.cc -o build.512y_f_inl0_hrd0/Parameters_sm.o
+mkdir -p ../lib/build.512y_f_inl0_hrd0
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -c read_slha.cc -o build.512y_f_inl0_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.512y_f_inl0_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.512y_f_inl0_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512y_f_inl0_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512y_f_inl0_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.512y_f_inl0_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512y_f_inl0_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512y_f_inl0_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.512y_f_inl0_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu runTest.cc -o build.512y_f_inl0_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu runTest.cc -o build.512y_f_inl0_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.512y_f_inl0_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512y_f_inl0_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512y_f_inl0_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.512y_f_inl0_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.512y_f_inl0_hrd0/libmg5amc_common.so build.512y_f_inl0_hrd0/Parameters_sm.o build.512y_f_inl0_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512y_f_inl0_hrd0/libmg5amc_gg_ttxg_cuda.so build.512y_f_inl0_hrd0/gCPPProcess.o build.512y_f_inl0_hrd0/gMatrixElementKernels.o build.512y_f_inl0_hrd0/gBridgeKernels.o build.512y_f_inl0_hrd0/gCrossSectionKernels.o build.512y_f_inl0_hrd0/fbridge_cu.o -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512y_f_inl0_hrd0/libmg5amc_gg_ttxg_cpp.so build.512y_f_inl0_hrd0/CPPProcess.o build.512y_f_inl0_hrd0/MatrixElementKernels.o build.512y_f_inl0_hrd0/BridgeKernels.o build.512y_f_inl0_hrd0/CrossSectionKernels.o build.512y_f_inl0_hrd0/fbridge.o -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl0_hrd0/runTest.exe build.512y_f_inl0_hrd0/CPPProcess.o build.512y_f_inl0_hrd0/MatrixElementKernels.o build.512y_f_inl0_hrd0/BridgeKernels.o build.512y_f_inl0_hrd0/CrossSectionKernels.o build.512y_f_inl0_hrd0/RandomNumberKernels.o build.512y_f_inl0_hrd0/RamboSamplingKernels.o build.512y_f_inl0_hrd0/testxxx.o  build.512y_f_inl0_hrd0/testmisc.o  build.512y_f_inl0_hrd0/runTest.o build.512y_f_inl0_hrd0/gCPPProcess.o build.512y_f_inl0_hrd0/gMatrixElementKernels.o build.512y_f_inl0_hrd0/gBridgeKernels.o build.512y_f_inl0_hrd0/gCrossSectionKernels.o build.512y_f_inl0_hrd0/gRandomNumberKernels.o build.512y_f_inl0_hrd0/gRamboSamplingKernels.o build.512y_f_inl0_hrd0/testxxx_cu.o  build.512y_f_inl0_hrd0/testmisc_cu.o  build.512y_f_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_f_inl0_hrd0/check.exe build.512y_f_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_gg_ttxg_cpp build.512y_f_inl0_hrd0/RandomNumberKernels.o build.512y_f_inl0_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_f_inl0_hrd0/fcheck.exe build.512y_f_inl0_hrd0/fcheck_sa.o build.512y_f_inl0_hrd0/fsampler.o -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_gg_ttxg_cpp build.512y_f_inl0_hrd0/RandomNumberKernels.o build.512y_f_inl0_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl0_hrd0/gcheck.exe build.512y_f_inl0_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_gg_ttxg_cuda build.512y_f_inl0_hrd0/gRandomNumberKernels.o build.512y_f_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl0_hrd0/fgcheck.exe build.512y_f_inl0_hrd0/fcheck_sa.o build.512y_f_inl0_hrd0/fsampler_cu.o -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_gg_ttxg_cuda build.512y_f_inl0_hrd0/gRandomNumberKernels.o build.512y_f_inl0_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512y_f_inl0_hrd0/libmg5amc_gg_ttxg_cuda.so build.512y_f_inl0_hrd0/gCPPProcess.o build.512y_f_inl0_hrd0/gMatrixElementKernels.o build.512y_f_inl0_hrd0/gBridgeKernels.o build.512y_f_inl0_hrd0/gCrossSectionKernels.o build.512y_f_inl0_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512y_f_inl0_hrd0/libmg5amc_gg_ttxg_cpp.so build.512y_f_inl0_hrd0/CPPProcess.o build.512y_f_inl0_hrd0/MatrixElementKernels.o build.512y_f_inl0_hrd0/BridgeKernels.o build.512y_f_inl0_hrd0/CrossSectionKernels.o build.512y_f_inl0_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_f_inl0_hrd0/fcheck.exe build.512y_f_inl0_hrd0/fcheck_sa.o build.512y_f_inl0_hrd0/fsampler.o -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_f_inl0_hrd0'  -lgfortran -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_gg_ttxg_cpp build.512y_f_inl0_hrd0/RandomNumberKernels.o build.512y_f_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl0_hrd0/gcheck.exe build.512y_f_inl0_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl0_hrd0'  -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_gg_ttxg_cuda build.512y_f_inl0_hrd0/gRandomNumberKernels.o build.512y_f_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl0_hrd0/fgcheck.exe build.512y_f_inl0_hrd0/fcheck_sa.o build.512y_f_inl0_hrd0/fsampler_cu.o -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl0_hrd0'  -lgfortran -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_gg_ttxg_cuda build.512y_f_inl0_hrd0/gRandomNumberKernels.o build.512y_f_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_f_inl0_hrd0/check.exe build.512y_f_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_f_inl0_hrd0'  -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_gg_ttxg_cpp build.512y_f_inl0_hrd0/RandomNumberKernels.o build.512y_f_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl0_hrd0/runTest.exe build.512y_f_inl0_hrd0/CPPProcess.o build.512y_f_inl0_hrd0/MatrixElementKernels.o build.512y_f_inl0_hrd0/BridgeKernels.o build.512y_f_inl0_hrd0/CrossSectionKernels.o build.512y_f_inl0_hrd0/RandomNumberKernels.o build.512y_f_inl0_hrd0/RamboSamplingKernels.o build.512y_f_inl0_hrd0/testxxx.o  build.512y_f_inl0_hrd0/testmisc.o  build.512y_f_inl0_hrd0/runTest.o build.512y_f_inl0_hrd0/gCPPProcess.o build.512y_f_inl0_hrd0/gMatrixElementKernels.o build.512y_f_inl0_hrd0/gBridgeKernels.o build.512y_f_inl0_hrd0/gCrossSectionKernels.o build.512y_f_inl0_hrd0/gRandomNumberKernels.o build.512y_f_inl0_hrd0/gRamboSamplingKernels.o build.512y_f_inl0_hrd0/testxxx_cu.o  build.512y_f_inl0_hrd0/testmisc_cu.o  build.512y_f_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl0_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
 touch build.512y_f_inl0_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_f_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.512y_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_f_inl0_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_f_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512y_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_f_inl0_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.512y_f_inl0_hrd0/libmg5amc_gg_ttxg_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_f_inl0_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512y_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_f_inl0_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:05:30
+DATE: 2022-09-25_00:03:19
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl0_hrd0/gcheck.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl0_hrd0/gcheck.exe -p 64 256 20 OMP=
 Process                     = SIGMA_SM_GG_TTXG_CUDA [nvcc 11.7.99 (gcc 11.2.0)] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK
 FP precision                = FLOAT (NaN/abnormal=0, zero=0)
-EvtsPerSec[Rmb+ME]     (23) = ( 2.491551e+07                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 3.436505e+07                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 3.557984e+07                 )  sec^-1
-MeanMatrixElemValue         = ( 2.361364e+02 +- 1.906865e+02 )  GeV^-2
-TOTAL       :     0.703518 sec
-real	0m0.980s
-==PROF== Profiling "sigmaKin": launch__registers_per_thread 242
-==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100%
+EvtsPerSec[Rmb+ME]     (23) = ( 1.175818e+07                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 1.480793e+07                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 1.500698e+07                 )  sec^-1
+MeanMatrixElemValue         = ( 4.102969e+02 +- 2.728659e+02 )  GeV^-2
+TOTAL       :     2.454550 sec
+real	0m2.945s
+   launch__registers_per_thread N/A
+   sm__sass_average_branch_targets_threads_uniform.pct N/A
 .........................................................................
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl0_hrd0/gcheck.exe -p 2048 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl0_hrd0/gcheck.exe -p 2048 256 2 OMP=
 Process                     = SIGMA_SM_GG_TTXG_CUDA [nvcc 11.7.99 (gcc 11.2.0)] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK
 FP precision                = FLOAT (NaN/abnormal=0, zero=0)
-EvtsPerSec[Rmb+ME]     (23) = ( 3.257654e+07                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 4.502847e+07                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 4.587926e+07                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 1.457029e+07                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 1.828731e+07                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 1.842414e+07                 )  sec^-1
 MeanMatrixElemValue         = ( 2.814041e+03 +- 2.181057e+03 )  GeV^-2
-TOTAL       :     0.580534 sec
-real	0m0.874s
+TOTAL       :     2.504301 sec
+real	0m2.972s
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl0_hrd0/gcheck.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl0_hrd0/fgcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl0_hrd0/gcheck.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl0_hrd0/fgcheck.exe 2 64 2
 Avg ME (C++/CUDA)   = 1.412607e+00
 Avg ME (F77/CUDA)   = 1.4132214893275545
 Relative difference = 0.0004350037395783756
@@ -4667,12 +4713,12 @@ ERROR (relative difference > 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:05:36 CEST 2022 Will execute './throughputX.sh -makej -ggttg -nocpp -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:03:50 CEST 2022 Will execute './throughputX.sh -makej -ggttg -nocpp -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
 CUDACPP_BUILDDIR='build.none_f_inl1_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -4682,51 +4728,52 @@ HELINL=1
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.none_f_inl1_hrd0 for tag=none_f_inl1_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.none_f_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.none_f_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.none_f_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.none_f_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.none_f_inl1_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.none_f_inl1_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.none_f_inl1_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.none_f_inl1_hrd0/fbridge_cu.o
 AVX=none
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.none_f_inl1_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.none_f_inl1_hrd0/gMatrixElementKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.none_f_inl1_hrd0/gBridgeKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.none_f_inl1_hrd0/Parameters_sm.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.none_f_inl1_hrd0/gCrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.none_f_inl1_hrd0/read_slha.o
-mkdir -p ../lib/build.none_f_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.none_f_inl1_hrd0/fbridge_cu.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.none_f_inl1_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.none_f_inl1_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.none_f_inl1_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.none_f_inl1_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.none_f_inl1_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.none_f_inl1_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.none_f_inl1_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.none_f_inl1_hrd0/BridgeKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.none_f_inl1_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.none_f_inl1_hrd0/fbridge.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.none_f_inl1_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.none_f_inl1_hrd0/RamboSamplingKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.none_f_inl1_hrd0/Parameters_sm.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.none_f_inl1_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.none_f_inl1_hrd0/testxxx_cu.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.none_f_inl1_hrd0/read_slha.o
+mkdir -p ../lib/build.none_f_inl1_hrd0
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.none_f_inl1_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.none_f_inl1_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.none_f_inl1_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.none_f_inl1_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.none_f_inl1_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.none_f_inl1_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.none_f_inl1_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.none_f_inl1_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.none_f_inl1_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.none_f_inl1_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.none_f_inl1_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.none_f_inl1_hrd0/libmg5amc_common.so build.none_f_inl1_hrd0/Parameters_sm.o build.none_f_inl1_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.none_f_inl1_hrd0/libmg5amc_gg_ttxg_cpp.so build.none_f_inl1_hrd0/CPPProcess.o build.none_f_inl1_hrd0/MatrixElementKernels.o build.none_f_inl1_hrd0/BridgeKernels.o build.none_f_inl1_hrd0/CrossSectionKernels.o build.none_f_inl1_hrd0/fbridge.o -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_f_inl1_hrd0/check.exe build.none_f_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_gg_ttxg_cpp build.none_f_inl1_hrd0/RandomNumberKernels.o build.none_f_inl1_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_f_inl1_hrd0/fcheck.exe build.none_f_inl1_hrd0/fcheck_sa.o build.none_f_inl1_hrd0/fsampler.o -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_gg_ttxg_cpp build.none_f_inl1_hrd0/RandomNumberKernels.o build.none_f_inl1_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.none_f_inl1_hrd0/libmg5amc_gg_ttxg_cuda.so build.none_f_inl1_hrd0/gCPPProcess.o build.none_f_inl1_hrd0/gMatrixElementKernels.o build.none_f_inl1_hrd0/gBridgeKernels.o build.none_f_inl1_hrd0/gCrossSectionKernels.o build.none_f_inl1_hrd0/fbridge_cu.o -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl1_hrd0/fgcheck.exe build.none_f_inl1_hrd0/fcheck_sa.o build.none_f_inl1_hrd0/fsampler_cu.o -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_gg_ttxg_cuda build.none_f_inl1_hrd0/gRandomNumberKernels.o build.none_f_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl1_hrd0/gcheck.exe build.none_f_inl1_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_gg_ttxg_cuda build.none_f_inl1_hrd0/gRandomNumberKernels.o build.none_f_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl1_hrd0/runTest.exe build.none_f_inl1_hrd0/CPPProcess.o build.none_f_inl1_hrd0/MatrixElementKernels.o build.none_f_inl1_hrd0/BridgeKernels.o build.none_f_inl1_hrd0/CrossSectionKernels.o build.none_f_inl1_hrd0/RandomNumberKernels.o build.none_f_inl1_hrd0/RamboSamplingKernels.o build.none_f_inl1_hrd0/testxxx.o  build.none_f_inl1_hrd0/testmisc.o  build.none_f_inl1_hrd0/runTest.o build.none_f_inl1_hrd0/gCPPProcess.o build.none_f_inl1_hrd0/gMatrixElementKernels.o build.none_f_inl1_hrd0/gBridgeKernels.o build.none_f_inl1_hrd0/gCrossSectionKernels.o build.none_f_inl1_hrd0/gRandomNumberKernels.o build.none_f_inl1_hrd0/gRamboSamplingKernels.o build.none_f_inl1_hrd0/testxxx_cu.o  build.none_f_inl1_hrd0/testmisc_cu.o  build.none_f_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.none_f_inl1_hrd0/libmg5amc_gg_ttxg_cpp.so build.none_f_inl1_hrd0/CPPProcess.o build.none_f_inl1_hrd0/MatrixElementKernels.o build.none_f_inl1_hrd0/BridgeKernels.o build.none_f_inl1_hrd0/CrossSectionKernels.o build.none_f_inl1_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_f_inl1_hrd0/check.exe build.none_f_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_f_inl1_hrd0'  -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_gg_ttxg_cpp build.none_f_inl1_hrd0/RandomNumberKernels.o build.none_f_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_f_inl1_hrd0/fcheck.exe build.none_f_inl1_hrd0/fcheck_sa.o build.none_f_inl1_hrd0/fsampler.o -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_f_inl1_hrd0'  -lgfortran -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_gg_ttxg_cpp build.none_f_inl1_hrd0/RandomNumberKernels.o build.none_f_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.none_f_inl1_hrd0/libmg5amc_gg_ttxg_cuda.so build.none_f_inl1_hrd0/gCPPProcess.o build.none_f_inl1_hrd0/gMatrixElementKernels.o build.none_f_inl1_hrd0/gBridgeKernels.o build.none_f_inl1_hrd0/gCrossSectionKernels.o build.none_f_inl1_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl1_hrd0/runTest.exe build.none_f_inl1_hrd0/CPPProcess.o build.none_f_inl1_hrd0/MatrixElementKernels.o build.none_f_inl1_hrd0/BridgeKernels.o build.none_f_inl1_hrd0/CrossSectionKernels.o build.none_f_inl1_hrd0/RandomNumberKernels.o build.none_f_inl1_hrd0/RamboSamplingKernels.o build.none_f_inl1_hrd0/testxxx.o  build.none_f_inl1_hrd0/testmisc.o  build.none_f_inl1_hrd0/runTest.o build.none_f_inl1_hrd0/gCPPProcess.o build.none_f_inl1_hrd0/gMatrixElementKernels.o build.none_f_inl1_hrd0/gBridgeKernels.o build.none_f_inl1_hrd0/gCrossSectionKernels.o build.none_f_inl1_hrd0/gRandomNumberKernels.o build.none_f_inl1_hrd0/gRamboSamplingKernels.o build.none_f_inl1_hrd0/testxxx_cu.o  build.none_f_inl1_hrd0/testmisc_cu.o  build.none_f_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl1_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl1_hrd0/gcheck.exe build.none_f_inl1_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl1_hrd0'  -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_gg_ttxg_cuda build.none_f_inl1_hrd0/gRandomNumberKernels.o build.none_f_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl1_hrd0/fgcheck.exe build.none_f_inl1_hrd0/fcheck_sa.o build.none_f_inl1_hrd0/fsampler_cu.o -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl1_hrd0'  -lgfortran -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_gg_ttxg_cuda build.none_f_inl1_hrd0/gRandomNumberKernels.o build.none_f_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
 touch build.none_f_inl1_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_f_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.none_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.none_f_inl1_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_f_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.none_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.none_f_inl1_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.none_f_inl1_hrd0/libmg5amc_gg_ttxg_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_f_inl1_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.none_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.none_f_inl1_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
 CUDACPP_BUILDDIR='build.512y_f_inl1_hrd0'
 make -f cudacpp.mk
@@ -4737,22 +4784,18 @@ HELINL=1
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.512y_f_inl1_hrd0 for tag=512y_f_inl1_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.512y_f_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.512y_f_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.512y_f_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.512y_f_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512y_f_inl1_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512y_f_inl1_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512y_f_inl1_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512y_f_inl1_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512y_f_inl1_hrd0/gRandomNumberKernels.o
 AVX=512y
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.512y_f_inl1_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512y_f_inl1_hrd0/gMatrixElementKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512y_f_inl1_hrd0/gBridgeKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.512y_f_inl1_hrd0/Parameters_sm.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512y_f_inl1_hrd0/gCrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.512y_f_inl1_hrd0/read_slha.o
-mkdir -p ../lib/build.512y_f_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512y_f_inl1_hrd0/fbridge_cu.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512y_f_inl1_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512y_f_inl1_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512y_f_inl1_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.512y_f_inl1_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.512y_f_inl1_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.512y_f_inl1_hrd0/MatrixElementKernels.o
@@ -4762,57 +4805,62 @@ ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.512y_f_inl1_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.512y_f_inl1_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.512y_f_inl1_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512y_f_inl1_hrd0/testxxx_cu.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.512y_f_inl1_hrd0/Parameters_sm.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512y_f_inl1_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.512y_f_inl1_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512y_f_inl1_hrd0/testmisc_cu.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.512y_f_inl1_hrd0/read_slha.o
+mkdir -p ../lib/build.512y_f_inl1_hrd0
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512y_f_inl1_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.512y_f_inl1_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.512y_f_inl1_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.512y_f_inl1_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.512y_f_inl1_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512y_f_inl1_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512y_f_inl1_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.512y_f_inl1_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.512y_f_inl1_hrd0/libmg5amc_common.so build.512y_f_inl1_hrd0/Parameters_sm.o build.512y_f_inl1_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512y_f_inl1_hrd0/libmg5amc_gg_ttxg_cuda.so build.512y_f_inl1_hrd0/gCPPProcess.o build.512y_f_inl1_hrd0/gMatrixElementKernels.o build.512y_f_inl1_hrd0/gBridgeKernels.o build.512y_f_inl1_hrd0/gCrossSectionKernels.o build.512y_f_inl1_hrd0/fbridge_cu.o -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512y_f_inl1_hrd0/libmg5amc_gg_ttxg_cpp.so build.512y_f_inl1_hrd0/CPPProcess.o build.512y_f_inl1_hrd0/MatrixElementKernels.o build.512y_f_inl1_hrd0/BridgeKernels.o build.512y_f_inl1_hrd0/CrossSectionKernels.o build.512y_f_inl1_hrd0/fbridge.o -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl1_hrd0/runTest.exe build.512y_f_inl1_hrd0/CPPProcess.o build.512y_f_inl1_hrd0/MatrixElementKernels.o build.512y_f_inl1_hrd0/BridgeKernels.o build.512y_f_inl1_hrd0/CrossSectionKernels.o build.512y_f_inl1_hrd0/RandomNumberKernels.o build.512y_f_inl1_hrd0/RamboSamplingKernels.o build.512y_f_inl1_hrd0/testxxx.o  build.512y_f_inl1_hrd0/testmisc.o  build.512y_f_inl1_hrd0/runTest.o build.512y_f_inl1_hrd0/gCPPProcess.o build.512y_f_inl1_hrd0/gMatrixElementKernels.o build.512y_f_inl1_hrd0/gBridgeKernels.o build.512y_f_inl1_hrd0/gCrossSectionKernels.o build.512y_f_inl1_hrd0/gRandomNumberKernels.o build.512y_f_inl1_hrd0/gRamboSamplingKernels.o build.512y_f_inl1_hrd0/testxxx_cu.o  build.512y_f_inl1_hrd0/testmisc_cu.o  build.512y_f_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_f_inl1_hrd0/check.exe build.512y_f_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_gg_ttxg_cpp build.512y_f_inl1_hrd0/RandomNumberKernels.o build.512y_f_inl1_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_f_inl1_hrd0/fcheck.exe build.512y_f_inl1_hrd0/fcheck_sa.o build.512y_f_inl1_hrd0/fsampler.o -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_gg_ttxg_cpp build.512y_f_inl1_hrd0/RandomNumberKernels.o build.512y_f_inl1_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl1_hrd0/gcheck.exe build.512y_f_inl1_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_gg_ttxg_cuda build.512y_f_inl1_hrd0/gRandomNumberKernels.o build.512y_f_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl1_hrd0/fgcheck.exe build.512y_f_inl1_hrd0/fcheck_sa.o build.512y_f_inl1_hrd0/fsampler_cu.o -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_gg_ttxg_cuda build.512y_f_inl1_hrd0/gRandomNumberKernels.o build.512y_f_inl1_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512y_f_inl1_hrd0/libmg5amc_gg_ttxg_cuda.so build.512y_f_inl1_hrd0/gCPPProcess.o build.512y_f_inl1_hrd0/gMatrixElementKernels.o build.512y_f_inl1_hrd0/gBridgeKernels.o build.512y_f_inl1_hrd0/gCrossSectionKernels.o build.512y_f_inl1_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl1_hrd0/gcheck.exe build.512y_f_inl1_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl1_hrd0'  -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_gg_ttxg_cuda build.512y_f_inl1_hrd0/gRandomNumberKernels.o build.512y_f_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl1_hrd0/fgcheck.exe build.512y_f_inl1_hrd0/fcheck_sa.o build.512y_f_inl1_hrd0/fsampler_cu.o -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl1_hrd0'  -lgfortran -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_gg_ttxg_cuda build.512y_f_inl1_hrd0/gRandomNumberKernels.o build.512y_f_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512y_f_inl1_hrd0/libmg5amc_gg_ttxg_cpp.so build.512y_f_inl1_hrd0/CPPProcess.o build.512y_f_inl1_hrd0/MatrixElementKernels.o build.512y_f_inl1_hrd0/BridgeKernels.o build.512y_f_inl1_hrd0/CrossSectionKernels.o build.512y_f_inl1_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_f_inl1_hrd0/check.exe build.512y_f_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_f_inl1_hrd0'  -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_gg_ttxg_cpp build.512y_f_inl1_hrd0/RandomNumberKernels.o build.512y_f_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_f_inl1_hrd0/fcheck.exe build.512y_f_inl1_hrd0/fcheck_sa.o build.512y_f_inl1_hrd0/fsampler.o -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_f_inl1_hrd0'  -lgfortran -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_gg_ttxg_cpp build.512y_f_inl1_hrd0/RandomNumberKernels.o build.512y_f_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl1_hrd0/runTest.exe build.512y_f_inl1_hrd0/CPPProcess.o build.512y_f_inl1_hrd0/MatrixElementKernels.o build.512y_f_inl1_hrd0/BridgeKernels.o build.512y_f_inl1_hrd0/CrossSectionKernels.o build.512y_f_inl1_hrd0/RandomNumberKernels.o build.512y_f_inl1_hrd0/RamboSamplingKernels.o build.512y_f_inl1_hrd0/testxxx.o  build.512y_f_inl1_hrd0/testmisc.o  build.512y_f_inl1_hrd0/runTest.o build.512y_f_inl1_hrd0/gCPPProcess.o build.512y_f_inl1_hrd0/gMatrixElementKernels.o build.512y_f_inl1_hrd0/gBridgeKernels.o build.512y_f_inl1_hrd0/gCrossSectionKernels.o build.512y_f_inl1_hrd0/gRandomNumberKernels.o build.512y_f_inl1_hrd0/gRamboSamplingKernels.o build.512y_f_inl1_hrd0/testxxx_cu.o  build.512y_f_inl1_hrd0/testmisc_cu.o  build.512y_f_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl1_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
 touch build.512y_f_inl1_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_f_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.512y_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_f_inl1_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_f_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512y_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_f_inl1_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.512y_f_inl1_hrd0/libmg5amc_gg_ttxg_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_f_inl1_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512y_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_f_inl1_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:05:48
+DATE: 2022-09-25_00:04:16
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl1_hrd0/gcheck.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl1_hrd0/gcheck.exe -p 64 256 20 OMP=
 Process                     = SIGMA_SM_GG_TTXG_CUDA [nvcc 11.7.99 (gcc 11.2.0)] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK
 FP precision                = FLOAT (NaN/abnormal=0, zero=0)
-EvtsPerSec[Rmb+ME]     (23) = ( 2.455926e+07                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 3.388705e+07                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 3.505986e+07                 )  sec^-1
-MeanMatrixElemValue         = ( 2.361364e+02 +- 1.906865e+02 )  GeV^-2
-TOTAL       :     0.495171 sec
-real	0m0.772s
-==PROF== Profiling "sigmaKin": launch__registers_per_thread 243
-==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100%
+EvtsPerSec[Rmb+ME]     (23) = ( 1.070160e+07                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 1.312354e+07                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 1.328105e+07                 )  sec^-1
+MeanMatrixElemValue         = ( 4.102969e+02 +- 2.728659e+02 )  GeV^-2
+TOTAL       :     2.425864 sec
+real	0m2.902s
+   launch__registers_per_thread N/A
+   sm__sass_average_branch_targets_threads_uniform.pct N/A
 .........................................................................
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl1_hrd0/gcheck.exe -p 2048 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl1_hrd0/gcheck.exe -p 2048 256 2 OMP=
 Process                     = SIGMA_SM_GG_TTXG_CUDA [nvcc 11.7.99 (gcc 11.2.0)] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK
 FP precision                = FLOAT (NaN/abnormal=0, zero=0)
-EvtsPerSec[Rmb+ME]     (23) = ( 3.244777e+07                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 4.470384e+07                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 4.553218e+07                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 1.454905e+07                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 1.823412e+07                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 1.837018e+07                 )  sec^-1
 MeanMatrixElemValue         = ( 2.814041e+03 +- 2.181057e+03 )  GeV^-2
-TOTAL       :     0.578850 sec
-real	0m0.872s
+TOTAL       :     2.494332 sec
+real	0m2.957s
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl1_hrd0/gcheck.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl1_hrd0/fgcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl1_hrd0/gcheck.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl1_hrd0/fgcheck.exe 2 64 2
 Avg ME (C++/CUDA)   = 1.412607e+00
 Avg ME (F77/CUDA)   = 1.4132214892143509
 Relative difference = 0.00043500365944025603
@@ -4820,35 +4868,35 @@ ERROR (relative difference > 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:05:55 CEST 2022 Will execute './throughputX.sh -makej -ggttg -noneonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:04:46 CEST 2022 Will execute './throughputX.sh -makej -ggttg -noneonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -noneonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
 CUDACPP_BUILDDIR='build.none_d_inl0_hrd0'
 make: Nothing to be done for `all'.
 
-DATE: 2022-08-31_21:05:55
+DATE: 2022-09-25_00:04:46
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl0_hrd0/check.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl0_hrd0/check.exe -p 64 256 20 OMP=
 Process                     = SIGMA_SM_GG_TTXG_CPP [gcc 11.2.0] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CPP:DBL+CXS:CURHST+RMBHST+MESHST/none+NAVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = SCALAR ('none': ~vector[1], no SIMD)
-EvtsPerSec[Rmb+ME]     (23) = ( 2.355236e+04                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 2.381964e+04                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 2.381964e+04                 )  sec^-1
-MeanMatrixElemValue         = ( 2.360828e+02 +- 1.906418e+02 )  GeV^-2
-TOTAL       :     1.400260 sec
-real	0m1.407s
+EvtsPerSec[Rmb+ME]     (23) = ( 2.360388e+04                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 2.386657e+04                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 2.386657e+04                 )  sec^-1
+MeanMatrixElemValue         = ( 4.103783e+02 +- 2.727382e+02 )  GeV^-2
+TOTAL       :    13.922817 sec
+real	0m13.930s
 =Symbols in CPPProcess.o= (~sse4:  852) (avx2:    0) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl0_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl0_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl0_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl0_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 1.413122e+00
 Avg ME (F77/C++)    = 1.4131213684432433
 Relative difference = 4.46923023397472e-07
@@ -4856,35 +4904,35 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:05:58 CEST 2022 Will execute './throughputX.sh -makej -ggttg -noneonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:05:15 CEST 2022 Will execute './throughputX.sh -makej -ggttg -noneonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -noneonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
 CUDACPP_BUILDDIR='build.none_d_inl1_hrd0'
 make: Nothing to be done for `all'.
 
-DATE: 2022-08-31_21:05:58
+DATE: 2022-09-25_00:05:15
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl1_hrd0/check.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl1_hrd0/check.exe -p 64 256 20 OMP=
 Process                     = SIGMA_SM_GG_TTXG_CPP [gcc 11.2.0] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CPP:DBL+CXS:CURHST+RMBHST+MESHST/none+NAVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = SCALAR ('none': ~vector[1], no SIMD)
-EvtsPerSec[Rmb+ME]     (23) = ( 6.238001e+03                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 6.256510e+03                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 6.256510e+03                 )  sec^-1
-MeanMatrixElemValue         = ( 2.360828e+02 +- 1.906418e+02 )  GeV^-2
-TOTAL       :     5.263914 sec
-real	0m5.271s
+EvtsPerSec[Rmb+ME]     (23) = ( 6.247463e+03                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 6.265805e+03                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 6.265805e+03                 )  sec^-1
+MeanMatrixElemValue         = ( 4.103783e+02 +- 2.727382e+02 )  GeV^-2
+TOTAL       :    52.493141 sec
+real	0m52.500s
 =Symbols in CPPProcess.o= (~sse4: 3986) (avx2:    0) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl1_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl1_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl1_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl1_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 1.413122e+00
 Avg ME (F77/C++)    = 1.4131213684432460
 Relative difference = 4.4692302151190567e-07
@@ -4892,35 +4940,35 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:06:06 CEST 2022 Will execute './throughputX.sh -makej -ggttg -noneonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:06:23 CEST 2022 Will execute './throughputX.sh -makej -ggttg -noneonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -noneonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
 CUDACPP_BUILDDIR='build.none_f_inl0_hrd0'
 make: Nothing to be done for `all'.
 
-DATE: 2022-08-31_21:06:06
+DATE: 2022-09-25_00:06:23
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl0_hrd0/check.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl0_hrd0/check.exe -p 64 256 20 OMP=
 Process                     = SIGMA_SM_GG_TTXG_CPP [gcc 11.2.0] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CPP:FLT+CXS:CURHST+RMBHST+MESHST/none+NAVBRK
 FP precision                = FLOAT (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = SCALAR ('none': ~vector[1], no SIMD)
-EvtsPerSec[Rmb+ME]     (23) = ( 2.417425e+04                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 2.439809e+04                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 2.439809e+04                 )  sec^-1
-MeanMatrixElemValue         = ( 2.361173e+02 +- 1.906789e+02 )  GeV^-2
-TOTAL       :     1.362637 sec
-real	0m1.369s
+EvtsPerSec[Rmb+ME]     (23) = ( 2.422043e+04                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 2.444263e+04                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 2.444263e+04                 )  sec^-1
+MeanMatrixElemValue         = ( 4.105411e+02 +- 2.728834e+02 )  GeV^-2
+TOTAL       :    13.565874 sec
+real	0m13.572s
 =Symbols in CPPProcess.o= (~sse4:  860) (avx2:    0) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl0_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl0_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl0_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl0_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 1.412995e+00
 Avg ME (F77/C++)    = 1.4129948988143610
 Relative difference = 7.161075515395485e-08
@@ -4928,35 +4976,35 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:06:10 CEST 2022 Will execute './throughputX.sh -makej -ggttg -noneonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:06:52 CEST 2022 Will execute './throughputX.sh -makej -ggttg -noneonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -noneonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
 CUDACPP_BUILDDIR='build.none_f_inl1_hrd0'
 make: Nothing to be done for `all'.
 
-DATE: 2022-08-31_21:06:10
+DATE: 2022-09-25_00:06:52
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl1_hrd0/check.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl1_hrd0/check.exe -p 64 256 20 OMP=
 Process                     = SIGMA_SM_GG_TTXG_CPP [gcc 11.2.0] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CPP:FLT+CXS:CURHST+RMBHST+MESHST/none+NAVBRK
 FP precision                = FLOAT (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = SCALAR ('none': ~vector[1], no SIMD)
-EvtsPerSec[Rmb+ME]     (23) = ( 1.015198e+04                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 1.019122e+04                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 1.019122e+04                 )  sec^-1
-MeanMatrixElemValue         = ( 2.361175e+02 +- 1.906790e+02 )  GeV^-2
-TOTAL       :     3.235682 sec
-real	0m3.243s
+EvtsPerSec[Rmb+ME]     (23) = ( 1.017215e+04                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 1.021119e+04                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 1.021119e+04                 )  sec^-1
+MeanMatrixElemValue         = ( 4.105413e+02 +- 2.728834e+02 )  GeV^-2
+TOTAL       :    32.251469 sec
+real	0m32.258s
 =Symbols in CPPProcess.o= (~sse4: 2804) (avx2:    0) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl1_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl1_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl1_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl1_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 1.412986e+00
 Avg ME (F77/C++)    = 1.4129859106965625
 Relative difference = 6.320192665303974e-08
@@ -4964,13 +5012,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:06:15 CEST 2022 Will execute './throughputX.sh -makej -ggttg -sse4only  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:07:40 CEST 2022 Will execute './throughputX.sh -makej -ggttg -sse4only  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -sse4only implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
 CUDACPP_BUILDDIR='build.sse4_d_inl0_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -4980,71 +5028,72 @@ HELINL=0
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.sse4_d_inl0_hrd0 for tag=sse4_d_inl0_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.sse4_d_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gcheck_sa.cu -o build.sse4_d_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gcheck_sa.cu -o build.sse4_d_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gCPPProcess.cu -o build.sse4_d_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.sse4_d_inl0_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gBridgeKernels.cu -o build.sse4_d_inl0_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.sse4_d_inl0_hrd0/gCrossSectionKernels.o
 AVX=sse4
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gCPPProcess.cu -o build.sse4_d_inl0_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.sse4_d_inl0_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gBridgeKernels.cu -o build.sse4_d_inl0_hrd0/gBridgeKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.sse4_d_inl0_hrd0/gCrossSectionKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fbridge.cc -o build.sse4_d_inl0_hrd0/fbridge_cu.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -c Parameters_sm.cc -o build.sse4_d_inl0_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -c read_slha.cc -o build.sse4_d_inl0_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.sse4_d_inl0_hrd0/gRandomNumberKernels.o
-mkdir -p ../lib/build.sse4_d_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.sse4_d_inl0_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fbridge.cc -o build.sse4_d_inl0_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.sse4_d_inl0_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.sse4_d_inl0_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.sse4_d_inl0_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.sse4_d_inl0_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.sse4_d_inl0_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.sse4_d_inl0_hrd0/BridgeKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.sse4_d_inl0_hrd0/CrossSectionKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.sse4_d_inl0_hrd0/fbridge.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.sse4_d_inl0_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.sse4_d_inl0_hrd0/RamboSamplingKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -c read_slha.cc -o build.sse4_d_inl0_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.sse4_d_inl0_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testxxx.cc -o build.sse4_d_inl0_hrd0/testxxx_cu.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -c Parameters_sm.cc -o build.sse4_d_inl0_hrd0/Parameters_sm.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testxxx.cc -o build.sse4_d_inl0_hrd0/testxxx_cu.o
+mkdir -p ../lib/build.sse4_d_inl0_hrd0
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.sse4_d_inl0_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testmisc.cc -o build.sse4_d_inl0_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testmisc.cc -o build.sse4_d_inl0_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.sse4_d_inl0_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu runTest.cc -o build.sse4_d_inl0_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu runTest.cc -o build.sse4_d_inl0_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.sse4_d_inl0_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fsampler.cc -o build.sse4_d_inl0_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fsampler.cc -o build.sse4_d_inl0_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.sse4_d_inl0_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.sse4_d_inl0_hrd0/libmg5amc_common.so build.sse4_d_inl0_hrd0/Parameters_sm.o build.sse4_d_inl0_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.sse4_d_inl0_hrd0/libmg5amc_gg_ttxg_cuda.so build.sse4_d_inl0_hrd0/gCPPProcess.o build.sse4_d_inl0_hrd0/gMatrixElementKernels.o build.sse4_d_inl0_hrd0/gBridgeKernels.o build.sse4_d_inl0_hrd0/gCrossSectionKernels.o build.sse4_d_inl0_hrd0/fbridge_cu.o -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.sse4_d_inl0_hrd0/libmg5amc_gg_ttxg_cpp.so build.sse4_d_inl0_hrd0/CPPProcess.o build.sse4_d_inl0_hrd0/MatrixElementKernels.o build.sse4_d_inl0_hrd0/BridgeKernels.o build.sse4_d_inl0_hrd0/CrossSectionKernels.o build.sse4_d_inl0_hrd0/fbridge.o -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl0_hrd0/runTest.exe build.sse4_d_inl0_hrd0/CPPProcess.o build.sse4_d_inl0_hrd0/MatrixElementKernels.o build.sse4_d_inl0_hrd0/BridgeKernels.o build.sse4_d_inl0_hrd0/CrossSectionKernels.o build.sse4_d_inl0_hrd0/RandomNumberKernels.o build.sse4_d_inl0_hrd0/RamboSamplingKernels.o build.sse4_d_inl0_hrd0/testxxx.o  build.sse4_d_inl0_hrd0/testmisc.o  build.sse4_d_inl0_hrd0/runTest.o build.sse4_d_inl0_hrd0/gCPPProcess.o build.sse4_d_inl0_hrd0/gMatrixElementKernels.o build.sse4_d_inl0_hrd0/gBridgeKernels.o build.sse4_d_inl0_hrd0/gCrossSectionKernels.o build.sse4_d_inl0_hrd0/gRandomNumberKernels.o build.sse4_d_inl0_hrd0/gRamboSamplingKernels.o build.sse4_d_inl0_hrd0/testxxx_cu.o  build.sse4_d_inl0_hrd0/testmisc_cu.o  build.sse4_d_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_d_inl0_hrd0/check.exe build.sse4_d_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_gg_ttxg_cpp build.sse4_d_inl0_hrd0/RandomNumberKernels.o build.sse4_d_inl0_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_d_inl0_hrd0/fcheck.exe build.sse4_d_inl0_hrd0/fcheck_sa.o build.sse4_d_inl0_hrd0/fsampler.o -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_gg_ttxg_cpp build.sse4_d_inl0_hrd0/RandomNumberKernels.o build.sse4_d_inl0_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl0_hrd0/gcheck.exe build.sse4_d_inl0_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_gg_ttxg_cuda build.sse4_d_inl0_hrd0/gRandomNumberKernels.o build.sse4_d_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl0_hrd0/fgcheck.exe build.sse4_d_inl0_hrd0/fcheck_sa.o build.sse4_d_inl0_hrd0/fsampler_cu.o -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_gg_ttxg_cuda build.sse4_d_inl0_hrd0/gRandomNumberKernels.o build.sse4_d_inl0_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.sse4_d_inl0_hrd0/libmg5amc_gg_ttxg_cuda.so build.sse4_d_inl0_hrd0/gCPPProcess.o build.sse4_d_inl0_hrd0/gMatrixElementKernels.o build.sse4_d_inl0_hrd0/gBridgeKernels.o build.sse4_d_inl0_hrd0/gCrossSectionKernels.o build.sse4_d_inl0_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.sse4_d_inl0_hrd0/libmg5amc_gg_ttxg_cpp.so build.sse4_d_inl0_hrd0/CPPProcess.o build.sse4_d_inl0_hrd0/MatrixElementKernels.o build.sse4_d_inl0_hrd0/BridgeKernels.o build.sse4_d_inl0_hrd0/CrossSectionKernels.o build.sse4_d_inl0_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_d_inl0_hrd0/fcheck.exe build.sse4_d_inl0_hrd0/fcheck_sa.o build.sse4_d_inl0_hrd0/fsampler.o -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_d_inl0_hrd0'  -lgfortran -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_gg_ttxg_cpp build.sse4_d_inl0_hrd0/RandomNumberKernels.o build.sse4_d_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl0_hrd0/gcheck.exe build.sse4_d_inl0_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl0_hrd0'  -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_gg_ttxg_cuda build.sse4_d_inl0_hrd0/gRandomNumberKernels.o build.sse4_d_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl0_hrd0/fgcheck.exe build.sse4_d_inl0_hrd0/fcheck_sa.o build.sse4_d_inl0_hrd0/fsampler_cu.o -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl0_hrd0'  -lgfortran -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_gg_ttxg_cuda build.sse4_d_inl0_hrd0/gRandomNumberKernels.o build.sse4_d_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_d_inl0_hrd0/check.exe build.sse4_d_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_d_inl0_hrd0'  -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_gg_ttxg_cpp build.sse4_d_inl0_hrd0/RandomNumberKernels.o build.sse4_d_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl0_hrd0/runTest.exe build.sse4_d_inl0_hrd0/CPPProcess.o build.sse4_d_inl0_hrd0/MatrixElementKernels.o build.sse4_d_inl0_hrd0/BridgeKernels.o build.sse4_d_inl0_hrd0/CrossSectionKernels.o build.sse4_d_inl0_hrd0/RandomNumberKernels.o build.sse4_d_inl0_hrd0/RamboSamplingKernels.o build.sse4_d_inl0_hrd0/testxxx.o  build.sse4_d_inl0_hrd0/testmisc.o  build.sse4_d_inl0_hrd0/runTest.o build.sse4_d_inl0_hrd0/gCPPProcess.o build.sse4_d_inl0_hrd0/gMatrixElementKernels.o build.sse4_d_inl0_hrd0/gBridgeKernels.o build.sse4_d_inl0_hrd0/gCrossSectionKernels.o build.sse4_d_inl0_hrd0/gRandomNumberKernels.o build.sse4_d_inl0_hrd0/gRamboSamplingKernels.o build.sse4_d_inl0_hrd0/testxxx_cu.o  build.sse4_d_inl0_hrd0/testmisc_cu.o  build.sse4_d_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl0_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
 touch build.sse4_d_inl0_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_d_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.sse4_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_d_inl0_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_d_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.sse4_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_d_inl0_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.sse4_d_inl0_hrd0/libmg5amc_gg_ttxg_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_d_inl0_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.sse4_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_d_inl0_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:06:16
+DATE: 2022-09-25_00:07:49
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_d_inl0_hrd0/check.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_d_inl0_hrd0/check.exe -p 64 256 20 OMP=
 Process                     = SIGMA_SM_GG_TTXG_CPP [gcc 11.2.0] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CPP:DBL+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 4.387968e+04                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 4.479785e+04                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 4.479785e+04                 )  sec^-1
-MeanMatrixElemValue         = ( 2.360828e+02 +- 1.906418e+02 )  GeV^-2
-TOTAL       :     0.755423 sec
-real	0m0.763s
+EvtsPerSec[Rmb+ME]     (23) = ( 4.400091e+04                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 4.490922e+04                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 4.490922e+04                 )  sec^-1
+MeanMatrixElemValue         = ( 4.103783e+02 +- 2.727382e+02 )  GeV^-2
+TOTAL       :     7.486098 sec
+real	0m7.493s
 =Symbols in CPPProcess.o= (~sse4: 4993) (avx2:    0) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_d_inl0_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_d_inl0_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_d_inl0_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_d_inl0_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 1.413122e+00
 Avg ME (F77/C++)    = 1.4131213684432429
 Relative difference = 4.4692302371173303e-07
@@ -5052,13 +5101,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:06:19 CEST 2022 Will execute './throughputX.sh -makej -ggttg -sse4only  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:08:12 CEST 2022 Will execute './throughputX.sh -makej -ggttg -sse4only  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -sse4only implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
 CUDACPP_BUILDDIR='build.sse4_d_inl1_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -5068,71 +5117,72 @@ HELINL=1
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.sse4_d_inl1_hrd0 for tag=sse4_d_inl1_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.sse4_d_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.sse4_d_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.sse4_d_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.sse4_d_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.sse4_d_inl1_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.sse4_d_inl1_hrd0/gBridgeKernels.o
 AVX=sse4
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.sse4_d_inl1_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.sse4_d_inl1_hrd0/gMatrixElementKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.sse4_d_inl1_hrd0/gBridgeKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.sse4_d_inl1_hrd0/gCrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.sse4_d_inl1_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.sse4_d_inl1_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.sse4_d_inl1_hrd0/fbridge_cu.o
-mkdir -p ../lib/build.sse4_d_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.sse4_d_inl1_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.sse4_d_inl1_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.sse4_d_inl1_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.sse4_d_inl1_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.sse4_d_inl1_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.sse4_d_inl1_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.sse4_d_inl1_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.sse4_d_inl1_hrd0/CPPProcess.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.sse4_d_inl1_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.sse4_d_inl1_hrd0/BridgeKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.sse4_d_inl1_hrd0/read_slha.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.sse4_d_inl1_hrd0/Parameters_sm.o
+mkdir -p ../lib/build.sse4_d_inl1_hrd0
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.sse4_d_inl1_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.sse4_d_inl1_hrd0/fbridge.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.sse4_d_inl1_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.sse4_d_inl1_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.sse4_d_inl1_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.sse4_d_inl1_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.sse4_d_inl1_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.sse4_d_inl1_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.sse4_d_inl1_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.sse4_d_inl1_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.sse4_d_inl1_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.sse4_d_inl1_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.sse4_d_inl1_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.sse4_d_inl1_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.sse4_d_inl1_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.sse4_d_inl1_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.sse4_d_inl1_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.sse4_d_inl1_hrd0/libmg5amc_common.so build.sse4_d_inl1_hrd0/Parameters_sm.o build.sse4_d_inl1_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.sse4_d_inl1_hrd0/libmg5amc_gg_ttxg_cuda.so build.sse4_d_inl1_hrd0/gCPPProcess.o build.sse4_d_inl1_hrd0/gMatrixElementKernels.o build.sse4_d_inl1_hrd0/gBridgeKernels.o build.sse4_d_inl1_hrd0/gCrossSectionKernels.o build.sse4_d_inl1_hrd0/fbridge_cu.o -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.sse4_d_inl1_hrd0/libmg5amc_gg_ttxg_cpp.so build.sse4_d_inl1_hrd0/CPPProcess.o build.sse4_d_inl1_hrd0/MatrixElementKernels.o build.sse4_d_inl1_hrd0/BridgeKernels.o build.sse4_d_inl1_hrd0/CrossSectionKernels.o build.sse4_d_inl1_hrd0/fbridge.o -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl1_hrd0/runTest.exe build.sse4_d_inl1_hrd0/CPPProcess.o build.sse4_d_inl1_hrd0/MatrixElementKernels.o build.sse4_d_inl1_hrd0/BridgeKernels.o build.sse4_d_inl1_hrd0/CrossSectionKernels.o build.sse4_d_inl1_hrd0/RandomNumberKernels.o build.sse4_d_inl1_hrd0/RamboSamplingKernels.o build.sse4_d_inl1_hrd0/testxxx.o  build.sse4_d_inl1_hrd0/testmisc.o  build.sse4_d_inl1_hrd0/runTest.o build.sse4_d_inl1_hrd0/gCPPProcess.o build.sse4_d_inl1_hrd0/gMatrixElementKernels.o build.sse4_d_inl1_hrd0/gBridgeKernels.o build.sse4_d_inl1_hrd0/gCrossSectionKernels.o build.sse4_d_inl1_hrd0/gRandomNumberKernels.o build.sse4_d_inl1_hrd0/gRamboSamplingKernels.o build.sse4_d_inl1_hrd0/testxxx_cu.o  build.sse4_d_inl1_hrd0/testmisc_cu.o  build.sse4_d_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_d_inl1_hrd0/check.exe build.sse4_d_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_gg_ttxg_cpp build.sse4_d_inl1_hrd0/RandomNumberKernels.o build.sse4_d_inl1_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_d_inl1_hrd0/fcheck.exe build.sse4_d_inl1_hrd0/fcheck_sa.o build.sse4_d_inl1_hrd0/fsampler.o -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_gg_ttxg_cpp build.sse4_d_inl1_hrd0/RandomNumberKernels.o build.sse4_d_inl1_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl1_hrd0/gcheck.exe build.sse4_d_inl1_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_gg_ttxg_cuda build.sse4_d_inl1_hrd0/gRandomNumberKernels.o build.sse4_d_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl1_hrd0/fgcheck.exe build.sse4_d_inl1_hrd0/fcheck_sa.o build.sse4_d_inl1_hrd0/fsampler_cu.o -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_gg_ttxg_cuda build.sse4_d_inl1_hrd0/gRandomNumberKernels.o build.sse4_d_inl1_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.sse4_d_inl1_hrd0/libmg5amc_gg_ttxg_cuda.so build.sse4_d_inl1_hrd0/gCPPProcess.o build.sse4_d_inl1_hrd0/gMatrixElementKernels.o build.sse4_d_inl1_hrd0/gBridgeKernels.o build.sse4_d_inl1_hrd0/gCrossSectionKernels.o build.sse4_d_inl1_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl1_hrd0/gcheck.exe build.sse4_d_inl1_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl1_hrd0'  -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_gg_ttxg_cuda build.sse4_d_inl1_hrd0/gRandomNumberKernels.o build.sse4_d_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl1_hrd0/fgcheck.exe build.sse4_d_inl1_hrd0/fcheck_sa.o build.sse4_d_inl1_hrd0/fsampler_cu.o -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl1_hrd0'  -lgfortran -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_gg_ttxg_cuda build.sse4_d_inl1_hrd0/gRandomNumberKernels.o build.sse4_d_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.sse4_d_inl1_hrd0/libmg5amc_gg_ttxg_cpp.so build.sse4_d_inl1_hrd0/CPPProcess.o build.sse4_d_inl1_hrd0/MatrixElementKernels.o build.sse4_d_inl1_hrd0/BridgeKernels.o build.sse4_d_inl1_hrd0/CrossSectionKernels.o build.sse4_d_inl1_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl1_hrd0/runTest.exe build.sse4_d_inl1_hrd0/CPPProcess.o build.sse4_d_inl1_hrd0/MatrixElementKernels.o build.sse4_d_inl1_hrd0/BridgeKernels.o build.sse4_d_inl1_hrd0/CrossSectionKernels.o build.sse4_d_inl1_hrd0/RandomNumberKernels.o build.sse4_d_inl1_hrd0/RamboSamplingKernels.o build.sse4_d_inl1_hrd0/testxxx.o  build.sse4_d_inl1_hrd0/testmisc.o  build.sse4_d_inl1_hrd0/runTest.o build.sse4_d_inl1_hrd0/gCPPProcess.o build.sse4_d_inl1_hrd0/gMatrixElementKernels.o build.sse4_d_inl1_hrd0/gBridgeKernels.o build.sse4_d_inl1_hrd0/gCrossSectionKernels.o build.sse4_d_inl1_hrd0/gRandomNumberKernels.o build.sse4_d_inl1_hrd0/gRamboSamplingKernels.o build.sse4_d_inl1_hrd0/testxxx_cu.o  build.sse4_d_inl1_hrd0/testmisc_cu.o  build.sse4_d_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl1_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_d_inl1_hrd0/check.exe build.sse4_d_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_d_inl1_hrd0'  -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_gg_ttxg_cpp build.sse4_d_inl1_hrd0/RandomNumberKernels.o build.sse4_d_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_d_inl1_hrd0/fcheck.exe build.sse4_d_inl1_hrd0/fcheck_sa.o build.sse4_d_inl1_hrd0/fsampler.o -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_d_inl1_hrd0'  -lgfortran -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_gg_ttxg_cpp build.sse4_d_inl1_hrd0/RandomNumberKernels.o build.sse4_d_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
 touch build.sse4_d_inl1_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_d_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.sse4_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_d_inl1_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_d_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.sse4_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_d_inl1_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.sse4_d_inl1_hrd0/libmg5amc_gg_ttxg_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_d_inl1_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.sse4_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_d_inl1_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:06:20
+DATE: 2022-09-25_00:08:19
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_d_inl1_hrd0/check.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_d_inl1_hrd0/check.exe -p 64 256 20 OMP=
 Process                     = SIGMA_SM_GG_TTXG_CPP [gcc 11.2.0] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CPP:DBL+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 4.094535e+04                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 4.174356e+04                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 4.174356e+04                 )  sec^-1
-MeanMatrixElemValue         = ( 2.360828e+02 +- 1.906418e+02 )  GeV^-2
-TOTAL       :     0.808944 sec
-real	0m0.816s
+EvtsPerSec[Rmb+ME]     (23) = ( 4.110709e+04                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 4.189894e+04                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 4.189894e+04                 )  sec^-1
+MeanMatrixElemValue         = ( 4.103783e+02 +- 2.727382e+02 )  GeV^-2
+TOTAL       :     8.010281 sec
+real	0m8.017s
 =Symbols in CPPProcess.o= (~sse4:10885) (avx2:    0) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_d_inl1_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_d_inl1_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_d_inl1_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_d_inl1_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 1.413122e+00
 Avg ME (F77/C++)    = 1.4131213684432509
 Relative difference = 4.469230180550341e-07
@@ -5140,13 +5190,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:06:23 CEST 2022 Will execute './throughputX.sh -makej -ggttg -sse4only -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:08:42 CEST 2022 Will execute './throughputX.sh -makej -ggttg -sse4only -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -sse4only implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
 CUDACPP_BUILDDIR='build.sse4_f_inl0_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -5156,71 +5206,72 @@ HELINL=0
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.sse4_f_inl0_hrd0 for tag=sse4_f_inl0_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.sse4_f_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gcheck_sa.cu -o build.sse4_f_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gcheck_sa.cu -o build.sse4_f_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gCPPProcess.cu -o build.sse4_f_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.sse4_f_inl0_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gBridgeKernels.cu -o build.sse4_f_inl0_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.sse4_f_inl0_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fbridge.cc -o build.sse4_f_inl0_hrd0/fbridge_cu.o
 AVX=sse4
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gCPPProcess.cu -o build.sse4_f_inl0_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.sse4_f_inl0_hrd0/gMatrixElementKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gBridgeKernels.cu -o build.sse4_f_inl0_hrd0/gBridgeKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -c read_slha.cc -o build.sse4_f_inl0_hrd0/read_slha.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -c Parameters_sm.cc -o build.sse4_f_inl0_hrd0/Parameters_sm.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.sse4_f_inl0_hrd0/gCrossSectionKernels.o
-mkdir -p ../lib/build.sse4_f_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fbridge.cc -o build.sse4_f_inl0_hrd0/fbridge_cu.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.sse4_f_inl0_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.sse4_f_inl0_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.sse4_f_inl0_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.sse4_f_inl0_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.sse4_f_inl0_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.sse4_f_inl0_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.sse4_f_inl0_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.sse4_f_inl0_hrd0/BridgeKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.sse4_f_inl0_hrd0/CrossSectionKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.sse4_f_inl0_hrd0/fbridge.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.sse4_f_inl0_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.sse4_f_inl0_hrd0/RamboSamplingKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -c Parameters_sm.cc -o build.sse4_f_inl0_hrd0/Parameters_sm.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.sse4_f_inl0_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testxxx.cc -o build.sse4_f_inl0_hrd0/testxxx_cu.o
+mkdir -p ../lib/build.sse4_f_inl0_hrd0
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -c read_slha.cc -o build.sse4_f_inl0_hrd0/read_slha.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testxxx.cc -o build.sse4_f_inl0_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.sse4_f_inl0_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testmisc.cc -o build.sse4_f_inl0_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testmisc.cc -o build.sse4_f_inl0_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.sse4_f_inl0_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu runTest.cc -o build.sse4_f_inl0_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu runTest.cc -o build.sse4_f_inl0_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.sse4_f_inl0_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fsampler.cc -o build.sse4_f_inl0_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fsampler.cc -o build.sse4_f_inl0_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.sse4_f_inl0_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.sse4_f_inl0_hrd0/libmg5amc_common.so build.sse4_f_inl0_hrd0/Parameters_sm.o build.sse4_f_inl0_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.sse4_f_inl0_hrd0/libmg5amc_gg_ttxg_cuda.so build.sse4_f_inl0_hrd0/gCPPProcess.o build.sse4_f_inl0_hrd0/gMatrixElementKernels.o build.sse4_f_inl0_hrd0/gBridgeKernels.o build.sse4_f_inl0_hrd0/gCrossSectionKernels.o build.sse4_f_inl0_hrd0/fbridge_cu.o -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.sse4_f_inl0_hrd0/libmg5amc_gg_ttxg_cpp.so build.sse4_f_inl0_hrd0/CPPProcess.o build.sse4_f_inl0_hrd0/MatrixElementKernels.o build.sse4_f_inl0_hrd0/BridgeKernels.o build.sse4_f_inl0_hrd0/CrossSectionKernels.o build.sse4_f_inl0_hrd0/fbridge.o -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl0_hrd0/runTest.exe build.sse4_f_inl0_hrd0/CPPProcess.o build.sse4_f_inl0_hrd0/MatrixElementKernels.o build.sse4_f_inl0_hrd0/BridgeKernels.o build.sse4_f_inl0_hrd0/CrossSectionKernels.o build.sse4_f_inl0_hrd0/RandomNumberKernels.o build.sse4_f_inl0_hrd0/RamboSamplingKernels.o build.sse4_f_inl0_hrd0/testxxx.o  build.sse4_f_inl0_hrd0/testmisc.o  build.sse4_f_inl0_hrd0/runTest.o build.sse4_f_inl0_hrd0/gCPPProcess.o build.sse4_f_inl0_hrd0/gMatrixElementKernels.o build.sse4_f_inl0_hrd0/gBridgeKernels.o build.sse4_f_inl0_hrd0/gCrossSectionKernels.o build.sse4_f_inl0_hrd0/gRandomNumberKernels.o build.sse4_f_inl0_hrd0/gRamboSamplingKernels.o build.sse4_f_inl0_hrd0/testxxx_cu.o  build.sse4_f_inl0_hrd0/testmisc_cu.o  build.sse4_f_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_f_inl0_hrd0/check.exe build.sse4_f_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_gg_ttxg_cpp build.sse4_f_inl0_hrd0/RandomNumberKernels.o build.sse4_f_inl0_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_f_inl0_hrd0/fcheck.exe build.sse4_f_inl0_hrd0/fcheck_sa.o build.sse4_f_inl0_hrd0/fsampler.o -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_gg_ttxg_cpp build.sse4_f_inl0_hrd0/RandomNumberKernels.o build.sse4_f_inl0_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl0_hrd0/gcheck.exe build.sse4_f_inl0_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_gg_ttxg_cuda build.sse4_f_inl0_hrd0/gRandomNumberKernels.o build.sse4_f_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl0_hrd0/fgcheck.exe build.sse4_f_inl0_hrd0/fcheck_sa.o build.sse4_f_inl0_hrd0/fsampler_cu.o -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_gg_ttxg_cuda build.sse4_f_inl0_hrd0/gRandomNumberKernels.o build.sse4_f_inl0_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.sse4_f_inl0_hrd0/libmg5amc_gg_ttxg_cuda.so build.sse4_f_inl0_hrd0/gCPPProcess.o build.sse4_f_inl0_hrd0/gMatrixElementKernels.o build.sse4_f_inl0_hrd0/gBridgeKernels.o build.sse4_f_inl0_hrd0/gCrossSectionKernels.o build.sse4_f_inl0_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.sse4_f_inl0_hrd0/libmg5amc_gg_ttxg_cpp.so build.sse4_f_inl0_hrd0/CPPProcess.o build.sse4_f_inl0_hrd0/MatrixElementKernels.o build.sse4_f_inl0_hrd0/BridgeKernels.o build.sse4_f_inl0_hrd0/CrossSectionKernels.o build.sse4_f_inl0_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_f_inl0_hrd0/fcheck.exe build.sse4_f_inl0_hrd0/fcheck_sa.o build.sse4_f_inl0_hrd0/fsampler.o -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_f_inl0_hrd0'  -lgfortran -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_gg_ttxg_cpp build.sse4_f_inl0_hrd0/RandomNumberKernels.o build.sse4_f_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl0_hrd0/gcheck.exe build.sse4_f_inl0_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl0_hrd0'  -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_gg_ttxg_cuda build.sse4_f_inl0_hrd0/gRandomNumberKernels.o build.sse4_f_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl0_hrd0/fgcheck.exe build.sse4_f_inl0_hrd0/fcheck_sa.o build.sse4_f_inl0_hrd0/fsampler_cu.o -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl0_hrd0'  -lgfortran -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_gg_ttxg_cuda build.sse4_f_inl0_hrd0/gRandomNumberKernels.o build.sse4_f_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_f_inl0_hrd0/check.exe build.sse4_f_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_f_inl0_hrd0'  -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_gg_ttxg_cpp build.sse4_f_inl0_hrd0/RandomNumberKernels.o build.sse4_f_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl0_hrd0/runTest.exe build.sse4_f_inl0_hrd0/CPPProcess.o build.sse4_f_inl0_hrd0/MatrixElementKernels.o build.sse4_f_inl0_hrd0/BridgeKernels.o build.sse4_f_inl0_hrd0/CrossSectionKernels.o build.sse4_f_inl0_hrd0/RandomNumberKernels.o build.sse4_f_inl0_hrd0/RamboSamplingKernels.o build.sse4_f_inl0_hrd0/testxxx.o  build.sse4_f_inl0_hrd0/testmisc.o  build.sse4_f_inl0_hrd0/runTest.o build.sse4_f_inl0_hrd0/gCPPProcess.o build.sse4_f_inl0_hrd0/gMatrixElementKernels.o build.sse4_f_inl0_hrd0/gBridgeKernels.o build.sse4_f_inl0_hrd0/gCrossSectionKernels.o build.sse4_f_inl0_hrd0/gRandomNumberKernels.o build.sse4_f_inl0_hrd0/gRamboSamplingKernels.o build.sse4_f_inl0_hrd0/testxxx_cu.o  build.sse4_f_inl0_hrd0/testmisc_cu.o  build.sse4_f_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl0_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
 touch build.sse4_f_inl0_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_f_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.sse4_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_f_inl0_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_f_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.sse4_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_f_inl0_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.sse4_f_inl0_hrd0/libmg5amc_gg_ttxg_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_f_inl0_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.sse4_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_f_inl0_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:06:25
+DATE: 2022-09-25_00:08:51
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_f_inl0_hrd0/check.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_f_inl0_hrd0/check.exe -p 64 256 20 OMP=
 Process                     = SIGMA_SM_GG_TTXG_CPP [gcc 11.2.0] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CPP:FLT+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK
 FP precision                = FLOAT (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 7.944568e+04                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 8.196074e+04                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 8.196074e+04                 )  sec^-1
-MeanMatrixElemValue         = ( 2.361173e+02 +- 1.906790e+02 )  GeV^-2
-TOTAL       :     0.418911 sec
-real	0m0.425s
+EvtsPerSec[Rmb+ME]     (23) = ( 7.953464e+04                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 8.202498e+04                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 8.202498e+04                 )  sec^-1
+MeanMatrixElemValue         = ( 4.105414e+02 +- 2.728832e+02 )  GeV^-2
+TOTAL       :     4.155622 sec
+real	0m4.162s
 =Symbols in CPPProcess.o= (~sse4: 5737) (avx2:    0) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_f_inl0_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_f_inl0_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_f_inl0_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_f_inl0_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 1.412996e+00
 Avg ME (F77/C++)    = 1.4129958932161344
 Relative difference = 7.557265946100326e-08
@@ -5228,13 +5279,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:06:27 CEST 2022 Will execute './throughputX.sh -makej -ggttg -sse4only -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:09:11 CEST 2022 Will execute './throughputX.sh -makej -ggttg -sse4only -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -sse4only implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
 CUDACPP_BUILDDIR='build.sse4_f_inl1_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -5244,71 +5295,72 @@ HELINL=1
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.sse4_f_inl1_hrd0 for tag=sse4_f_inl1_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.sse4_f_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.sse4_f_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.sse4_f_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.sse4_f_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.sse4_f_inl1_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.sse4_f_inl1_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.sse4_f_inl1_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.sse4_f_inl1_hrd0/fbridge_cu.o
 AVX=sse4
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.sse4_f_inl1_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.sse4_f_inl1_hrd0/gMatrixElementKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.sse4_f_inl1_hrd0/gBridgeKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.sse4_f_inl1_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.sse4_f_inl1_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.sse4_f_inl1_hrd0/gCrossSectionKernels.o
-mkdir -p ../lib/build.sse4_f_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.sse4_f_inl1_hrd0/fbridge_cu.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.sse4_f_inl1_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.sse4_f_inl1_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.sse4_f_inl1_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.sse4_f_inl1_hrd0/check_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.sse4_f_inl1_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.sse4_f_inl1_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.sse4_f_inl1_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.sse4_f_inl1_hrd0/BridgeKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.sse4_f_inl1_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.sse4_f_inl1_hrd0/fbridge.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.sse4_f_inl1_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.sse4_f_inl1_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.sse4_f_inl1_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.sse4_f_inl1_hrd0/testxxx_cu.o
+mkdir -p ../lib/build.sse4_f_inl1_hrd0
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.sse4_f_inl1_hrd0/Parameters_sm.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.sse4_f_inl1_hrd0/read_slha.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.sse4_f_inl1_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.sse4_f_inl1_hrd0/testmisc.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.sse4_f_inl1_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.sse4_f_inl1_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.sse4_f_inl1_hrd0/testmisc_cu.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.sse4_f_inl1_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.sse4_f_inl1_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.sse4_f_inl1_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.sse4_f_inl1_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.sse4_f_inl1_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.sse4_f_inl1_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.sse4_f_inl1_hrd0/libmg5amc_common.so build.sse4_f_inl1_hrd0/Parameters_sm.o build.sse4_f_inl1_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.sse4_f_inl1_hrd0/libmg5amc_gg_ttxg_cuda.so build.sse4_f_inl1_hrd0/gCPPProcess.o build.sse4_f_inl1_hrd0/gMatrixElementKernels.o build.sse4_f_inl1_hrd0/gBridgeKernels.o build.sse4_f_inl1_hrd0/gCrossSectionKernels.o build.sse4_f_inl1_hrd0/fbridge_cu.o -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.sse4_f_inl1_hrd0/libmg5amc_gg_ttxg_cpp.so build.sse4_f_inl1_hrd0/CPPProcess.o build.sse4_f_inl1_hrd0/MatrixElementKernels.o build.sse4_f_inl1_hrd0/BridgeKernels.o build.sse4_f_inl1_hrd0/CrossSectionKernels.o build.sse4_f_inl1_hrd0/fbridge.o -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl1_hrd0/runTest.exe build.sse4_f_inl1_hrd0/CPPProcess.o build.sse4_f_inl1_hrd0/MatrixElementKernels.o build.sse4_f_inl1_hrd0/BridgeKernels.o build.sse4_f_inl1_hrd0/CrossSectionKernels.o build.sse4_f_inl1_hrd0/RandomNumberKernels.o build.sse4_f_inl1_hrd0/RamboSamplingKernels.o build.sse4_f_inl1_hrd0/testxxx.o  build.sse4_f_inl1_hrd0/testmisc.o  build.sse4_f_inl1_hrd0/runTest.o build.sse4_f_inl1_hrd0/gCPPProcess.o build.sse4_f_inl1_hrd0/gMatrixElementKernels.o build.sse4_f_inl1_hrd0/gBridgeKernels.o build.sse4_f_inl1_hrd0/gCrossSectionKernels.o build.sse4_f_inl1_hrd0/gRandomNumberKernels.o build.sse4_f_inl1_hrd0/gRamboSamplingKernels.o build.sse4_f_inl1_hrd0/testxxx_cu.o  build.sse4_f_inl1_hrd0/testmisc_cu.o  build.sse4_f_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_f_inl1_hrd0/check.exe build.sse4_f_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_gg_ttxg_cpp build.sse4_f_inl1_hrd0/RandomNumberKernels.o build.sse4_f_inl1_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_f_inl1_hrd0/fcheck.exe build.sse4_f_inl1_hrd0/fcheck_sa.o build.sse4_f_inl1_hrd0/fsampler.o -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_gg_ttxg_cpp build.sse4_f_inl1_hrd0/RandomNumberKernels.o build.sse4_f_inl1_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl1_hrd0/gcheck.exe build.sse4_f_inl1_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_gg_ttxg_cuda build.sse4_f_inl1_hrd0/gRandomNumberKernels.o build.sse4_f_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl1_hrd0/fgcheck.exe build.sse4_f_inl1_hrd0/fcheck_sa.o build.sse4_f_inl1_hrd0/fsampler_cu.o -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_gg_ttxg_cuda build.sse4_f_inl1_hrd0/gRandomNumberKernels.o build.sse4_f_inl1_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.sse4_f_inl1_hrd0/libmg5amc_gg_ttxg_cuda.so build.sse4_f_inl1_hrd0/gCPPProcess.o build.sse4_f_inl1_hrd0/gMatrixElementKernels.o build.sse4_f_inl1_hrd0/gBridgeKernels.o build.sse4_f_inl1_hrd0/gCrossSectionKernels.o build.sse4_f_inl1_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl1_hrd0/gcheck.exe build.sse4_f_inl1_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl1_hrd0'  -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_gg_ttxg_cuda build.sse4_f_inl1_hrd0/gRandomNumberKernels.o build.sse4_f_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl1_hrd0/fgcheck.exe build.sse4_f_inl1_hrd0/fcheck_sa.o build.sse4_f_inl1_hrd0/fsampler_cu.o -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl1_hrd0'  -lgfortran -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_gg_ttxg_cuda build.sse4_f_inl1_hrd0/gRandomNumberKernels.o build.sse4_f_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.sse4_f_inl1_hrd0/libmg5amc_gg_ttxg_cpp.so build.sse4_f_inl1_hrd0/CPPProcess.o build.sse4_f_inl1_hrd0/MatrixElementKernels.o build.sse4_f_inl1_hrd0/BridgeKernels.o build.sse4_f_inl1_hrd0/CrossSectionKernels.o build.sse4_f_inl1_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl1_hrd0/runTest.exe build.sse4_f_inl1_hrd0/CPPProcess.o build.sse4_f_inl1_hrd0/MatrixElementKernels.o build.sse4_f_inl1_hrd0/BridgeKernels.o build.sse4_f_inl1_hrd0/CrossSectionKernels.o build.sse4_f_inl1_hrd0/RandomNumberKernels.o build.sse4_f_inl1_hrd0/RamboSamplingKernels.o build.sse4_f_inl1_hrd0/testxxx.o  build.sse4_f_inl1_hrd0/testmisc.o  build.sse4_f_inl1_hrd0/runTest.o build.sse4_f_inl1_hrd0/gCPPProcess.o build.sse4_f_inl1_hrd0/gMatrixElementKernels.o build.sse4_f_inl1_hrd0/gBridgeKernels.o build.sse4_f_inl1_hrd0/gCrossSectionKernels.o build.sse4_f_inl1_hrd0/gRandomNumberKernels.o build.sse4_f_inl1_hrd0/gRamboSamplingKernels.o build.sse4_f_inl1_hrd0/testxxx_cu.o  build.sse4_f_inl1_hrd0/testmisc_cu.o  build.sse4_f_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl1_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_f_inl1_hrd0/check.exe build.sse4_f_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_f_inl1_hrd0'  -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_gg_ttxg_cpp build.sse4_f_inl1_hrd0/RandomNumberKernels.o build.sse4_f_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_f_inl1_hrd0/fcheck.exe build.sse4_f_inl1_hrd0/fcheck_sa.o build.sse4_f_inl1_hrd0/fsampler.o -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_f_inl1_hrd0'  -lgfortran -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_gg_ttxg_cpp build.sse4_f_inl1_hrd0/RandomNumberKernels.o build.sse4_f_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
 touch build.sse4_f_inl1_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_f_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.sse4_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_f_inl1_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_f_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.sse4_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_f_inl1_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.sse4_f_inl1_hrd0/libmg5amc_gg_ttxg_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_f_inl1_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.sse4_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_f_inl1_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:06:28
+DATE: 2022-09-25_00:09:18
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_f_inl1_hrd0/check.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_f_inl1_hrd0/check.exe -p 64 256 20 OMP=
 Process                     = SIGMA_SM_GG_TTXG_CPP [gcc 11.2.0] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CPP:FLT+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK
 FP precision                = FLOAT (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 8.421089e+04                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 8.704277e+04                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 8.704277e+04                 )  sec^-1
-MeanMatrixElemValue         = ( 2.361139e+02 +- 1.906746e+02 )  GeV^-2
-TOTAL       :     0.395581 sec
-real	0m0.402s
+EvtsPerSec[Rmb+ME]     (23) = ( 8.440614e+04                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 8.721548e+04                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 8.721548e+04                 )  sec^-1
+MeanMatrixElemValue         = ( 4.105004e+02 +- 2.728381e+02 )  GeV^-2
+TOTAL       :     3.917344 sec
+real	0m3.924s
 =Symbols in CPPProcess.o= (~sse4:11317) (avx2:    0) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_f_inl1_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_f_inl1_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_f_inl1_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_f_inl1_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 1.413065e+00
 Avg ME (F77/C++)    = 1.4130651236732490
 Relative difference = 8.752127395067397e-08
@@ -5316,13 +5368,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:06:31 CEST 2022 Will execute './throughputX.sh -makej -ggttg -avx2only  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:09:37 CEST 2022 Will execute './throughputX.sh -makej -ggttg -avx2only  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -avx2only implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
 CUDACPP_BUILDDIR='build.avx2_d_inl0_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -5332,71 +5384,72 @@ HELINL=0
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.avx2_d_inl0_hrd0 for tag=avx2_d_inl0_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.avx2_d_inl0_hrd0
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gcheck_sa.cu -o build.avx2_d_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gCPPProcess.cu -o build.avx2_d_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.avx2_d_inl0_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gBridgeKernels.cu -o build.avx2_d_inl0_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.avx2_d_inl0_hrd0/gCrossSectionKernels.o
 AVX=avx2
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gcheck_sa.cu -o build.avx2_d_inl0_hrd0/gcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gCPPProcess.cu -o build.avx2_d_inl0_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.avx2_d_inl0_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gBridgeKernels.cu -o build.avx2_d_inl0_hrd0/gBridgeKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.avx2_d_inl0_hrd0/gCrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -c read_slha.cc -o build.avx2_d_inl0_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fbridge.cc -o build.avx2_d_inl0_hrd0/fbridge_cu.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -c Parameters_sm.cc -o build.avx2_d_inl0_hrd0/Parameters_sm.o
-mkdir -p ../lib/build.avx2_d_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.avx2_d_inl0_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.avx2_d_inl0_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fbridge.cc -o build.avx2_d_inl0_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.avx2_d_inl0_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.avx2_d_inl0_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.avx2_d_inl0_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.avx2_d_inl0_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.avx2_d_inl0_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.avx2_d_inl0_hrd0/BridgeKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.avx2_d_inl0_hrd0/libmg5amc_common.so build.avx2_d_inl0_hrd0/Parameters_sm.o build.avx2_d_inl0_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.avx2_d_inl0_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.avx2_d_inl0_hrd0/fbridge.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.avx2_d_inl0_hrd0/RandomNumberKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.avx2_d_inl0_hrd0/RamboSamplingKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -c Parameters_sm.cc -o build.avx2_d_inl0_hrd0/Parameters_sm.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -c read_slha.cc -o build.avx2_d_inl0_hrd0/read_slha.o
+mkdir -p ../lib/build.avx2_d_inl0_hrd0
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.avx2_d_inl0_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testxxx.cc -o build.avx2_d_inl0_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testxxx.cc -o build.avx2_d_inl0_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.avx2_d_inl0_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testmisc.cc -o build.avx2_d_inl0_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testmisc.cc -o build.avx2_d_inl0_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.avx2_d_inl0_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu runTest.cc -o build.avx2_d_inl0_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu runTest.cc -o build.avx2_d_inl0_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.avx2_d_inl0_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fsampler.cc -o build.avx2_d_inl0_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fsampler.cc -o build.avx2_d_inl0_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.avx2_d_inl0_hrd0/fsampler.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.avx2_d_inl0_hrd0/libmg5amc_gg_ttxg_cuda.so build.avx2_d_inl0_hrd0/gCPPProcess.o build.avx2_d_inl0_hrd0/gMatrixElementKernels.o build.avx2_d_inl0_hrd0/gBridgeKernels.o build.avx2_d_inl0_hrd0/gCrossSectionKernels.o build.avx2_d_inl0_hrd0/fbridge_cu.o -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.avx2_d_inl0_hrd0/libmg5amc_gg_ttxg_cpp.so build.avx2_d_inl0_hrd0/CPPProcess.o build.avx2_d_inl0_hrd0/MatrixElementKernels.o build.avx2_d_inl0_hrd0/BridgeKernels.o build.avx2_d_inl0_hrd0/CrossSectionKernels.o build.avx2_d_inl0_hrd0/fbridge.o -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl0_hrd0/runTest.exe build.avx2_d_inl0_hrd0/CPPProcess.o build.avx2_d_inl0_hrd0/MatrixElementKernels.o build.avx2_d_inl0_hrd0/BridgeKernels.o build.avx2_d_inl0_hrd0/CrossSectionKernels.o build.avx2_d_inl0_hrd0/RandomNumberKernels.o build.avx2_d_inl0_hrd0/RamboSamplingKernels.o build.avx2_d_inl0_hrd0/testxxx.o  build.avx2_d_inl0_hrd0/testmisc.o  build.avx2_d_inl0_hrd0/runTest.o build.avx2_d_inl0_hrd0/gCPPProcess.o build.avx2_d_inl0_hrd0/gMatrixElementKernels.o build.avx2_d_inl0_hrd0/gBridgeKernels.o build.avx2_d_inl0_hrd0/gCrossSectionKernels.o build.avx2_d_inl0_hrd0/gRandomNumberKernels.o build.avx2_d_inl0_hrd0/gRamboSamplingKernels.o build.avx2_d_inl0_hrd0/testxxx_cu.o  build.avx2_d_inl0_hrd0/testmisc_cu.o  build.avx2_d_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_d_inl0_hrd0/check.exe build.avx2_d_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_gg_ttxg_cpp build.avx2_d_inl0_hrd0/RandomNumberKernels.o build.avx2_d_inl0_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_d_inl0_hrd0/fcheck.exe build.avx2_d_inl0_hrd0/fcheck_sa.o build.avx2_d_inl0_hrd0/fsampler.o -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_gg_ttxg_cpp build.avx2_d_inl0_hrd0/RandomNumberKernels.o build.avx2_d_inl0_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl0_hrd0/gcheck.exe build.avx2_d_inl0_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_gg_ttxg_cuda build.avx2_d_inl0_hrd0/gRandomNumberKernels.o build.avx2_d_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl0_hrd0/fgcheck.exe build.avx2_d_inl0_hrd0/fcheck_sa.o build.avx2_d_inl0_hrd0/fsampler_cu.o -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_gg_ttxg_cuda build.avx2_d_inl0_hrd0/gRandomNumberKernels.o build.avx2_d_inl0_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.avx2_d_inl0_hrd0/libmg5amc_common.so build.avx2_d_inl0_hrd0/Parameters_sm.o build.avx2_d_inl0_hrd0/read_slha.o
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.avx2_d_inl0_hrd0/libmg5amc_gg_ttxg_cuda.so build.avx2_d_inl0_hrd0/gCPPProcess.o build.avx2_d_inl0_hrd0/gMatrixElementKernels.o build.avx2_d_inl0_hrd0/gBridgeKernels.o build.avx2_d_inl0_hrd0/gCrossSectionKernels.o build.avx2_d_inl0_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.avx2_d_inl0_hrd0/libmg5amc_gg_ttxg_cpp.so build.avx2_d_inl0_hrd0/CPPProcess.o build.avx2_d_inl0_hrd0/MatrixElementKernels.o build.avx2_d_inl0_hrd0/BridgeKernels.o build.avx2_d_inl0_hrd0/CrossSectionKernels.o build.avx2_d_inl0_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_d_inl0_hrd0/fcheck.exe build.avx2_d_inl0_hrd0/fcheck_sa.o build.avx2_d_inl0_hrd0/fsampler.o -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_d_inl0_hrd0'  -lgfortran -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_gg_ttxg_cpp build.avx2_d_inl0_hrd0/RandomNumberKernels.o build.avx2_d_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl0_hrd0/gcheck.exe build.avx2_d_inl0_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl0_hrd0'  -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_gg_ttxg_cuda build.avx2_d_inl0_hrd0/gRandomNumberKernels.o build.avx2_d_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl0_hrd0/fgcheck.exe build.avx2_d_inl0_hrd0/fcheck_sa.o build.avx2_d_inl0_hrd0/fsampler_cu.o -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl0_hrd0'  -lgfortran -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_gg_ttxg_cuda build.avx2_d_inl0_hrd0/gRandomNumberKernels.o build.avx2_d_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_d_inl0_hrd0/check.exe build.avx2_d_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_d_inl0_hrd0'  -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_gg_ttxg_cpp build.avx2_d_inl0_hrd0/RandomNumberKernels.o build.avx2_d_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl0_hrd0/runTest.exe build.avx2_d_inl0_hrd0/CPPProcess.o build.avx2_d_inl0_hrd0/MatrixElementKernels.o build.avx2_d_inl0_hrd0/BridgeKernels.o build.avx2_d_inl0_hrd0/CrossSectionKernels.o build.avx2_d_inl0_hrd0/RandomNumberKernels.o build.avx2_d_inl0_hrd0/RamboSamplingKernels.o build.avx2_d_inl0_hrd0/testxxx.o  build.avx2_d_inl0_hrd0/testmisc.o  build.avx2_d_inl0_hrd0/runTest.o build.avx2_d_inl0_hrd0/gCPPProcess.o build.avx2_d_inl0_hrd0/gMatrixElementKernels.o build.avx2_d_inl0_hrd0/gBridgeKernels.o build.avx2_d_inl0_hrd0/gCrossSectionKernels.o build.avx2_d_inl0_hrd0/gRandomNumberKernels.o build.avx2_d_inl0_hrd0/gRamboSamplingKernels.o build.avx2_d_inl0_hrd0/testxxx_cu.o  build.avx2_d_inl0_hrd0/testmisc_cu.o  build.avx2_d_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl0_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
 touch build.avx2_d_inl0_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_d_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.avx2_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_d_inl0_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_d_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.avx2_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_d_inl0_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.avx2_d_inl0_hrd0/libmg5amc_gg_ttxg_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_d_inl0_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.avx2_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_d_inl0_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:06:32
+DATE: 2022-09-25_00:09:47
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_d_inl0_hrd0/check.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_d_inl0_hrd0/check.exe -p 64 256 20 OMP=
 Process                     = SIGMA_SM_GG_TTXG_CPP [gcc 11.2.0] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CPP:DBL+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 8.389138e+04                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 8.729928e+04                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 8.729928e+04                 )  sec^-1
-MeanMatrixElemValue         = ( 2.360828e+02 +- 1.906418e+02 )  GeV^-2
-TOTAL       :     0.399193 sec
-real	0m0.406s
+EvtsPerSec[Rmb+ME]     (23) = ( 8.399688e+04                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 8.735905e+04                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 8.735905e+04                 )  sec^-1
+MeanMatrixElemValue         = ( 4.103783e+02 +- 2.727382e+02 )  GeV^-2
+TOTAL       :     3.942075 sec
+real	0m3.949s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2: 4086) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_d_inl0_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_d_inl0_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_d_inl0_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_d_inl0_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 1.413122e+00
 Avg ME (F77/C++)    = 1.4131213684416470
 Relative difference = 4.469241530088324e-07
@@ -5404,13 +5457,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:06:35 CEST 2022 Will execute './throughputX.sh -makej -ggttg -avx2only  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:10:06 CEST 2022 Will execute './throughputX.sh -makej -ggttg -avx2only  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -avx2only implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
 CUDACPP_BUILDDIR='build.avx2_d_inl1_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -5420,71 +5473,72 @@ HELINL=1
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.avx2_d_inl1_hrd0 for tag=avx2_d_inl1_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.avx2_d_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.avx2_d_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.avx2_d_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.avx2_d_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.avx2_d_inl1_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.avx2_d_inl1_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.avx2_d_inl1_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.avx2_d_inl1_hrd0/fbridge_cu.o
 AVX=avx2
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.avx2_d_inl1_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.avx2_d_inl1_hrd0/gMatrixElementKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.avx2_d_inl1_hrd0/gBridgeKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.avx2_d_inl1_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.avx2_d_inl1_hrd0/read_slha.o
-mkdir -p ../lib/build.avx2_d_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.avx2_d_inl1_hrd0/gCrossSectionKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.avx2_d_inl1_hrd0/fbridge_cu.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.avx2_d_inl1_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.avx2_d_inl1_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.avx2_d_inl1_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.avx2_d_inl1_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.avx2_d_inl1_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.avx2_d_inl1_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.avx2_d_inl1_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.avx2_d_inl1_hrd0/BridgeKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.avx2_d_inl1_hrd0/CrossSectionKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.avx2_d_inl1_hrd0/fbridge.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.avx2_d_inl1_hrd0/Parameters_sm.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.avx2_d_inl1_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.avx2_d_inl1_hrd0/RamboSamplingKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.avx2_d_inl1_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.avx2_d_inl1_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.avx2_d_inl1_hrd0/testxxx_cu.o
+mkdir -p ../lib/build.avx2_d_inl1_hrd0
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.avx2_d_inl1_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.avx2_d_inl1_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.avx2_d_inl1_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.avx2_d_inl1_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.avx2_d_inl1_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.avx2_d_inl1_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.avx2_d_inl1_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.avx2_d_inl1_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.avx2_d_inl1_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.avx2_d_inl1_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.avx2_d_inl1_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.avx2_d_inl1_hrd0/libmg5amc_common.so build.avx2_d_inl1_hrd0/Parameters_sm.o build.avx2_d_inl1_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.avx2_d_inl1_hrd0/libmg5amc_gg_ttxg_cuda.so build.avx2_d_inl1_hrd0/gCPPProcess.o build.avx2_d_inl1_hrd0/gMatrixElementKernels.o build.avx2_d_inl1_hrd0/gBridgeKernels.o build.avx2_d_inl1_hrd0/gCrossSectionKernels.o build.avx2_d_inl1_hrd0/fbridge_cu.o -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.avx2_d_inl1_hrd0/libmg5amc_gg_ttxg_cpp.so build.avx2_d_inl1_hrd0/CPPProcess.o build.avx2_d_inl1_hrd0/MatrixElementKernels.o build.avx2_d_inl1_hrd0/BridgeKernels.o build.avx2_d_inl1_hrd0/CrossSectionKernels.o build.avx2_d_inl1_hrd0/fbridge.o -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl1_hrd0/runTest.exe build.avx2_d_inl1_hrd0/CPPProcess.o build.avx2_d_inl1_hrd0/MatrixElementKernels.o build.avx2_d_inl1_hrd0/BridgeKernels.o build.avx2_d_inl1_hrd0/CrossSectionKernels.o build.avx2_d_inl1_hrd0/RandomNumberKernels.o build.avx2_d_inl1_hrd0/RamboSamplingKernels.o build.avx2_d_inl1_hrd0/testxxx.o  build.avx2_d_inl1_hrd0/testmisc.o  build.avx2_d_inl1_hrd0/runTest.o build.avx2_d_inl1_hrd0/gCPPProcess.o build.avx2_d_inl1_hrd0/gMatrixElementKernels.o build.avx2_d_inl1_hrd0/gBridgeKernels.o build.avx2_d_inl1_hrd0/gCrossSectionKernels.o build.avx2_d_inl1_hrd0/gRandomNumberKernels.o build.avx2_d_inl1_hrd0/gRamboSamplingKernels.o build.avx2_d_inl1_hrd0/testxxx_cu.o  build.avx2_d_inl1_hrd0/testmisc_cu.o  build.avx2_d_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_d_inl1_hrd0/check.exe build.avx2_d_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_gg_ttxg_cpp build.avx2_d_inl1_hrd0/RandomNumberKernels.o build.avx2_d_inl1_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_d_inl1_hrd0/fcheck.exe build.avx2_d_inl1_hrd0/fcheck_sa.o build.avx2_d_inl1_hrd0/fsampler.o -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_gg_ttxg_cpp build.avx2_d_inl1_hrd0/RandomNumberKernels.o build.avx2_d_inl1_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl1_hrd0/gcheck.exe build.avx2_d_inl1_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_gg_ttxg_cuda build.avx2_d_inl1_hrd0/gRandomNumberKernels.o build.avx2_d_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl1_hrd0/fgcheck.exe build.avx2_d_inl1_hrd0/fcheck_sa.o build.avx2_d_inl1_hrd0/fsampler_cu.o -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_gg_ttxg_cuda build.avx2_d_inl1_hrd0/gRandomNumberKernels.o build.avx2_d_inl1_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.avx2_d_inl1_hrd0/libmg5amc_gg_ttxg_cuda.so build.avx2_d_inl1_hrd0/gCPPProcess.o build.avx2_d_inl1_hrd0/gMatrixElementKernels.o build.avx2_d_inl1_hrd0/gBridgeKernels.o build.avx2_d_inl1_hrd0/gCrossSectionKernels.o build.avx2_d_inl1_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl1_hrd0/gcheck.exe build.avx2_d_inl1_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl1_hrd0'  -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_gg_ttxg_cuda build.avx2_d_inl1_hrd0/gRandomNumberKernels.o build.avx2_d_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl1_hrd0/fgcheck.exe build.avx2_d_inl1_hrd0/fcheck_sa.o build.avx2_d_inl1_hrd0/fsampler_cu.o -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl1_hrd0'  -lgfortran -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_gg_ttxg_cuda build.avx2_d_inl1_hrd0/gRandomNumberKernels.o build.avx2_d_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.avx2_d_inl1_hrd0/libmg5amc_gg_ttxg_cpp.so build.avx2_d_inl1_hrd0/CPPProcess.o build.avx2_d_inl1_hrd0/MatrixElementKernels.o build.avx2_d_inl1_hrd0/BridgeKernels.o build.avx2_d_inl1_hrd0/CrossSectionKernels.o build.avx2_d_inl1_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_d_inl1_hrd0/check.exe build.avx2_d_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_d_inl1_hrd0'  -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_gg_ttxg_cpp build.avx2_d_inl1_hrd0/RandomNumberKernels.o build.avx2_d_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_d_inl1_hrd0/fcheck.exe build.avx2_d_inl1_hrd0/fcheck_sa.o build.avx2_d_inl1_hrd0/fsampler.o -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_d_inl1_hrd0'  -lgfortran -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_gg_ttxg_cpp build.avx2_d_inl1_hrd0/RandomNumberKernels.o build.avx2_d_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl1_hrd0/runTest.exe build.avx2_d_inl1_hrd0/CPPProcess.o build.avx2_d_inl1_hrd0/MatrixElementKernels.o build.avx2_d_inl1_hrd0/BridgeKernels.o build.avx2_d_inl1_hrd0/CrossSectionKernels.o build.avx2_d_inl1_hrd0/RandomNumberKernels.o build.avx2_d_inl1_hrd0/RamboSamplingKernels.o build.avx2_d_inl1_hrd0/testxxx.o  build.avx2_d_inl1_hrd0/testmisc.o  build.avx2_d_inl1_hrd0/runTest.o build.avx2_d_inl1_hrd0/gCPPProcess.o build.avx2_d_inl1_hrd0/gMatrixElementKernels.o build.avx2_d_inl1_hrd0/gBridgeKernels.o build.avx2_d_inl1_hrd0/gCrossSectionKernels.o build.avx2_d_inl1_hrd0/gRandomNumberKernels.o build.avx2_d_inl1_hrd0/gRamboSamplingKernels.o build.avx2_d_inl1_hrd0/testxxx_cu.o  build.avx2_d_inl1_hrd0/testmisc_cu.o  build.avx2_d_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl1_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
 touch build.avx2_d_inl1_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_d_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.avx2_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_d_inl1_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_d_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.avx2_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_d_inl1_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.avx2_d_inl1_hrd0/libmg5amc_gg_ttxg_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_d_inl1_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.avx2_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_d_inl1_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:06:37
+DATE: 2022-09-25_00:10:13
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_d_inl1_hrd0/check.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_d_inl1_hrd0/check.exe -p 64 256 20 OMP=
 Process                     = SIGMA_SM_GG_TTXG_CPP [gcc 11.2.0] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CPP:DBL+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 7.771407e+04                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 8.064271e+04                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 8.064271e+04                 )  sec^-1
-MeanMatrixElemValue         = ( 2.360828e+02 +- 1.906418e+02 )  GeV^-2
-TOTAL       :     0.430325 sec
-real	0m0.437s
+EvtsPerSec[Rmb+ME]     (23) = ( 7.799938e+04                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 8.087989e+04                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 8.087989e+04                 )  sec^-1
+MeanMatrixElemValue         = ( 4.103783e+02 +- 2.727382e+02 )  GeV^-2
+TOTAL       :     4.242149 sec
+real	0m4.249s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2: 7827) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_d_inl1_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_d_inl1_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_d_inl1_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_d_inl1_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 1.413122e+00
 Avg ME (F77/C++)    = 1.4131213684417272
 Relative difference = 4.4692409628471204e-07
@@ -5492,13 +5546,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:06:39 CEST 2022 Will execute './throughputX.sh -makej -ggttg -avx2only -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:10:32 CEST 2022 Will execute './throughputX.sh -makej -ggttg -avx2only -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -avx2only implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
 CUDACPP_BUILDDIR='build.avx2_f_inl0_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -5508,71 +5562,72 @@ HELINL=0
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.avx2_f_inl0_hrd0 for tag=avx2_f_inl0_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.avx2_f_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gcheck_sa.cu -o build.avx2_f_inl0_hrd0/gcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gCPPProcess.cu -o build.avx2_f_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gcheck_sa.cu -o build.avx2_f_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gCPPProcess.cu -o build.avx2_f_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.avx2_f_inl0_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gBridgeKernels.cu -o build.avx2_f_inl0_hrd0/gBridgeKernels.o
 AVX=avx2
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.avx2_f_inl0_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gBridgeKernels.cu -o build.avx2_f_inl0_hrd0/gBridgeKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.avx2_f_inl0_hrd0/gCrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -c Parameters_sm.cc -o build.avx2_f_inl0_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -c read_slha.cc -o build.avx2_f_inl0_hrd0/read_slha.o
-mkdir -p ../lib/build.avx2_f_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fbridge.cc -o build.avx2_f_inl0_hrd0/fbridge_cu.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.avx2_f_inl0_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.avx2_f_inl0_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.avx2_f_inl0_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fbridge.cc -o build.avx2_f_inl0_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.avx2_f_inl0_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.avx2_f_inl0_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.avx2_f_inl0_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.avx2_f_inl0_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.avx2_f_inl0_hrd0/MatrixElementKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.avx2_f_inl0_hrd0/BridgeKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -c Parameters_sm.cc -o build.avx2_f_inl0_hrd0/Parameters_sm.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.avx2_f_inl0_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.avx2_f_inl0_hrd0/fbridge.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -c read_slha.cc -o build.avx2_f_inl0_hrd0/read_slha.o
+mkdir -p ../lib/build.avx2_f_inl0_hrd0
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.avx2_f_inl0_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.avx2_f_inl0_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.avx2_f_inl0_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testxxx.cc -o build.avx2_f_inl0_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testxxx.cc -o build.avx2_f_inl0_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.avx2_f_inl0_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testmisc.cc -o build.avx2_f_inl0_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testmisc.cc -o build.avx2_f_inl0_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.avx2_f_inl0_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu runTest.cc -o build.avx2_f_inl0_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu runTest.cc -o build.avx2_f_inl0_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.avx2_f_inl0_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fsampler.cc -o build.avx2_f_inl0_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fsampler.cc -o build.avx2_f_inl0_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.avx2_f_inl0_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.avx2_f_inl0_hrd0/libmg5amc_common.so build.avx2_f_inl0_hrd0/Parameters_sm.o build.avx2_f_inl0_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.avx2_f_inl0_hrd0/libmg5amc_gg_ttxg_cuda.so build.avx2_f_inl0_hrd0/gCPPProcess.o build.avx2_f_inl0_hrd0/gMatrixElementKernels.o build.avx2_f_inl0_hrd0/gBridgeKernels.o build.avx2_f_inl0_hrd0/gCrossSectionKernels.o build.avx2_f_inl0_hrd0/fbridge_cu.o -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.avx2_f_inl0_hrd0/libmg5amc_gg_ttxg_cpp.so build.avx2_f_inl0_hrd0/CPPProcess.o build.avx2_f_inl0_hrd0/MatrixElementKernels.o build.avx2_f_inl0_hrd0/BridgeKernels.o build.avx2_f_inl0_hrd0/CrossSectionKernels.o build.avx2_f_inl0_hrd0/fbridge.o -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl0_hrd0/runTest.exe build.avx2_f_inl0_hrd0/CPPProcess.o build.avx2_f_inl0_hrd0/MatrixElementKernels.o build.avx2_f_inl0_hrd0/BridgeKernels.o build.avx2_f_inl0_hrd0/CrossSectionKernels.o build.avx2_f_inl0_hrd0/RandomNumberKernels.o build.avx2_f_inl0_hrd0/RamboSamplingKernels.o build.avx2_f_inl0_hrd0/testxxx.o  build.avx2_f_inl0_hrd0/testmisc.o  build.avx2_f_inl0_hrd0/runTest.o build.avx2_f_inl0_hrd0/gCPPProcess.o build.avx2_f_inl0_hrd0/gMatrixElementKernels.o build.avx2_f_inl0_hrd0/gBridgeKernels.o build.avx2_f_inl0_hrd0/gCrossSectionKernels.o build.avx2_f_inl0_hrd0/gRandomNumberKernels.o build.avx2_f_inl0_hrd0/gRamboSamplingKernels.o build.avx2_f_inl0_hrd0/testxxx_cu.o  build.avx2_f_inl0_hrd0/testmisc_cu.o  build.avx2_f_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_f_inl0_hrd0/check.exe build.avx2_f_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_gg_ttxg_cpp build.avx2_f_inl0_hrd0/RandomNumberKernels.o build.avx2_f_inl0_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_f_inl0_hrd0/fcheck.exe build.avx2_f_inl0_hrd0/fcheck_sa.o build.avx2_f_inl0_hrd0/fsampler.o -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_gg_ttxg_cpp build.avx2_f_inl0_hrd0/RandomNumberKernels.o build.avx2_f_inl0_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl0_hrd0/gcheck.exe build.avx2_f_inl0_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_gg_ttxg_cuda build.avx2_f_inl0_hrd0/gRandomNumberKernels.o build.avx2_f_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl0_hrd0/fgcheck.exe build.avx2_f_inl0_hrd0/fcheck_sa.o build.avx2_f_inl0_hrd0/fsampler_cu.o -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_gg_ttxg_cuda build.avx2_f_inl0_hrd0/gRandomNumberKernels.o build.avx2_f_inl0_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.avx2_f_inl0_hrd0/libmg5amc_gg_ttxg_cuda.so build.avx2_f_inl0_hrd0/gCPPProcess.o build.avx2_f_inl0_hrd0/gMatrixElementKernels.o build.avx2_f_inl0_hrd0/gBridgeKernels.o build.avx2_f_inl0_hrd0/gCrossSectionKernels.o build.avx2_f_inl0_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.avx2_f_inl0_hrd0/libmg5amc_gg_ttxg_cpp.so build.avx2_f_inl0_hrd0/CPPProcess.o build.avx2_f_inl0_hrd0/MatrixElementKernels.o build.avx2_f_inl0_hrd0/BridgeKernels.o build.avx2_f_inl0_hrd0/CrossSectionKernels.o build.avx2_f_inl0_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_f_inl0_hrd0/fcheck.exe build.avx2_f_inl0_hrd0/fcheck_sa.o build.avx2_f_inl0_hrd0/fsampler.o -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_f_inl0_hrd0'  -lgfortran -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_gg_ttxg_cpp build.avx2_f_inl0_hrd0/RandomNumberKernels.o build.avx2_f_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl0_hrd0/gcheck.exe build.avx2_f_inl0_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl0_hrd0'  -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_gg_ttxg_cuda build.avx2_f_inl0_hrd0/gRandomNumberKernels.o build.avx2_f_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl0_hrd0/fgcheck.exe build.avx2_f_inl0_hrd0/fcheck_sa.o build.avx2_f_inl0_hrd0/fsampler_cu.o -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl0_hrd0'  -lgfortran -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_gg_ttxg_cuda build.avx2_f_inl0_hrd0/gRandomNumberKernels.o build.avx2_f_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_f_inl0_hrd0/check.exe build.avx2_f_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_f_inl0_hrd0'  -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_gg_ttxg_cpp build.avx2_f_inl0_hrd0/RandomNumberKernels.o build.avx2_f_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl0_hrd0/runTest.exe build.avx2_f_inl0_hrd0/CPPProcess.o build.avx2_f_inl0_hrd0/MatrixElementKernels.o build.avx2_f_inl0_hrd0/BridgeKernels.o build.avx2_f_inl0_hrd0/CrossSectionKernels.o build.avx2_f_inl0_hrd0/RandomNumberKernels.o build.avx2_f_inl0_hrd0/RamboSamplingKernels.o build.avx2_f_inl0_hrd0/testxxx.o  build.avx2_f_inl0_hrd0/testmisc.o  build.avx2_f_inl0_hrd0/runTest.o build.avx2_f_inl0_hrd0/gCPPProcess.o build.avx2_f_inl0_hrd0/gMatrixElementKernels.o build.avx2_f_inl0_hrd0/gBridgeKernels.o build.avx2_f_inl0_hrd0/gCrossSectionKernels.o build.avx2_f_inl0_hrd0/gRandomNumberKernels.o build.avx2_f_inl0_hrd0/gRamboSamplingKernels.o build.avx2_f_inl0_hrd0/testxxx_cu.o  build.avx2_f_inl0_hrd0/testmisc_cu.o  build.avx2_f_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl0_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
 touch build.avx2_f_inl0_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_f_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.avx2_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_f_inl0_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_f_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.avx2_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_f_inl0_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.avx2_f_inl0_hrd0/libmg5amc_gg_ttxg_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_f_inl0_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.avx2_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_f_inl0_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:06:40
+DATE: 2022-09-25_00:10:43
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_f_inl0_hrd0/check.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_f_inl0_hrd0/check.exe -p 64 256 20 OMP=
 Process                     = SIGMA_SM_GG_TTXG_CPP [gcc 11.2.0] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CPP:FLT+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK
 FP precision                = FLOAT (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 1.633137e+05                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 1.741543e+05                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 1.741543e+05                 )  sec^-1
-MeanMatrixElemValue         = ( 2.361273e+02 +- 1.906833e+02 )  GeV^-2
-TOTAL       :     0.207237 sec
-real	0m0.214s
+EvtsPerSec[Rmb+ME]     (23) = ( 1.636913e+05                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 1.743659e+05                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 1.743659e+05                 )  sec^-1
+MeanMatrixElemValue         = ( 4.103219e+02 +- 2.726966e+02 )  GeV^-2
+TOTAL       :     2.039603 sec
+real	0m2.046s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2: 4385) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_f_inl0_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_f_inl0_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_f_inl0_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_f_inl0_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 1.413313e+00
 Avg ME (F77/C++)    = 1.4133134558441043
 Relative difference = 3.225358460873602e-07
@@ -5580,13 +5635,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:06:43 CEST 2022 Will execute './throughputX.sh -makej -ggttg -avx2only -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:11:00 CEST 2022 Will execute './throughputX.sh -makej -ggttg -avx2only -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -avx2only implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
 CUDACPP_BUILDDIR='build.avx2_f_inl1_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -5596,22 +5651,18 @@ HELINL=1
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.avx2_f_inl1_hrd0 for tag=avx2_f_inl1_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.avx2_f_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.avx2_f_inl1_hrd0/gcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.avx2_f_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.avx2_f_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.avx2_f_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.avx2_f_inl1_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.avx2_f_inl1_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.avx2_f_inl1_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.avx2_f_inl1_hrd0/fbridge_cu.o
 AVX=avx2
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.avx2_f_inl1_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.avx2_f_inl1_hrd0/gBridgeKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.avx2_f_inl1_hrd0/gCrossSectionKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.avx2_f_inl1_hrd0/fbridge_cu.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.avx2_f_inl1_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.avx2_f_inl1_hrd0/read_slha.o
-mkdir -p ../lib/build.avx2_f_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.avx2_f_inl1_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.avx2_f_inl1_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.avx2_f_inl1_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.avx2_f_inl1_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.avx2_f_inl1_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.avx2_f_inl1_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.avx2_f_inl1_hrd0/MatrixElementKernels.o
@@ -5619,48 +5670,53 @@ ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.avx2_f_inl1_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.avx2_f_inl1_hrd0/fbridge.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.avx2_f_inl1_hrd0/RandomNumberKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.avx2_f_inl1_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.avx2_f_inl1_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.avx2_f_inl1_hrd0/testxxx_cu.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.avx2_f_inl1_hrd0/Parameters_sm.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.avx2_f_inl1_hrd0/read_slha.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.avx2_f_inl1_hrd0/testxxx_cu.o
+mkdir -p ../lib/build.avx2_f_inl1_hrd0
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.avx2_f_inl1_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.avx2_f_inl1_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.avx2_f_inl1_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.avx2_f_inl1_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.avx2_f_inl1_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.avx2_f_inl1_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.avx2_f_inl1_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.avx2_f_inl1_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.avx2_f_inl1_hrd0/fsampler.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.avx2_f_inl1_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.avx2_f_inl1_hrd0/libmg5amc_common.so build.avx2_f_inl1_hrd0/Parameters_sm.o build.avx2_f_inl1_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.avx2_f_inl1_hrd0/libmg5amc_gg_ttxg_cuda.so build.avx2_f_inl1_hrd0/gCPPProcess.o build.avx2_f_inl1_hrd0/gMatrixElementKernels.o build.avx2_f_inl1_hrd0/gBridgeKernels.o build.avx2_f_inl1_hrd0/gCrossSectionKernels.o build.avx2_f_inl1_hrd0/fbridge_cu.o -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.avx2_f_inl1_hrd0/libmg5amc_gg_ttxg_cpp.so build.avx2_f_inl1_hrd0/CPPProcess.o build.avx2_f_inl1_hrd0/MatrixElementKernels.o build.avx2_f_inl1_hrd0/BridgeKernels.o build.avx2_f_inl1_hrd0/CrossSectionKernels.o build.avx2_f_inl1_hrd0/fbridge.o -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl1_hrd0/runTest.exe build.avx2_f_inl1_hrd0/CPPProcess.o build.avx2_f_inl1_hrd0/MatrixElementKernels.o build.avx2_f_inl1_hrd0/BridgeKernels.o build.avx2_f_inl1_hrd0/CrossSectionKernels.o build.avx2_f_inl1_hrd0/RandomNumberKernels.o build.avx2_f_inl1_hrd0/RamboSamplingKernels.o build.avx2_f_inl1_hrd0/testxxx.o  build.avx2_f_inl1_hrd0/testmisc.o  build.avx2_f_inl1_hrd0/runTest.o build.avx2_f_inl1_hrd0/gCPPProcess.o build.avx2_f_inl1_hrd0/gMatrixElementKernels.o build.avx2_f_inl1_hrd0/gBridgeKernels.o build.avx2_f_inl1_hrd0/gCrossSectionKernels.o build.avx2_f_inl1_hrd0/gRandomNumberKernels.o build.avx2_f_inl1_hrd0/gRamboSamplingKernels.o build.avx2_f_inl1_hrd0/testxxx_cu.o  build.avx2_f_inl1_hrd0/testmisc_cu.o  build.avx2_f_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_f_inl1_hrd0/check.exe build.avx2_f_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_gg_ttxg_cpp build.avx2_f_inl1_hrd0/RandomNumberKernels.o build.avx2_f_inl1_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_f_inl1_hrd0/fcheck.exe build.avx2_f_inl1_hrd0/fcheck_sa.o build.avx2_f_inl1_hrd0/fsampler.o -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_gg_ttxg_cpp build.avx2_f_inl1_hrd0/RandomNumberKernels.o build.avx2_f_inl1_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl1_hrd0/gcheck.exe build.avx2_f_inl1_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_gg_ttxg_cuda build.avx2_f_inl1_hrd0/gRandomNumberKernels.o build.avx2_f_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl1_hrd0/fgcheck.exe build.avx2_f_inl1_hrd0/fcheck_sa.o build.avx2_f_inl1_hrd0/fsampler_cu.o -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_gg_ttxg_cuda build.avx2_f_inl1_hrd0/gRandomNumberKernels.o build.avx2_f_inl1_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.avx2_f_inl1_hrd0/libmg5amc_gg_ttxg_cuda.so build.avx2_f_inl1_hrd0/gCPPProcess.o build.avx2_f_inl1_hrd0/gMatrixElementKernels.o build.avx2_f_inl1_hrd0/gBridgeKernels.o build.avx2_f_inl1_hrd0/gCrossSectionKernels.o build.avx2_f_inl1_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl1_hrd0/gcheck.exe build.avx2_f_inl1_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl1_hrd0'  -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_gg_ttxg_cuda build.avx2_f_inl1_hrd0/gRandomNumberKernels.o build.avx2_f_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl1_hrd0/fgcheck.exe build.avx2_f_inl1_hrd0/fcheck_sa.o build.avx2_f_inl1_hrd0/fsampler_cu.o -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl1_hrd0'  -lgfortran -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_gg_ttxg_cuda build.avx2_f_inl1_hrd0/gRandomNumberKernels.o build.avx2_f_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.avx2_f_inl1_hrd0/libmg5amc_gg_ttxg_cpp.so build.avx2_f_inl1_hrd0/CPPProcess.o build.avx2_f_inl1_hrd0/MatrixElementKernels.o build.avx2_f_inl1_hrd0/BridgeKernels.o build.avx2_f_inl1_hrd0/CrossSectionKernels.o build.avx2_f_inl1_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_f_inl1_hrd0/check.exe build.avx2_f_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_f_inl1_hrd0'  -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_gg_ttxg_cpp build.avx2_f_inl1_hrd0/RandomNumberKernels.o build.avx2_f_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_f_inl1_hrd0/fcheck.exe build.avx2_f_inl1_hrd0/fcheck_sa.o build.avx2_f_inl1_hrd0/fsampler.o -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_f_inl1_hrd0'  -lgfortran -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_gg_ttxg_cpp build.avx2_f_inl1_hrd0/RandomNumberKernels.o build.avx2_f_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl1_hrd0/runTest.exe build.avx2_f_inl1_hrd0/CPPProcess.o build.avx2_f_inl1_hrd0/MatrixElementKernels.o build.avx2_f_inl1_hrd0/BridgeKernels.o build.avx2_f_inl1_hrd0/CrossSectionKernels.o build.avx2_f_inl1_hrd0/RandomNumberKernels.o build.avx2_f_inl1_hrd0/RamboSamplingKernels.o build.avx2_f_inl1_hrd0/testxxx.o  build.avx2_f_inl1_hrd0/testmisc.o  build.avx2_f_inl1_hrd0/runTest.o build.avx2_f_inl1_hrd0/gCPPProcess.o build.avx2_f_inl1_hrd0/gMatrixElementKernels.o build.avx2_f_inl1_hrd0/gBridgeKernels.o build.avx2_f_inl1_hrd0/gCrossSectionKernels.o build.avx2_f_inl1_hrd0/gRandomNumberKernels.o build.avx2_f_inl1_hrd0/gRamboSamplingKernels.o build.avx2_f_inl1_hrd0/testxxx_cu.o  build.avx2_f_inl1_hrd0/testmisc_cu.o  build.avx2_f_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl1_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
 touch build.avx2_f_inl1_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_f_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.avx2_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_f_inl1_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_f_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.avx2_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_f_inl1_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.avx2_f_inl1_hrd0/libmg5amc_gg_ttxg_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_f_inl1_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.avx2_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_f_inl1_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:06:44
+DATE: 2022-09-25_00:11:07
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_f_inl1_hrd0/check.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_f_inl1_hrd0/check.exe -p 64 256 20 OMP=
 Process                     = SIGMA_SM_GG_TTXG_CPP [gcc 11.2.0] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CPP:FLT+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK
 FP precision                = FLOAT (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 1.331747e+05                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 1.402327e+05                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 1.402327e+05                 )  sec^-1
-MeanMatrixElemValue         = ( 2.361234e+02 +- 1.906766e+02 )  GeV^-2
-TOTAL       :     0.252636 sec
-real	0m0.259s
+EvtsPerSec[Rmb+ME]     (23) = ( 1.333834e+05                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 1.403720e+05                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 1.403720e+05                 )  sec^-1
+MeanMatrixElemValue         = ( 4.103258e+02 +- 2.726957e+02 )  GeV^-2
+TOTAL       :     2.494432 sec
+real	0m2.501s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2: 8982) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_f_inl1_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_f_inl1_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_f_inl1_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_f_inl1_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 1.413205e+00
 Avg ME (F77/C++)    = 1.4132052211958808
 Relative difference = 1.5652073175724815e-07
@@ -5668,35 +5724,35 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:06:47 CEST 2022 Will execute './throughputX.sh -makej -ggttg -512yonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:11:25 CEST 2022 Will execute './throughputX.sh -makej -ggttg -512yonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -512yonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
 CUDACPP_BUILDDIR='build.512y_d_inl0_hrd0'
 make: Nothing to be done for `all'.
 
-DATE: 2022-08-31_21:06:47
+DATE: 2022-09-25_00:11:25
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_d_inl0_hrd0/check.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_d_inl0_hrd0/check.exe -p 64 256 20 OMP=
 Process                     = SIGMA_SM_GG_TTXG_CPP [gcc 11.2.0] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 9.561836e+04                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 1.000389e+05                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 1.000389e+05                 )  sec^-1
-MeanMatrixElemValue         = ( 2.360828e+02 +- 1.906418e+02 )  GeV^-2
-TOTAL       :     0.351071 sec
-real	0m0.358s
+EvtsPerSec[Rmb+ME]     (23) = ( 9.573443e+04                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 1.000866e+05                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 1.000866e+05                 )  sec^-1
+MeanMatrixElemValue         = ( 4.103783e+02 +- 2.727382e+02 )  GeV^-2
+TOTAL       :     3.464200 sec
+real	0m3.471s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2: 3858) (512y:   22) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_d_inl0_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_d_inl0_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_d_inl0_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_d_inl0_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 1.413122e+00
 Avg ME (F77/C++)    = 1.4131213684416470
 Relative difference = 4.469241530088324e-07
@@ -5704,35 +5760,35 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:06:49 CEST 2022 Will execute './throughputX.sh -makej -ggttg -512yonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:11:44 CEST 2022 Will execute './throughputX.sh -makej -ggttg -512yonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -512yonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
 CUDACPP_BUILDDIR='build.512y_d_inl1_hrd0'
 make: Nothing to be done for `all'.
 
-DATE: 2022-08-31_21:06:49
+DATE: 2022-09-25_00:11:44
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_d_inl1_hrd0/check.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_d_inl1_hrd0/check.exe -p 64 256 20 OMP=
 Process                     = SIGMA_SM_GG_TTXG_CPP [gcc 11.2.0] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 8.544047e+04                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 8.893861e+04                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 8.893861e+04                 )  sec^-1
-MeanMatrixElemValue         = ( 2.360828e+02 +- 1.906418e+02 )  GeV^-2
-TOTAL       :     0.391953 sec
-real	0m0.399s
+EvtsPerSec[Rmb+ME]     (23) = ( 8.554833e+04                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 8.901841e+04                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 8.901841e+04                 )  sec^-1
+MeanMatrixElemValue         = ( 4.103783e+02 +- 2.727382e+02 )  GeV^-2
+TOTAL       :     3.871578 sec
+real	0m3.878s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2: 7321) (512y:  170) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_d_inl1_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_d_inl1_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_d_inl1_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_d_inl1_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 1.413122e+00
 Avg ME (F77/C++)    = 1.4131213684417272
 Relative difference = 4.4692409628471204e-07
@@ -5740,35 +5796,35 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:06:52 CEST 2022 Will execute './throughputX.sh -makej -ggttg -512yonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:12:03 CEST 2022 Will execute './throughputX.sh -makej -ggttg -512yonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -512yonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
 CUDACPP_BUILDDIR='build.512y_f_inl0_hrd0'
 make: Nothing to be done for `all'.
 
-DATE: 2022-08-31_21:06:52
+DATE: 2022-09-25_00:12:03
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_f_inl0_hrd0/check.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_f_inl0_hrd0/check.exe -p 64 256 20 OMP=
 Process                     = SIGMA_SM_GG_TTXG_CPP [gcc 11.2.0] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK
 FP precision                = FLOAT (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 1.834103e+05                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 1.973599e+05                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 1.973599e+05                 )  sec^-1
-MeanMatrixElemValue         = ( 2.361273e+02 +- 1.906833e+02 )  GeV^-2
-TOTAL       :     0.185105 sec
-real	0m0.192s
+EvtsPerSec[Rmb+ME]     (23) = ( 1.843535e+05                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 1.979833e+05                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 1.979833e+05                 )  sec^-1
+MeanMatrixElemValue         = ( 4.103219e+02 +- 2.726966e+02 )  GeV^-2
+TOTAL       :     1.815004 sec
+real	0m1.822s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2: 4117) (512y:   25) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_f_inl0_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_f_inl0_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_f_inl0_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_f_inl0_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 1.413313e+00
 Avg ME (F77/C++)    = 1.4133134558441043
 Relative difference = 3.225358460873602e-07
@@ -5776,35 +5832,35 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:06:54 CEST 2022 Will execute './throughputX.sh -makej -ggttg -512yonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:12:20 CEST 2022 Will execute './throughputX.sh -makej -ggttg -512yonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -512yonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
 CUDACPP_BUILDDIR='build.512y_f_inl1_hrd0'
 make: Nothing to be done for `all'.
 
-DATE: 2022-08-31_21:06:54
+DATE: 2022-09-25_00:12:20
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_f_inl1_hrd0/check.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_f_inl1_hrd0/check.exe -p 64 256 20 OMP=
 Process                     = SIGMA_SM_GG_TTXG_CPP [gcc 11.2.0] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK
 FP precision                = FLOAT (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 1.468435e+05                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 1.554937e+05                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 1.554937e+05                 )  sec^-1
-MeanMatrixElemValue         = ( 2.361234e+02 +- 1.906766e+02 )  GeV^-2
-TOTAL       :     0.229562 sec
-real	0m0.236s
+EvtsPerSec[Rmb+ME]     (23) = ( 1.472873e+05                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 1.558765e+05                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 1.558765e+05                 )  sec^-1
+MeanMatrixElemValue         = ( 4.103258e+02 +- 2.726957e+02 )  GeV^-2
+TOTAL       :     2.262346 sec
+real	0m2.269s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2: 8637) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_f_inl1_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_f_inl1_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_f_inl1_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_f_inl1_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 1.413205e+00
 Avg ME (F77/C++)    = 1.4132052211958808
 Relative difference = 1.5652073175724815e-07
@@ -5812,13 +5868,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:06:57 CEST 2022 Will execute './throughputX.sh -makej -ggttg -512zonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:12:37 CEST 2022 Will execute './throughputX.sh -makej -ggttg -512zonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -512zonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
 CUDACPP_BUILDDIR='build.512z_d_inl0_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -5828,71 +5884,72 @@ HELINL=0
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.512z_d_inl0_hrd0 for tag=512z_d_inl0_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.512z_d_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gcheck_sa.cu -o build.512z_d_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gcheck_sa.cu -o build.512z_d_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gCPPProcess.cu -o build.512z_d_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512z_d_inl0_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512z_d_inl0_hrd0/gBridgeKernels.o
 AVX=512z
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gCPPProcess.cu -o build.512z_d_inl0_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512z_d_inl0_hrd0/gMatrixElementKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512z_d_inl0_hrd0/gBridgeKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -c Parameters_sm.cc -o build.512z_d_inl0_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -c read_slha.cc -o build.512z_d_inl0_hrd0/read_slha.o
-mkdir -p ../lib/build.512z_d_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512z_d_inl0_hrd0/gCrossSectionKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512z_d_inl0_hrd0/fbridge_cu.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512z_d_inl0_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512z_d_inl0_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512z_d_inl0_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512z_d_inl0_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512z_d_inl0_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512z_d_inl0_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.512z_d_inl0_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.512z_d_inl0_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.512z_d_inl0_hrd0/MatrixElementKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.512z_d_inl0_hrd0/BridgeKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -c Parameters_sm.cc -o build.512z_d_inl0_hrd0/Parameters_sm.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -c read_slha.cc -o build.512z_d_inl0_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.512z_d_inl0_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.512z_d_inl0_hrd0/fbridge.o
+mkdir -p ../lib/build.512z_d_inl0_hrd0
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.512z_d_inl0_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.512z_d_inl0_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.512z_d_inl0_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512z_d_inl0_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512z_d_inl0_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.512z_d_inl0_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512z_d_inl0_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512z_d_inl0_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.512z_d_inl0_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu runTest.cc -o build.512z_d_inl0_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu runTest.cc -o build.512z_d_inl0_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.512z_d_inl0_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512z_d_inl0_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512z_d_inl0_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.512z_d_inl0_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.512z_d_inl0_hrd0/libmg5amc_common.so build.512z_d_inl0_hrd0/Parameters_sm.o build.512z_d_inl0_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512z_d_inl0_hrd0/libmg5amc_gg_ttxg_cuda.so build.512z_d_inl0_hrd0/gCPPProcess.o build.512z_d_inl0_hrd0/gMatrixElementKernels.o build.512z_d_inl0_hrd0/gBridgeKernels.o build.512z_d_inl0_hrd0/gCrossSectionKernels.o build.512z_d_inl0_hrd0/fbridge_cu.o -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512z_d_inl0_hrd0/libmg5amc_gg_ttxg_cpp.so build.512z_d_inl0_hrd0/CPPProcess.o build.512z_d_inl0_hrd0/MatrixElementKernels.o build.512z_d_inl0_hrd0/BridgeKernels.o build.512z_d_inl0_hrd0/CrossSectionKernels.o build.512z_d_inl0_hrd0/fbridge.o -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl0_hrd0/runTest.exe build.512z_d_inl0_hrd0/CPPProcess.o build.512z_d_inl0_hrd0/MatrixElementKernels.o build.512z_d_inl0_hrd0/BridgeKernels.o build.512z_d_inl0_hrd0/CrossSectionKernels.o build.512z_d_inl0_hrd0/RandomNumberKernels.o build.512z_d_inl0_hrd0/RamboSamplingKernels.o build.512z_d_inl0_hrd0/testxxx.o  build.512z_d_inl0_hrd0/testmisc.o  build.512z_d_inl0_hrd0/runTest.o build.512z_d_inl0_hrd0/gCPPProcess.o build.512z_d_inl0_hrd0/gMatrixElementKernels.o build.512z_d_inl0_hrd0/gBridgeKernels.o build.512z_d_inl0_hrd0/gCrossSectionKernels.o build.512z_d_inl0_hrd0/gRandomNumberKernels.o build.512z_d_inl0_hrd0/gRamboSamplingKernels.o build.512z_d_inl0_hrd0/testxxx_cu.o  build.512z_d_inl0_hrd0/testmisc_cu.o  build.512z_d_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_d_inl0_hrd0/check.exe build.512z_d_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_gg_ttxg_cpp build.512z_d_inl0_hrd0/RandomNumberKernels.o build.512z_d_inl0_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_d_inl0_hrd0/fcheck.exe build.512z_d_inl0_hrd0/fcheck_sa.o build.512z_d_inl0_hrd0/fsampler.o -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_gg_ttxg_cpp build.512z_d_inl0_hrd0/RandomNumberKernels.o build.512z_d_inl0_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl0_hrd0/gcheck.exe build.512z_d_inl0_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_gg_ttxg_cuda build.512z_d_inl0_hrd0/gRandomNumberKernels.o build.512z_d_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl0_hrd0/fgcheck.exe build.512z_d_inl0_hrd0/fcheck_sa.o build.512z_d_inl0_hrd0/fsampler_cu.o -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_gg_ttxg_cuda build.512z_d_inl0_hrd0/gRandomNumberKernels.o build.512z_d_inl0_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512z_d_inl0_hrd0/libmg5amc_gg_ttxg_cuda.so build.512z_d_inl0_hrd0/gCPPProcess.o build.512z_d_inl0_hrd0/gMatrixElementKernels.o build.512z_d_inl0_hrd0/gBridgeKernels.o build.512z_d_inl0_hrd0/gCrossSectionKernels.o build.512z_d_inl0_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512z_d_inl0_hrd0/libmg5amc_gg_ttxg_cpp.so build.512z_d_inl0_hrd0/CPPProcess.o build.512z_d_inl0_hrd0/MatrixElementKernels.o build.512z_d_inl0_hrd0/BridgeKernels.o build.512z_d_inl0_hrd0/CrossSectionKernels.o build.512z_d_inl0_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_d_inl0_hrd0/fcheck.exe build.512z_d_inl0_hrd0/fcheck_sa.o build.512z_d_inl0_hrd0/fsampler.o -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_d_inl0_hrd0'  -lgfortran -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_gg_ttxg_cpp build.512z_d_inl0_hrd0/RandomNumberKernels.o build.512z_d_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl0_hrd0/gcheck.exe build.512z_d_inl0_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl0_hrd0'  -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_gg_ttxg_cuda build.512z_d_inl0_hrd0/gRandomNumberKernels.o build.512z_d_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl0_hrd0/fgcheck.exe build.512z_d_inl0_hrd0/fcheck_sa.o build.512z_d_inl0_hrd0/fsampler_cu.o -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl0_hrd0'  -lgfortran -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_gg_ttxg_cuda build.512z_d_inl0_hrd0/gRandomNumberKernels.o build.512z_d_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_d_inl0_hrd0/check.exe build.512z_d_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_d_inl0_hrd0'  -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_gg_ttxg_cpp build.512z_d_inl0_hrd0/RandomNumberKernels.o build.512z_d_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl0_hrd0/runTest.exe build.512z_d_inl0_hrd0/CPPProcess.o build.512z_d_inl0_hrd0/MatrixElementKernels.o build.512z_d_inl0_hrd0/BridgeKernels.o build.512z_d_inl0_hrd0/CrossSectionKernels.o build.512z_d_inl0_hrd0/RandomNumberKernels.o build.512z_d_inl0_hrd0/RamboSamplingKernels.o build.512z_d_inl0_hrd0/testxxx.o  build.512z_d_inl0_hrd0/testmisc.o  build.512z_d_inl0_hrd0/runTest.o build.512z_d_inl0_hrd0/gCPPProcess.o build.512z_d_inl0_hrd0/gMatrixElementKernels.o build.512z_d_inl0_hrd0/gBridgeKernels.o build.512z_d_inl0_hrd0/gCrossSectionKernels.o build.512z_d_inl0_hrd0/gRandomNumberKernels.o build.512z_d_inl0_hrd0/gRamboSamplingKernels.o build.512z_d_inl0_hrd0/testxxx_cu.o  build.512z_d_inl0_hrd0/testmisc_cu.o  build.512z_d_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl0_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
 touch build.512z_d_inl0_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_d_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.512z_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_d_inl0_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_d_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512z_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_d_inl0_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.512z_d_inl0_hrd0/libmg5amc_gg_ttxg_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_d_inl0_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512z_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_d_inl0_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:06:58
+DATE: 2022-09-25_00:12:47
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_d_inl0_hrd0/check.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_d_inl0_hrd0/check.exe -p 64 256 20 OMP=
 Process                     = SIGMA_SM_GG_TTXG_CPP [gcc 11.2.0] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 6.984848e+04                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 7.216728e+04                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 7.216728e+04                 )  sec^-1
-MeanMatrixElemValue         = ( 2.360828e+02 +- 1.906418e+02 )  GeV^-2
-TOTAL       :     0.478268 sec
-real	0m0.485s
+EvtsPerSec[Rmb+ME]     (23) = ( 7.000149e+04                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 7.235249e+04                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 7.235249e+04                 )  sec^-1
+MeanMatrixElemValue         = ( 4.103783e+02 +- 2.727382e+02 )  GeV^-2
+TOTAL       :     4.725633 sec
+real	0m4.732s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2: 1125) (512y:   62) (512z: 3406)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_d_inl0_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_d_inl0_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_d_inl0_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_d_inl0_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 1.413122e+00
 Avg ME (F77/C++)    = 1.4131213684416488
 Relative difference = 4.4692415175178817e-07
@@ -5900,13 +5957,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:07:01 CEST 2022 Will execute './throughputX.sh -makej -ggttg -512zonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:13:07 CEST 2022 Will execute './throughputX.sh -makej -ggttg -512zonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -512zonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
 CUDACPP_BUILDDIR='build.512z_d_inl1_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -5916,71 +5973,72 @@ HELINL=1
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.512z_d_inl1_hrd0 for tag=512z_d_inl1_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.512z_d_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.512z_d_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.512z_d_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.512z_d_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512z_d_inl1_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512z_d_inl1_hrd0/gBridgeKernels.o
 AVX=512z
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.512z_d_inl1_hrd0/gCPPProcess.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512z_d_inl1_hrd0/gMatrixElementKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.512z_d_inl1_hrd0/Parameters_sm.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512z_d_inl1_hrd0/gBridgeKernels.o
-mkdir -p ../lib/build.512z_d_inl1_hrd0
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.512z_d_inl1_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512z_d_inl1_hrd0/gCrossSectionKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512z_d_inl1_hrd0/fbridge_cu.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512z_d_inl1_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512z_d_inl1_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512z_d_inl1_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512z_d_inl1_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512z_d_inl1_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512z_d_inl1_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.512z_d_inl1_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.512z_d_inl1_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.512z_d_inl1_hrd0/MatrixElementKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.512z_d_inl1_hrd0/BridgeKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.512z_d_inl1_hrd0/CrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.512z_d_inl1_hrd0/RandomNumberKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.512z_d_inl1_hrd0/Parameters_sm.o
+mkdir -p ../lib/build.512z_d_inl1_hrd0
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.512z_d_inl1_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.512z_d_inl1_hrd0/fbridge.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.512z_d_inl1_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.512z_d_inl1_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.512z_d_inl1_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512z_d_inl1_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512z_d_inl1_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.512z_d_inl1_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512z_d_inl1_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512z_d_inl1_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.512z_d_inl1_hrd0/runTest.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.512z_d_inl1_hrd0/libmg5amc_common.so build.512z_d_inl1_hrd0/Parameters_sm.o build.512z_d_inl1_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.512z_d_inl1_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.512z_d_inl1_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.512z_d_inl1_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512z_d_inl1_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512z_d_inl1_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.512z_d_inl1_hrd0/fsampler.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512z_d_inl1_hrd0/libmg5amc_gg_ttxg_cuda.so build.512z_d_inl1_hrd0/gCPPProcess.o build.512z_d_inl1_hrd0/gMatrixElementKernels.o build.512z_d_inl1_hrd0/gBridgeKernels.o build.512z_d_inl1_hrd0/gCrossSectionKernels.o build.512z_d_inl1_hrd0/fbridge_cu.o -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512z_d_inl1_hrd0/libmg5amc_gg_ttxg_cpp.so build.512z_d_inl1_hrd0/CPPProcess.o build.512z_d_inl1_hrd0/MatrixElementKernels.o build.512z_d_inl1_hrd0/BridgeKernels.o build.512z_d_inl1_hrd0/CrossSectionKernels.o build.512z_d_inl1_hrd0/fbridge.o -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl1_hrd0/runTest.exe build.512z_d_inl1_hrd0/CPPProcess.o build.512z_d_inl1_hrd0/MatrixElementKernels.o build.512z_d_inl1_hrd0/BridgeKernels.o build.512z_d_inl1_hrd0/CrossSectionKernels.o build.512z_d_inl1_hrd0/RandomNumberKernels.o build.512z_d_inl1_hrd0/RamboSamplingKernels.o build.512z_d_inl1_hrd0/testxxx.o  build.512z_d_inl1_hrd0/testmisc.o  build.512z_d_inl1_hrd0/runTest.o build.512z_d_inl1_hrd0/gCPPProcess.o build.512z_d_inl1_hrd0/gMatrixElementKernels.o build.512z_d_inl1_hrd0/gBridgeKernels.o build.512z_d_inl1_hrd0/gCrossSectionKernels.o build.512z_d_inl1_hrd0/gRandomNumberKernels.o build.512z_d_inl1_hrd0/gRamboSamplingKernels.o build.512z_d_inl1_hrd0/testxxx_cu.o  build.512z_d_inl1_hrd0/testmisc_cu.o  build.512z_d_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_d_inl1_hrd0/check.exe build.512z_d_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_gg_ttxg_cpp build.512z_d_inl1_hrd0/RandomNumberKernels.o build.512z_d_inl1_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_d_inl1_hrd0/fcheck.exe build.512z_d_inl1_hrd0/fcheck_sa.o build.512z_d_inl1_hrd0/fsampler.o -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_gg_ttxg_cpp build.512z_d_inl1_hrd0/RandomNumberKernels.o build.512z_d_inl1_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl1_hrd0/gcheck.exe build.512z_d_inl1_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_gg_ttxg_cuda build.512z_d_inl1_hrd0/gRandomNumberKernels.o build.512z_d_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl1_hrd0/fgcheck.exe build.512z_d_inl1_hrd0/fcheck_sa.o build.512z_d_inl1_hrd0/fsampler_cu.o -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_gg_ttxg_cuda build.512z_d_inl1_hrd0/gRandomNumberKernels.o build.512z_d_inl1_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.512z_d_inl1_hrd0/libmg5amc_common.so build.512z_d_inl1_hrd0/Parameters_sm.o build.512z_d_inl1_hrd0/read_slha.o
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512z_d_inl1_hrd0/libmg5amc_gg_ttxg_cuda.so build.512z_d_inl1_hrd0/gCPPProcess.o build.512z_d_inl1_hrd0/gMatrixElementKernels.o build.512z_d_inl1_hrd0/gBridgeKernels.o build.512z_d_inl1_hrd0/gCrossSectionKernels.o build.512z_d_inl1_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl1_hrd0/gcheck.exe build.512z_d_inl1_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl1_hrd0'  -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_gg_ttxg_cuda build.512z_d_inl1_hrd0/gRandomNumberKernels.o build.512z_d_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl1_hrd0/fgcheck.exe build.512z_d_inl1_hrd0/fcheck_sa.o build.512z_d_inl1_hrd0/fsampler_cu.o -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl1_hrd0'  -lgfortran -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_gg_ttxg_cuda build.512z_d_inl1_hrd0/gRandomNumberKernels.o build.512z_d_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512z_d_inl1_hrd0/libmg5amc_gg_ttxg_cpp.so build.512z_d_inl1_hrd0/CPPProcess.o build.512z_d_inl1_hrd0/MatrixElementKernels.o build.512z_d_inl1_hrd0/BridgeKernels.o build.512z_d_inl1_hrd0/CrossSectionKernels.o build.512z_d_inl1_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_d_inl1_hrd0/check.exe build.512z_d_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_d_inl1_hrd0'  -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_gg_ttxg_cpp build.512z_d_inl1_hrd0/RandomNumberKernels.o build.512z_d_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_d_inl1_hrd0/fcheck.exe build.512z_d_inl1_hrd0/fcheck_sa.o build.512z_d_inl1_hrd0/fsampler.o -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_d_inl1_hrd0'  -lgfortran -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_gg_ttxg_cpp build.512z_d_inl1_hrd0/RandomNumberKernels.o build.512z_d_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl1_hrd0/runTest.exe build.512z_d_inl1_hrd0/CPPProcess.o build.512z_d_inl1_hrd0/MatrixElementKernels.o build.512z_d_inl1_hrd0/BridgeKernels.o build.512z_d_inl1_hrd0/CrossSectionKernels.o build.512z_d_inl1_hrd0/RandomNumberKernels.o build.512z_d_inl1_hrd0/RamboSamplingKernels.o build.512z_d_inl1_hrd0/testxxx.o  build.512z_d_inl1_hrd0/testmisc.o  build.512z_d_inl1_hrd0/runTest.o build.512z_d_inl1_hrd0/gCPPProcess.o build.512z_d_inl1_hrd0/gMatrixElementKernels.o build.512z_d_inl1_hrd0/gBridgeKernels.o build.512z_d_inl1_hrd0/gCrossSectionKernels.o build.512z_d_inl1_hrd0/gRandomNumberKernels.o build.512z_d_inl1_hrd0/gRamboSamplingKernels.o build.512z_d_inl1_hrd0/testxxx_cu.o  build.512z_d_inl1_hrd0/testmisc_cu.o  build.512z_d_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl1_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
 touch build.512z_d_inl1_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_d_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.512z_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_d_inl1_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_d_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512z_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_d_inl1_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.512z_d_inl1_hrd0/libmg5amc_gg_ttxg_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_d_inl1_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512z_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_d_inl1_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:07:02
+DATE: 2022-09-25_00:13:15
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_d_inl1_hrd0/check.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_d_inl1_hrd0/check.exe -p 64 256 20 OMP=
 Process                     = SIGMA_SM_GG_TTXG_CPP [gcc 11.2.0] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 6.291486e+04                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 6.479495e+04                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 6.479495e+04                 )  sec^-1
-MeanMatrixElemValue         = ( 2.360828e+02 +- 1.906418e+02 )  GeV^-2
-TOTAL       :     0.529791 sec
-real	0m0.536s
+EvtsPerSec[Rmb+ME]     (23) = ( 6.305020e+04                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 6.491223e+04                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 6.491223e+04                 )  sec^-1
+MeanMatrixElemValue         = ( 4.103783e+02 +- 2.727382e+02 )  GeV^-2
+TOTAL       :     5.241760 sec
+real	0m5.248s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2: 1745) (512y:  281) (512z: 6756)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_d_inl1_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_d_inl1_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_d_inl1_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_d_inl1_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 1.413122e+00
 Avg ME (F77/C++)    = 1.4131213684417272
 Relative difference = 4.4692409628471204e-07
@@ -5988,13 +6046,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:07:05 CEST 2022 Will execute './throughputX.sh -makej -ggttg -512zonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:13:35 CEST 2022 Will execute './throughputX.sh -makej -ggttg -512zonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -512zonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
 CUDACPP_BUILDDIR='build.512z_f_inl0_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -6004,71 +6062,72 @@ HELINL=0
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.512z_f_inl0_hrd0 for tag=512z_f_inl0_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.512z_f_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gcheck_sa.cu -o build.512z_f_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gcheck_sa.cu -o build.512z_f_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gCPPProcess.cu -o build.512z_f_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512z_f_inl0_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512z_f_inl0_hrd0/gBridgeKernels.o
 AVX=512z
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gCPPProcess.cu -o build.512z_f_inl0_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512z_f_inl0_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512z_f_inl0_hrd0/gBridgeKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -c Parameters_sm.cc -o build.512z_f_inl0_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -c read_slha.cc -o build.512z_f_inl0_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512z_f_inl0_hrd0/gCrossSectionKernels.o
-mkdir -p ../lib/build.512z_f_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512z_f_inl0_hrd0/fbridge_cu.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512z_f_inl0_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512z_f_inl0_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512z_f_inl0_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512z_f_inl0_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512z_f_inl0_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512z_f_inl0_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.512z_f_inl0_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.512z_f_inl0_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.512z_f_inl0_hrd0/MatrixElementKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -c read_slha.cc -o build.512z_f_inl0_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.512z_f_inl0_hrd0/BridgeKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -c Parameters_sm.cc -o build.512z_f_inl0_hrd0/Parameters_sm.o
+mkdir -p ../lib/build.512z_f_inl0_hrd0
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.512z_f_inl0_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.512z_f_inl0_hrd0/fbridge.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.512z_f_inl0_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.512z_f_inl0_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.512z_f_inl0_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512z_f_inl0_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512z_f_inl0_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.512z_f_inl0_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512z_f_inl0_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512z_f_inl0_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.512z_f_inl0_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu runTest.cc -o build.512z_f_inl0_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu runTest.cc -o build.512z_f_inl0_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.512z_f_inl0_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512z_f_inl0_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512z_f_inl0_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.512z_f_inl0_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.512z_f_inl0_hrd0/libmg5amc_common.so build.512z_f_inl0_hrd0/Parameters_sm.o build.512z_f_inl0_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512z_f_inl0_hrd0/libmg5amc_gg_ttxg_cuda.so build.512z_f_inl0_hrd0/gCPPProcess.o build.512z_f_inl0_hrd0/gMatrixElementKernels.o build.512z_f_inl0_hrd0/gBridgeKernels.o build.512z_f_inl0_hrd0/gCrossSectionKernels.o build.512z_f_inl0_hrd0/fbridge_cu.o -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512z_f_inl0_hrd0/libmg5amc_gg_ttxg_cpp.so build.512z_f_inl0_hrd0/CPPProcess.o build.512z_f_inl0_hrd0/MatrixElementKernels.o build.512z_f_inl0_hrd0/BridgeKernels.o build.512z_f_inl0_hrd0/CrossSectionKernels.o build.512z_f_inl0_hrd0/fbridge.o -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl0_hrd0/runTest.exe build.512z_f_inl0_hrd0/CPPProcess.o build.512z_f_inl0_hrd0/MatrixElementKernels.o build.512z_f_inl0_hrd0/BridgeKernels.o build.512z_f_inl0_hrd0/CrossSectionKernels.o build.512z_f_inl0_hrd0/RandomNumberKernels.o build.512z_f_inl0_hrd0/RamboSamplingKernels.o build.512z_f_inl0_hrd0/testxxx.o  build.512z_f_inl0_hrd0/testmisc.o  build.512z_f_inl0_hrd0/runTest.o build.512z_f_inl0_hrd0/gCPPProcess.o build.512z_f_inl0_hrd0/gMatrixElementKernels.o build.512z_f_inl0_hrd0/gBridgeKernels.o build.512z_f_inl0_hrd0/gCrossSectionKernels.o build.512z_f_inl0_hrd0/gRandomNumberKernels.o build.512z_f_inl0_hrd0/gRamboSamplingKernels.o build.512z_f_inl0_hrd0/testxxx_cu.o  build.512z_f_inl0_hrd0/testmisc_cu.o  build.512z_f_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_f_inl0_hrd0/check.exe build.512z_f_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_gg_ttxg_cpp build.512z_f_inl0_hrd0/RandomNumberKernels.o build.512z_f_inl0_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_f_inl0_hrd0/fcheck.exe build.512z_f_inl0_hrd0/fcheck_sa.o build.512z_f_inl0_hrd0/fsampler.o -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_gg_ttxg_cpp build.512z_f_inl0_hrd0/RandomNumberKernels.o build.512z_f_inl0_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl0_hrd0/gcheck.exe build.512z_f_inl0_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_gg_ttxg_cuda build.512z_f_inl0_hrd0/gRandomNumberKernels.o build.512z_f_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl0_hrd0/fgcheck.exe build.512z_f_inl0_hrd0/fcheck_sa.o build.512z_f_inl0_hrd0/fsampler_cu.o -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_gg_ttxg_cuda build.512z_f_inl0_hrd0/gRandomNumberKernels.o build.512z_f_inl0_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512z_f_inl0_hrd0/libmg5amc_gg_ttxg_cuda.so build.512z_f_inl0_hrd0/gCPPProcess.o build.512z_f_inl0_hrd0/gMatrixElementKernels.o build.512z_f_inl0_hrd0/gBridgeKernels.o build.512z_f_inl0_hrd0/gCrossSectionKernels.o build.512z_f_inl0_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512z_f_inl0_hrd0/libmg5amc_gg_ttxg_cpp.so build.512z_f_inl0_hrd0/CPPProcess.o build.512z_f_inl0_hrd0/MatrixElementKernels.o build.512z_f_inl0_hrd0/BridgeKernels.o build.512z_f_inl0_hrd0/CrossSectionKernels.o build.512z_f_inl0_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_f_inl0_hrd0/fcheck.exe build.512z_f_inl0_hrd0/fcheck_sa.o build.512z_f_inl0_hrd0/fsampler.o -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_f_inl0_hrd0'  -lgfortran -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_gg_ttxg_cpp build.512z_f_inl0_hrd0/RandomNumberKernels.o build.512z_f_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl0_hrd0/gcheck.exe build.512z_f_inl0_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl0_hrd0'  -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_gg_ttxg_cuda build.512z_f_inl0_hrd0/gRandomNumberKernels.o build.512z_f_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl0_hrd0/fgcheck.exe build.512z_f_inl0_hrd0/fcheck_sa.o build.512z_f_inl0_hrd0/fsampler_cu.o -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl0_hrd0'  -lgfortran -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_gg_ttxg_cuda build.512z_f_inl0_hrd0/gRandomNumberKernels.o build.512z_f_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_f_inl0_hrd0/check.exe build.512z_f_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_f_inl0_hrd0'  -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_gg_ttxg_cpp build.512z_f_inl0_hrd0/RandomNumberKernels.o build.512z_f_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl0_hrd0/runTest.exe build.512z_f_inl0_hrd0/CPPProcess.o build.512z_f_inl0_hrd0/MatrixElementKernels.o build.512z_f_inl0_hrd0/BridgeKernels.o build.512z_f_inl0_hrd0/CrossSectionKernels.o build.512z_f_inl0_hrd0/RandomNumberKernels.o build.512z_f_inl0_hrd0/RamboSamplingKernels.o build.512z_f_inl0_hrd0/testxxx.o  build.512z_f_inl0_hrd0/testmisc.o  build.512z_f_inl0_hrd0/runTest.o build.512z_f_inl0_hrd0/gCPPProcess.o build.512z_f_inl0_hrd0/gMatrixElementKernels.o build.512z_f_inl0_hrd0/gBridgeKernels.o build.512z_f_inl0_hrd0/gCrossSectionKernels.o build.512z_f_inl0_hrd0/gRandomNumberKernels.o build.512z_f_inl0_hrd0/gRamboSamplingKernels.o build.512z_f_inl0_hrd0/testxxx_cu.o  build.512z_f_inl0_hrd0/testmisc_cu.o  build.512z_f_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl0_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
 touch build.512z_f_inl0_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_f_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.512z_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_f_inl0_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_f_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512z_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_f_inl0_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.512z_f_inl0_hrd0/libmg5amc_gg_ttxg_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_f_inl0_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512z_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_f_inl0_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:07:06
+DATE: 2022-09-25_00:13:45
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_f_inl0_hrd0/check.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_f_inl0_hrd0/check.exe -p 64 256 20 OMP=
 Process                     = SIGMA_SM_GG_TTXG_CPP [gcc 11.2.0] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK
 FP precision                = FLOAT (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 1.419492e+05                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 1.501641e+05                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 1.501641e+05                 )  sec^-1
-MeanMatrixElemValue         = ( 2.361273e+02 +- 1.906834e+02 )  GeV^-2
-TOTAL       :     0.237770 sec
-real	0m0.244s
+EvtsPerSec[Rmb+ME]     (23) = ( 1.420025e+05                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 1.503583e+05                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 1.503583e+05                 )  sec^-1
+MeanMatrixElemValue         = ( 4.103217e+02 +- 2.726967e+02 )  GeV^-2
+TOTAL       :     2.348852 sec
+real	0m2.355s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2: 1425) (512y:   33) (512z: 3520)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_f_inl0_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_f_inl0_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_f_inl0_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_f_inl0_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 1.413317e+00
 Avg ME (F77/C++)    = 1.4133166018511645
 Relative difference = 2.817123373287977e-07
@@ -6076,13 +6135,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:07:08 CEST 2022 Will execute './throughputX.sh -makej -ggttg -512zonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:14:03 CEST 2022 Will execute './throughputX.sh -makej -ggttg -512zonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -512zonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg
 CUDACPP_BUILDDIR='build.512z_f_inl1_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -6092,71 +6151,72 @@ HELINL=1
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.512z_f_inl1_hrd0 for tag=512z_f_inl1_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.512z_f_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.512z_f_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.512z_f_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.512z_f_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512z_f_inl1_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512z_f_inl1_hrd0/gBridgeKernels.o
 AVX=512z
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.512z_f_inl1_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512z_f_inl1_hrd0/gMatrixElementKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512z_f_inl1_hrd0/gBridgeKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512z_f_inl1_hrd0/gCrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.512z_f_inl1_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.512z_f_inl1_hrd0/read_slha.o
-mkdir -p ../lib/build.512z_f_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512z_f_inl1_hrd0/fbridge_cu.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512z_f_inl1_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512z_f_inl1_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512z_f_inl1_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512z_f_inl1_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512z_f_inl1_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512z_f_inl1_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.512z_f_inl1_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.512z_f_inl1_hrd0/CPPProcess.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.512z_f_inl1_hrd0/Parameters_sm.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.512z_f_inl1_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.512z_f_inl1_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.512z_f_inl1_hrd0/BridgeKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.512z_f_inl1_hrd0/CrossSectionKernels.o
+mkdir -p ../lib/build.512z_f_inl1_hrd0
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.512z_f_inl1_hrd0/fbridge.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.512z_f_inl1_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.512z_f_inl1_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.512z_f_inl1_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512z_f_inl1_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512z_f_inl1_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.512z_f_inl1_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512z_f_inl1_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512z_f_inl1_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.512z_f_inl1_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.512z_f_inl1_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.512z_f_inl1_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.512z_f_inl1_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512z_f_inl1_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512z_f_inl1_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.512z_f_inl1_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.512z_f_inl1_hrd0/libmg5amc_common.so build.512z_f_inl1_hrd0/Parameters_sm.o build.512z_f_inl1_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512z_f_inl1_hrd0/libmg5amc_gg_ttxg_cuda.so build.512z_f_inl1_hrd0/gCPPProcess.o build.512z_f_inl1_hrd0/gMatrixElementKernels.o build.512z_f_inl1_hrd0/gBridgeKernels.o build.512z_f_inl1_hrd0/gCrossSectionKernels.o build.512z_f_inl1_hrd0/fbridge_cu.o -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512z_f_inl1_hrd0/libmg5amc_gg_ttxg_cpp.so build.512z_f_inl1_hrd0/CPPProcess.o build.512z_f_inl1_hrd0/MatrixElementKernels.o build.512z_f_inl1_hrd0/BridgeKernels.o build.512z_f_inl1_hrd0/CrossSectionKernels.o build.512z_f_inl1_hrd0/fbridge.o -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl1_hrd0/runTest.exe build.512z_f_inl1_hrd0/CPPProcess.o build.512z_f_inl1_hrd0/MatrixElementKernels.o build.512z_f_inl1_hrd0/BridgeKernels.o build.512z_f_inl1_hrd0/CrossSectionKernels.o build.512z_f_inl1_hrd0/RandomNumberKernels.o build.512z_f_inl1_hrd0/RamboSamplingKernels.o build.512z_f_inl1_hrd0/testxxx.o  build.512z_f_inl1_hrd0/testmisc.o  build.512z_f_inl1_hrd0/runTest.o build.512z_f_inl1_hrd0/gCPPProcess.o build.512z_f_inl1_hrd0/gMatrixElementKernels.o build.512z_f_inl1_hrd0/gBridgeKernels.o build.512z_f_inl1_hrd0/gCrossSectionKernels.o build.512z_f_inl1_hrd0/gRandomNumberKernels.o build.512z_f_inl1_hrd0/gRamboSamplingKernels.o build.512z_f_inl1_hrd0/testxxx_cu.o  build.512z_f_inl1_hrd0/testmisc_cu.o  build.512z_f_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_f_inl1_hrd0/check.exe build.512z_f_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_gg_ttxg_cpp build.512z_f_inl1_hrd0/RandomNumberKernels.o build.512z_f_inl1_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_f_inl1_hrd0/fcheck.exe build.512z_f_inl1_hrd0/fcheck_sa.o build.512z_f_inl1_hrd0/fsampler.o -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_gg_ttxg_cpp build.512z_f_inl1_hrd0/RandomNumberKernels.o build.512z_f_inl1_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl1_hrd0/gcheck.exe build.512z_f_inl1_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_gg_ttxg_cuda build.512z_f_inl1_hrd0/gRandomNumberKernels.o build.512z_f_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl1_hrd0/fgcheck.exe build.512z_f_inl1_hrd0/fcheck_sa.o build.512z_f_inl1_hrd0/fsampler_cu.o -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_gg_ttxg_cuda build.512z_f_inl1_hrd0/gRandomNumberKernels.o build.512z_f_inl1_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512z_f_inl1_hrd0/libmg5amc_gg_ttxg_cuda.so build.512z_f_inl1_hrd0/gCPPProcess.o build.512z_f_inl1_hrd0/gMatrixElementKernels.o build.512z_f_inl1_hrd0/gBridgeKernels.o build.512z_f_inl1_hrd0/gCrossSectionKernels.o build.512z_f_inl1_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl1_hrd0/gcheck.exe build.512z_f_inl1_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl1_hrd0'  -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_gg_ttxg_cuda build.512z_f_inl1_hrd0/gRandomNumberKernels.o build.512z_f_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl1_hrd0/fgcheck.exe build.512z_f_inl1_hrd0/fcheck_sa.o build.512z_f_inl1_hrd0/fsampler_cu.o -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl1_hrd0'  -lgfortran -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_gg_ttxg_cuda build.512z_f_inl1_hrd0/gRandomNumberKernels.o build.512z_f_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512z_f_inl1_hrd0/libmg5amc_gg_ttxg_cpp.so build.512z_f_inl1_hrd0/CPPProcess.o build.512z_f_inl1_hrd0/MatrixElementKernels.o build.512z_f_inl1_hrd0/BridgeKernels.o build.512z_f_inl1_hrd0/CrossSectionKernels.o build.512z_f_inl1_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_f_inl1_hrd0/check.exe build.512z_f_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_f_inl1_hrd0'  -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_gg_ttxg_cpp build.512z_f_inl1_hrd0/RandomNumberKernels.o build.512z_f_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_f_inl1_hrd0/fcheck.exe build.512z_f_inl1_hrd0/fcheck_sa.o build.512z_f_inl1_hrd0/fsampler.o -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_f_inl1_hrd0'  -lgfortran -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_gg_ttxg_cpp build.512z_f_inl1_hrd0/RandomNumberKernels.o build.512z_f_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl1_hrd0/runTest.exe build.512z_f_inl1_hrd0/CPPProcess.o build.512z_f_inl1_hrd0/MatrixElementKernels.o build.512z_f_inl1_hrd0/BridgeKernels.o build.512z_f_inl1_hrd0/CrossSectionKernels.o build.512z_f_inl1_hrd0/RandomNumberKernels.o build.512z_f_inl1_hrd0/RamboSamplingKernels.o build.512z_f_inl1_hrd0/testxxx.o  build.512z_f_inl1_hrd0/testmisc.o  build.512z_f_inl1_hrd0/runTest.o build.512z_f_inl1_hrd0/gCPPProcess.o build.512z_f_inl1_hrd0/gMatrixElementKernels.o build.512z_f_inl1_hrd0/gBridgeKernels.o build.512z_f_inl1_hrd0/gCrossSectionKernels.o build.512z_f_inl1_hrd0/gRandomNumberKernels.o build.512z_f_inl1_hrd0/gRamboSamplingKernels.o build.512z_f_inl1_hrd0/testxxx_cu.o  build.512z_f_inl1_hrd0/testmisc_cu.o  build.512z_f_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl1_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg'
 touch build.512z_f_inl1_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_f_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.512z_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_f_inl1_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_f_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512z_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_f_inl1_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.512z_f_inl1_hrd0/libmg5amc_gg_ttxg_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_f_inl1_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512z_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxg_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_f_inl1_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:07:11
+DATE: 2022-09-25_00:14:13
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_f_inl1_hrd0/check.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_f_inl1_hrd0/check.exe -p 64 256 20 OMP=
 Process                     = SIGMA_SM_GG_TTXG_CPP [gcc 11.2.0] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK
 FP precision                = FLOAT (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 1.102187e+05                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 1.150097e+05                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 1.150097e+05                 )  sec^-1
-MeanMatrixElemValue         = ( 2.361234e+02 +- 1.906766e+02 )  GeV^-2
-TOTAL       :     0.304269 sec
-real	0m0.311s
+EvtsPerSec[Rmb+ME]     (23) = ( 1.106226e+05                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 1.154932e+05                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 1.154932e+05                 )  sec^-1
+MeanMatrixElemValue         = ( 4.103259e+02 +- 2.726958e+02 )  GeV^-2
+TOTAL       :     3.003301 sec
+real	0m3.010s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2: 3775) (512y:    2) (512z: 7185)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_f_inl1_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_f_inl1_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_f_inl1_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_f_inl1_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 1.413205e+00
 Avg ME (F77/C++)    = 1.4132053883742799
 Relative difference = 2.7481807653324893e-07
@@ -6164,12 +6224,12 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:07:14 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -nocpp  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:14:31 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -nocpp  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
 CUDACPP_BUILDDIR='build.none_d_inl0_hrd0'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -w -cpp  -c myamp.f -I../../Source/ -fopenmp -o myamp.o
 cd ../../Source; make
@@ -6183,31 +6243,24 @@ ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfort
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -w -cpp  -c addmothers.f -I../../Source/ -fopenmp -o addmothers.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -w -cpp  -c setscales.f -I../../Source/ -fopenmp -o setscales.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -w -cpp  -c idenparts.f -I../../Source/ -fopenmp -o idenparts.o
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/Source'
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o StringCast.o StringCast.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -w -cpp  -c dummy_fct.f -I../../Source/ -fopenmp -o dummy_fct.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -w -cpp  -c auto_dsig1.f -I../../Source/ -fopenmp -o auto_dsig1.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -std=c++11 -Wall -Wshadow -Wextra -c counters.cpp -o counters.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -w -cpp  -c -DMG5AMC_MEEXPORTER_CUDACPP auto_dsig1.f -I../../Source/ -fopenmp -o auto_dsig1_cudacpp.o
+make -f cudacpp.mk
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/Source'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o StringCast.o StringCast.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o ranmar.o ranmar.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o alfas_functions.o alfas_functions.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -std=c++11 -Wall -Wshadow -Wextra -c counters.cpp -o counters.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o transpole.o transpole.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -w -cpp  -c -DMG5AMC_MEEXPORTER_CUDACPP auto_dsig1.f -I../../Source/ -fopenmp -o auto_dsig1_cudacpp.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o invarients.o invarients.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o hfill.o hfill.f
-make -f cudacpp.mk
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o pawgraphs.o pawgraphs.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o ran1.o ran1.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o rw_events.o rw_events.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o rw_routines.o rw_routines.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o kin_functions.o kin_functions.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o open_file.o open_file.f
-OMPFLAGS=
-AVX=none
-FPTYPE=d
-HELINL=0
-HRDCOD=0
-RNDGEN=hasCurand
-Building in BUILDDIR=build.none_d_inl0_hrd0 for tag=none_d_inl0_hrd0_hasCurand (USEBUILDDIR is set = 1)
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o basecode.o basecode.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o setrun.o setrun.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o run_printout.o run_printout.f
@@ -6219,73 +6272,87 @@ cd PDF; make
 cd MODEL; make    
 cd CERNLIB; make
 cd BIAS/dummy; make
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/Source/MODEL'
+OMPFLAGS=
+AVX=none
+FPTYPE=d
+HELINL=0
+HRDCOD=0
+RNDGEN=hasCurand
+Building in BUILDDIR=build.none_d_inl0_hrd0 for tag=none_d_inl0_hrd0_hasCurand (USEBUILDDIR is set = 1)
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/Source/PDF'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o Ctq6Pdf.o Ctq6Pdf.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o pdfwrap.o pdfwrap.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o opendata.o opendata.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o pdf.o pdf.f
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/Source/MODEL'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o couplings.o couplings.f
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/Source/DHELAS'
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o aloha_functions.o aloha_functions.f
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/Source/CERNLIB'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o abend.o abend.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o lha_read.o lha_read.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o dlsqp2.o dlsqp2.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o lenocc.o lenocc.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o printout.o printout.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I.. -c -o rw_para.o rw_para.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o mtlprt.o mtlprt.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o mtlset.o mtlset.f
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/Source/DHELAS'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o aloha_functions.o aloha_functions.f
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/Source/BIAS/dummy'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o dummy.o dummy.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o model_functions.o model_functions.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o VVV1_0.o VVV1_0.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o PhotonFlux.o PhotonFlux.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o couplings1.o couplings1.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o couplings2.o couplings2.f
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/Source/BIAS/dummy'
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o dummy.o dummy.f
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/Source/PDF'
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o Ctq6Pdf.o Ctq6Pdf.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o pdg2pdf.o pdg2pdf.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o NNPDFDriver.o NNPDFDriver.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o VVVV3P0_1.o VVVV3P0_1.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o pdfwrap.o pdfwrap.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o eepdf.o eepdf.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o FFV1_1.o FFV1_1.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o VVVV4P0_1.o VVVV4P0_1.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o VVVV3_0.o VVVV3_0.f
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/Source/CERNLIB'
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o abend.o abend.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o FFV1P0_3.o FFV1P0_3.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o dlsqp2.o dlsqp2.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o FFV1_0.o FFV1_0.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o lenocc.o lenocc.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o FFV1_2.o FFV1_2.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o mtlprt.o mtlprt.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o VVVV1_0.o VVVV1_0.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o opendata.o opendata.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o mtlset.o mtlset.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o VVVV1P0_1.o VVVV1P0_1.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o radmul.o radmul.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o pdf.o pdf.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o VVVV4_0.o VVVV4_0.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o VVV1P0_1.o VVV1P0_1.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o PhotonFlux.o PhotonFlux.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o pdg2pdf.o pdg2pdf.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o NNPDFDriver.o NNPDFDriver.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o DiscreteSampler.o DiscreteSampler.f
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o eepdf.o eepdf.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o gridpdfaux.o gridpdfaux.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o couplings2.o couplings2.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o VVVV1P0_1.o VVVV1P0_1.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o dfint.o dfint.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o kerset.o kerset.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o VVVV4_0.o VVVV4_0.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o ElectroweakFluxDriver.o ElectroweakFluxDriver.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132   -c -o VVV1P0_1.o VVV1P0_1.f
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -I..  -c -o ElectroweakFlux.o ElectroweakFlux.f
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o DiscreteSampler.o DiscreteSampler.f
 ar cru  ../../../lib/libbias.a  dummy.o
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
-mkdir -p build.none_d_inl0_hrd0
+ranlib  ../../../lib/libbias.a
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/Source/BIAS/dummy'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.none_d_inl0_hrd0
-mkdir -p build.none_d_inl0_hrd0
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gcheck_sa.cu -o build.none_d_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gCPPProcess.cu -o build.none_d_inl0_hrd0/gCPPProcess.o
 AVX=none
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
-ranlib  ../../../lib/libbias.a
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gcheck_sa.cu -o build.none_d_inl0_hrd0/gcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gCPPProcess.cu -o build.none_d_inl0_hrd0/gCPPProcess.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/Source/BIAS/dummy'
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.none_d_inl0_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gBridgeKernels.cu -o build.none_d_inl0_hrd0/gBridgeKernels.o
+ar cru  ../../lib/libcernlib.a  abend.o dlsqp2.o lenocc.o mtlprt.o mtlset.o radmul.o
+ar cru  ../../lib/libpdf.a  Ctq6Pdf.o pdfwrap.o opendata.o pdf.o PhotonFlux.o pdg2pdf.o NNPDFDriver.o eepdf.o gridpdfaux.o dfint.o kerset.o ElectroweakFluxDriver.o ElectroweakFlux.o
+ranlib  ../../lib/libpdf.a
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
+ranlib  ../../lib/libcernlib.a
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/Source/CERNLIB'
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.none_d_inl0_hrd0/gCrossSectionKernels.o
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/Source/PDF'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -c Parameters_sm.cc -o build.none_d_inl0_hrd0/Parameters_sm.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.none_d_inl0_hrd0/gMatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -c read_slha.cc -o build.none_d_inl0_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gBridgeKernels.cu -o build.none_d_inl0_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fbridge.cc -o build.none_d_inl0_hrd0/fbridge_cu.o
+ar cru  ../../lib/libmodel.a  couplings.o lha_read.o printout.o rw_para.o model_functions.o couplings1.o couplings2.o
 mkdir -p ../lib/build.none_d_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.none_d_inl0_hrd0/gCrossSectionKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fbridge.cc -o build.none_d_inl0_hrd0/fbridge_cu.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.none_d_inl0_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.none_d_inl0_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.none_d_inl0_hrd0/gRandomNumberKernels.o
+ranlib  ../../lib/libmodel.a
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/Source/MODEL'
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.none_d_inl0_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.none_d_inl0_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.none_d_inl0_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.none_d_inl0_hrd0/MatrixElementKernels.o
@@ -6294,52 +6361,44 @@ ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.none_d_inl0_hrd0/fbridge.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.none_d_inl0_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.none_d_inl0_hrd0/RamboSamplingKernels.o
+ar cru  ../lib/libgeneric.a  alfas_functions.o transpole.o invarients.o hfill.o pawgraphs.o ran1.o rw_events.o rw_routines.o kin_functions.o open_file.o basecode.o setrun.o run_printout.o dgauss.o readgrid.o getissud.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.none_d_inl0_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testxxx.cc -o build.none_d_inl0_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testxxx.cc -o build.none_d_inl0_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.none_d_inl0_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testmisc.cc -o build.none_d_inl0_hrd0/testmisc_cu.o
+ranlib  ../lib/libgeneric.a
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testmisc.cc -o build.none_d_inl0_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.none_d_inl0_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu runTest.cc -o build.none_d_inl0_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu runTest.cc -o build.none_d_inl0_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.none_d_inl0_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fsampler.cc -o build.none_d_inl0_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fsampler.cc -o build.none_d_inl0_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.none_d_inl0_hrd0/fsampler.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.none_d_inl0_hrd0/libmg5amc_common.so build.none_d_inl0_hrd0/Parameters_sm.o build.none_d_inl0_hrd0/read_slha.o
-ar cru  ../../lib/libmodel.a  couplings.o lha_read.o printout.o rw_para.o model_functions.o couplings1.o couplings2.o
-ranlib  ../../lib/libmodel.a
-ar cru  ../lib/libgeneric.a  alfas_functions.o transpole.o invarients.o hfill.o pawgraphs.o ran1.o rw_events.o rw_routines.o kin_functions.o open_file.o basecode.o setrun.o run_printout.o dgauss.o readgrid.o getissud.o
-ranlib  ../lib/libgeneric.a
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/Source/MODEL'
-ar cru  ../../lib/libcernlib.a  abend.o dlsqp2.o lenocc.o mtlprt.o mtlset.o radmul.o
-ranlib  ../../lib/libcernlib.a
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/Source/CERNLIB'
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.none_d_inl0_hrd0/libmg5amc_gg_ttxgg_cpp.so build.none_d_inl0_hrd0/CPPProcess.o build.none_d_inl0_hrd0/MatrixElementKernels.o build.none_d_inl0_hrd0/BridgeKernels.o build.none_d_inl0_hrd0/CrossSectionKernels.o build.none_d_inl0_hrd0/fbridge.o -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common
-ar cru  ../../lib/libpdf.a  Ctq6Pdf.o pdfwrap.o opendata.o pdf.o PhotonFlux.o pdg2pdf.o NNPDFDriver.o eepdf.o gridpdfaux.o dfint.o kerset.o ElectroweakFluxDriver.o ElectroweakFlux.o
-ranlib  ../../lib/libpdf.a
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/Source/PDF'
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_d_inl0_hrd0/check.exe build.none_d_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_gg_ttxgg_cpp build.none_d_inl0_hrd0/RandomNumberKernels.o build.none_d_inl0_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_d_inl0_hrd0/fcheck.exe build.none_d_inl0_hrd0/fcheck_sa.o build.none_d_inl0_hrd0/fsampler.o -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_gg_ttxgg_cpp build.none_d_inl0_hrd0/RandomNumberKernels.o build.none_d_inl0_hrd0/RamboSamplingKernels.o
 ar cru  ../../lib/libdhelas.a  aloha_functions.o VVV1_0.o VVVV3P0_1.o FFV1_1.o VVVV4P0_1.o VVVV3_0.o FFV1P0_3.o FFV1_0.o FFV1_2.o VVVV1_0.o VVVV1P0_1.o VVVV4_0.o VVV1P0_1.o
 ranlib  ../../lib/libdhelas.a
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/Source/DHELAS'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/Source/DHELAS'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.none_d_inl0_hrd0/libmg5amc_common.so build.none_d_inl0_hrd0/Parameters_sm.o build.none_d_inl0_hrd0/read_slha.o
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.none_d_inl0_hrd0/libmg5amc_gg_ttxgg_cpp.so build.none_d_inl0_hrd0/CPPProcess.o build.none_d_inl0_hrd0/MatrixElementKernels.o build.none_d_inl0_hrd0/BridgeKernels.o build.none_d_inl0_hrd0/CrossSectionKernels.o build.none_d_inl0_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_d_inl0_hrd0/check.exe build.none_d_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_d_inl0_hrd0'  -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_gg_ttxgg_cpp build.none_d_inl0_hrd0/RandomNumberKernels.o build.none_d_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_d_inl0_hrd0/fcheck.exe build.none_d_inl0_hrd0/fcheck_sa.o build.none_d_inl0_hrd0/fsampler.o -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_d_inl0_hrd0'  -lgfortran -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_gg_ttxgg_cpp build.none_d_inl0_hrd0/RandomNumberKernels.o build.none_d_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132  -c -o dsample.o dsample.f
 ar cru  ../lib/libdsample.a  dsample.o ranmar.o DiscreteSampler.o StringCast.o
 ranlib  ../lib/libdsample.a
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/Source'
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/Source'
 touch .libs
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -w -cpp  -c genps.f -I../../Source/ -fopenmp -o genps.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -w -cpp  -c driver.f -I../../Source/ -fopenmp -o driver.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -w -cpp  -c auto_dsig.f -I../../Source/ -fopenmp -o auto_dsig.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -w -cpp   -c matrix1.f -I../../Source/ -fopenmp
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -w -fPIC -O3 -ffast-math -fbounds-check -ffixed-line-length-132 -w -cpp  -c -DMG5AMC_MEEXPORTER_CUDACPP driver.f -I../../Source/ -fopenmp -o driver_cudacpp.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o madevent myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver.o  auto_dsig1.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.none_d_inl0_hrd0/libmg5amc_gg_ttxgg_cuda.so build.none_d_inl0_hrd0/gCPPProcess.o build.none_d_inl0_hrd0/gMatrixElementKernels.o build.none_d_inl0_hrd0/gBridgeKernels.o build.none_d_inl0_hrd0/gCrossSectionKernels.o build.none_d_inl0_hrd0/fbridge_cu.o -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl0_hrd0/runTest.exe build.none_d_inl0_hrd0/CPPProcess.o build.none_d_inl0_hrd0/MatrixElementKernels.o build.none_d_inl0_hrd0/BridgeKernels.o build.none_d_inl0_hrd0/CrossSectionKernels.o build.none_d_inl0_hrd0/RandomNumberKernels.o build.none_d_inl0_hrd0/RamboSamplingKernels.o build.none_d_inl0_hrd0/testxxx.o  build.none_d_inl0_hrd0/testmisc.o  build.none_d_inl0_hrd0/runTest.o build.none_d_inl0_hrd0/gCPPProcess.o build.none_d_inl0_hrd0/gMatrixElementKernels.o build.none_d_inl0_hrd0/gBridgeKernels.o build.none_d_inl0_hrd0/gCrossSectionKernels.o build.none_d_inl0_hrd0/gRandomNumberKernels.o build.none_d_inl0_hrd0/gRamboSamplingKernels.o build.none_d_inl0_hrd0/testxxx_cu.o  build.none_d_inl0_hrd0/testmisc_cu.o  build.none_d_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl0_hrd0/gcheck.exe build.none_d_inl0_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_gg_ttxgg_cuda build.none_d_inl0_hrd0/gRandomNumberKernels.o build.none_d_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl0_hrd0/fgcheck.exe build.none_d_inl0_hrd0/fcheck_sa.o build.none_d_inl0_hrd0/fsampler_cu.o -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_gg_ttxgg_cuda build.none_d_inl0_hrd0/gRandomNumberKernels.o build.none_d_inl0_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o madevent myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver.o  auto_dsig1.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -lstdc++  -Wl,--no-relax 
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.none_d_inl0_hrd0/libmg5amc_gg_ttxgg_cuda.so build.none_d_inl0_hrd0/gCPPProcess.o build.none_d_inl0_hrd0/gMatrixElementKernels.o build.none_d_inl0_hrd0/gBridgeKernels.o build.none_d_inl0_hrd0/gCrossSectionKernels.o build.none_d_inl0_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl0_hrd0/runTest.exe build.none_d_inl0_hrd0/CPPProcess.o build.none_d_inl0_hrd0/MatrixElementKernels.o build.none_d_inl0_hrd0/BridgeKernels.o build.none_d_inl0_hrd0/CrossSectionKernels.o build.none_d_inl0_hrd0/RandomNumberKernels.o build.none_d_inl0_hrd0/RamboSamplingKernels.o build.none_d_inl0_hrd0/testxxx.o  build.none_d_inl0_hrd0/testmisc.o  build.none_d_inl0_hrd0/runTest.o build.none_d_inl0_hrd0/gCPPProcess.o build.none_d_inl0_hrd0/gMatrixElementKernels.o build.none_d_inl0_hrd0/gBridgeKernels.o build.none_d_inl0_hrd0/gCrossSectionKernels.o build.none_d_inl0_hrd0/gRandomNumberKernels.o build.none_d_inl0_hrd0/gRamboSamplingKernels.o build.none_d_inl0_hrd0/testxxx_cu.o  build.none_d_inl0_hrd0/testmisc_cu.o  build.none_d_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl0_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl0_hrd0/gcheck.exe build.none_d_inl0_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl0_hrd0'  -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_gg_ttxgg_cuda build.none_d_inl0_hrd0/gRandomNumberKernels.o build.none_d_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl0_hrd0/fgcheck.exe build.none_d_inl0_hrd0/fcheck_sa.o build.none_d_inl0_hrd0/fsampler_cu.o -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl0_hrd0'  -lgfortran -L../../lib/build.none_d_inl0_hrd0 -lmg5amc_gg_ttxgg_cuda build.none_d_inl0_hrd0/gRandomNumberKernels.o build.none_d_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
 touch build.none_d_inl0_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_d_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.none_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.none_d_inl0_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_d_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.none_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.none_d_inl0_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.none_d_inl0_hrd0/libmg5amc_gg_ttxgg_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_d_inl0_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.none_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.none_d_inl0_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
 CUDACPP_BUILDDIR='build.512y_d_inl0_hrd0'
 make -f cudacpp.mk
@@ -6350,82 +6409,83 @@ HELINL=0
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.512y_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.512y_d_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gcheck_sa.cu -o build.512y_d_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gcheck_sa.cu -o build.512y_d_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gCPPProcess.cu -o build.512y_d_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512y_d_inl0_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512y_d_inl0_hrd0/gBridgeKernels.o
 AVX=512y
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gCPPProcess.cu -o build.512y_d_inl0_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512y_d_inl0_hrd0/gMatrixElementKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512y_d_inl0_hrd0/gBridgeKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512y_d_inl0_hrd0/gCrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -c Parameters_sm.cc -o build.512y_d_inl0_hrd0/Parameters_sm.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512y_d_inl0_hrd0/fbridge_cu.o
-mkdir -p ../lib/build.512y_d_inl0_hrd0
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -c read_slha.cc -o build.512y_d_inl0_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512y_d_inl0_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512y_d_inl0_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512y_d_inl0_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512y_d_inl0_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512y_d_inl0_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512y_d_inl0_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.512y_d_inl0_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.512y_d_inl0_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.512y_d_inl0_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.512y_d_inl0_hrd0/BridgeKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.512y_d_inl0_hrd0/CrossSectionKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.512y_d_inl0_hrd0/fbridge.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -c Parameters_sm.cc -o build.512y_d_inl0_hrd0/Parameters_sm.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -c read_slha.cc -o build.512y_d_inl0_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.512y_d_inl0_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.512y_d_inl0_hrd0/RamboSamplingKernels.o
+mkdir -p ../lib/build.512y_d_inl0_hrd0
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.512y_d_inl0_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512y_d_inl0_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512y_d_inl0_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.512y_d_inl0_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512y_d_inl0_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512y_d_inl0_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.512y_d_inl0_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu runTest.cc -o build.512y_d_inl0_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu runTest.cc -o build.512y_d_inl0_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.512y_d_inl0_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512y_d_inl0_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512y_d_inl0_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.512y_d_inl0_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.512y_d_inl0_hrd0/libmg5amc_common.so build.512y_d_inl0_hrd0/Parameters_sm.o build.512y_d_inl0_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512y_d_inl0_hrd0/libmg5amc_gg_ttxgg_cuda.so build.512y_d_inl0_hrd0/gCPPProcess.o build.512y_d_inl0_hrd0/gMatrixElementKernels.o build.512y_d_inl0_hrd0/gBridgeKernels.o build.512y_d_inl0_hrd0/gCrossSectionKernels.o build.512y_d_inl0_hrd0/fbridge_cu.o -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512y_d_inl0_hrd0/libmg5amc_gg_ttxgg_cpp.so build.512y_d_inl0_hrd0/CPPProcess.o build.512y_d_inl0_hrd0/MatrixElementKernels.o build.512y_d_inl0_hrd0/BridgeKernels.o build.512y_d_inl0_hrd0/CrossSectionKernels.o build.512y_d_inl0_hrd0/fbridge.o -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl0_hrd0/runTest.exe build.512y_d_inl0_hrd0/CPPProcess.o build.512y_d_inl0_hrd0/MatrixElementKernels.o build.512y_d_inl0_hrd0/BridgeKernels.o build.512y_d_inl0_hrd0/CrossSectionKernels.o build.512y_d_inl0_hrd0/RandomNumberKernels.o build.512y_d_inl0_hrd0/RamboSamplingKernels.o build.512y_d_inl0_hrd0/testxxx.o  build.512y_d_inl0_hrd0/testmisc.o  build.512y_d_inl0_hrd0/runTest.o build.512y_d_inl0_hrd0/gCPPProcess.o build.512y_d_inl0_hrd0/gMatrixElementKernels.o build.512y_d_inl0_hrd0/gBridgeKernels.o build.512y_d_inl0_hrd0/gCrossSectionKernels.o build.512y_d_inl0_hrd0/gRandomNumberKernels.o build.512y_d_inl0_hrd0/gRamboSamplingKernels.o build.512y_d_inl0_hrd0/testxxx_cu.o  build.512y_d_inl0_hrd0/testmisc_cu.o  build.512y_d_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_d_inl0_hrd0/check.exe build.512y_d_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_gg_ttxgg_cpp build.512y_d_inl0_hrd0/RandomNumberKernels.o build.512y_d_inl0_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_d_inl0_hrd0/fcheck.exe build.512y_d_inl0_hrd0/fcheck_sa.o build.512y_d_inl0_hrd0/fsampler.o -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_gg_ttxgg_cpp build.512y_d_inl0_hrd0/RandomNumberKernels.o build.512y_d_inl0_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl0_hrd0/gcheck.exe build.512y_d_inl0_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_gg_ttxgg_cuda build.512y_d_inl0_hrd0/gRandomNumberKernels.o build.512y_d_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl0_hrd0/fgcheck.exe build.512y_d_inl0_hrd0/fcheck_sa.o build.512y_d_inl0_hrd0/fsampler_cu.o -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_gg_ttxgg_cuda build.512y_d_inl0_hrd0/gRandomNumberKernels.o build.512y_d_inl0_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512y_d_inl0_hrd0/libmg5amc_gg_ttxgg_cuda.so build.512y_d_inl0_hrd0/gCPPProcess.o build.512y_d_inl0_hrd0/gMatrixElementKernels.o build.512y_d_inl0_hrd0/gBridgeKernels.o build.512y_d_inl0_hrd0/gCrossSectionKernels.o build.512y_d_inl0_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl0_hrd0/gcheck.exe build.512y_d_inl0_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl0_hrd0'  -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_gg_ttxgg_cuda build.512y_d_inl0_hrd0/gRandomNumberKernels.o build.512y_d_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl0_hrd0/fgcheck.exe build.512y_d_inl0_hrd0/fcheck_sa.o build.512y_d_inl0_hrd0/fsampler_cu.o -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl0_hrd0'  -lgfortran -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_gg_ttxgg_cuda build.512y_d_inl0_hrd0/gRandomNumberKernels.o build.512y_d_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512y_d_inl0_hrd0/libmg5amc_gg_ttxgg_cpp.so build.512y_d_inl0_hrd0/CPPProcess.o build.512y_d_inl0_hrd0/MatrixElementKernels.o build.512y_d_inl0_hrd0/BridgeKernels.o build.512y_d_inl0_hrd0/CrossSectionKernels.o build.512y_d_inl0_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_d_inl0_hrd0/fcheck.exe build.512y_d_inl0_hrd0/fcheck_sa.o build.512y_d_inl0_hrd0/fsampler.o -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_d_inl0_hrd0'  -lgfortran -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_gg_ttxgg_cpp build.512y_d_inl0_hrd0/RandomNumberKernels.o build.512y_d_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_d_inl0_hrd0/check.exe build.512y_d_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_d_inl0_hrd0'  -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_gg_ttxgg_cpp build.512y_d_inl0_hrd0/RandomNumberKernels.o build.512y_d_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl0_hrd0/runTest.exe build.512y_d_inl0_hrd0/CPPProcess.o build.512y_d_inl0_hrd0/MatrixElementKernels.o build.512y_d_inl0_hrd0/BridgeKernels.o build.512y_d_inl0_hrd0/CrossSectionKernels.o build.512y_d_inl0_hrd0/RandomNumberKernels.o build.512y_d_inl0_hrd0/RamboSamplingKernels.o build.512y_d_inl0_hrd0/testxxx.o  build.512y_d_inl0_hrd0/testmisc.o  build.512y_d_inl0_hrd0/runTest.o build.512y_d_inl0_hrd0/gCPPProcess.o build.512y_d_inl0_hrd0/gMatrixElementKernels.o build.512y_d_inl0_hrd0/gBridgeKernels.o build.512y_d_inl0_hrd0/gCrossSectionKernels.o build.512y_d_inl0_hrd0/gRandomNumberKernels.o build.512y_d_inl0_hrd0/gRamboSamplingKernels.o build.512y_d_inl0_hrd0/testxxx_cu.o  build.512y_d_inl0_hrd0/testmisc_cu.o  build.512y_d_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.512y_d_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl0_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
 touch build.512y_d_inl0_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_d_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.512y_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_d_inl0_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_d_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512y_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_d_inl0_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.512y_d_inl0_hrd0/libmg5amc_gg_ttxgg_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_d_inl0_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512y_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_d_inl0_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:07:50
+DATE: 2022-09-25_00:15:46
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/gcheck.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/gcheck.exe -p 64 256 2 OMP=
 Process                     = SIGMA_SM_GG_TTXGG_CUDA [nvcc 11.7.99 (gcc 11.2.0)] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
-EvtsPerSec[Rmb+ME]     (23) = ( 3.618923e+05                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 3.650934e+05                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 3.653181e+05                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 4.772922e+04                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 4.780844e+04                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 4.781239e+04                 )  sec^-1
 MeanMatrixElemValue         = ( 2.520822e+00 +- 1.235793e+00 )  GeV^-4
-TOTAL       :     0.645562 sec
-real	0m0.938s
-==PROF== Profiling "sigmaKin": launch__registers_per_thread 255
-==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100%
+TOTAL       :     3.462805 sec
+real	0m3.905s
+   launch__registers_per_thread N/A
+   sm__sass_average_branch_targets_threads_uniform.pct N/A
 .........................................................................
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/gcheck.exe -p 2048 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/gcheck.exe -p 2048 256 2 OMP=
 Process                     = SIGMA_SM_GG_TTXGG_CUDA [nvcc 11.7.99 (gcc 11.2.0)] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
-EvtsPerSec[Rmb+ME]     (23) = ( 4.164502e+05                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 4.199363e+05                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 4.200846e+05                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 5.539750e+04                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 5.548635e+04                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 5.548891e+04                 )  sec^-1
 MeanMatrixElemValue         = ( 1.559350e+01 +- 8.724727e+00 )  GeV^-4
-TOTAL       :     4.391623 sec
-real	0m4.727s
+TOTAL       :    30.737724 sec
+real	0m31.223s
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/gcheck.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/fgcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/gcheck.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/fgcheck.exe 2 64 2
 Avg ME (C++/CUDA)   = 6.626675e-04
 Avg ME (F77/CUDA)   = 6.6266731198158133E-004
 Relative difference = 2.837296512218831e-07
@@ -6433,12 +6493,12 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:08:01 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -nocpp  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:16:46 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -nocpp  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
 CUDACPP_BUILDDIR='build.none_d_inl1_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -6448,51 +6508,52 @@ HELINL=1
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.none_d_inl1_hrd0 for tag=none_d_inl1_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.none_d_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.none_d_inl1_hrd0/gcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.none_d_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.none_d_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.none_d_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.none_d_inl1_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.none_d_inl1_hrd0/gBridgeKernels.o
 AVX=none
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.none_d_inl1_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.none_d_inl1_hrd0/gBridgeKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.none_d_inl1_hrd0/gCrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.none_d_inl1_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.none_d_inl1_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.none_d_inl1_hrd0/fbridge_cu.o
-mkdir -p ../lib/build.none_d_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.none_d_inl1_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.none_d_inl1_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.none_d_inl1_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.none_d_inl1_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.none_d_inl1_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.none_d_inl1_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.none_d_inl1_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.none_d_inl1_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.none_d_inl1_hrd0/MatrixElementKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.none_d_inl1_hrd0/BridgeKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.none_d_inl1_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.none_d_inl1_hrd0/fbridge.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.none_d_inl1_hrd0/RandomNumberKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.none_d_inl1_hrd0/Parameters_sm.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.none_d_inl1_hrd0/RamboSamplingKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.none_d_inl1_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.none_d_inl1_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.none_d_inl1_hrd0/testxxx_cu.o
+mkdir -p ../lib/build.none_d_inl1_hrd0
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.none_d_inl1_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.none_d_inl1_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.none_d_inl1_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.none_d_inl1_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.none_d_inl1_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.none_d_inl1_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.none_d_inl1_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.none_d_inl1_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.none_d_inl1_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.none_d_inl1_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.none_d_inl1_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.none_d_inl1_hrd0/libmg5amc_common.so build.none_d_inl1_hrd0/Parameters_sm.o build.none_d_inl1_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.none_d_inl1_hrd0/libmg5amc_gg_ttxgg_cpp.so build.none_d_inl1_hrd0/CPPProcess.o build.none_d_inl1_hrd0/MatrixElementKernels.o build.none_d_inl1_hrd0/BridgeKernels.o build.none_d_inl1_hrd0/CrossSectionKernels.o build.none_d_inl1_hrd0/fbridge.o -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_d_inl1_hrd0/check.exe build.none_d_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_gg_ttxgg_cpp build.none_d_inl1_hrd0/RandomNumberKernels.o build.none_d_inl1_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_d_inl1_hrd0/fcheck.exe build.none_d_inl1_hrd0/fcheck_sa.o build.none_d_inl1_hrd0/fsampler.o -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_gg_ttxgg_cpp build.none_d_inl1_hrd0/RandomNumberKernels.o build.none_d_inl1_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.none_d_inl1_hrd0/libmg5amc_gg_ttxgg_cuda.so build.none_d_inl1_hrd0/gCPPProcess.o build.none_d_inl1_hrd0/gMatrixElementKernels.o build.none_d_inl1_hrd0/gBridgeKernels.o build.none_d_inl1_hrd0/gCrossSectionKernels.o build.none_d_inl1_hrd0/fbridge_cu.o -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl1_hrd0/runTest.exe build.none_d_inl1_hrd0/CPPProcess.o build.none_d_inl1_hrd0/MatrixElementKernels.o build.none_d_inl1_hrd0/BridgeKernels.o build.none_d_inl1_hrd0/CrossSectionKernels.o build.none_d_inl1_hrd0/RandomNumberKernels.o build.none_d_inl1_hrd0/RamboSamplingKernels.o build.none_d_inl1_hrd0/testxxx.o  build.none_d_inl1_hrd0/testmisc.o  build.none_d_inl1_hrd0/runTest.o build.none_d_inl1_hrd0/gCPPProcess.o build.none_d_inl1_hrd0/gMatrixElementKernels.o build.none_d_inl1_hrd0/gBridgeKernels.o build.none_d_inl1_hrd0/gCrossSectionKernels.o build.none_d_inl1_hrd0/gRandomNumberKernels.o build.none_d_inl1_hrd0/gRamboSamplingKernels.o build.none_d_inl1_hrd0/testxxx_cu.o  build.none_d_inl1_hrd0/testmisc_cu.o  build.none_d_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl1_hrd0/gcheck.exe build.none_d_inl1_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_gg_ttxgg_cuda build.none_d_inl1_hrd0/gRandomNumberKernels.o build.none_d_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl1_hrd0/fgcheck.exe build.none_d_inl1_hrd0/fcheck_sa.o build.none_d_inl1_hrd0/fsampler_cu.o -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_gg_ttxgg_cuda build.none_d_inl1_hrd0/gRandomNumberKernels.o build.none_d_inl1_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.none_d_inl1_hrd0/libmg5amc_gg_ttxgg_cpp.so build.none_d_inl1_hrd0/CPPProcess.o build.none_d_inl1_hrd0/MatrixElementKernels.o build.none_d_inl1_hrd0/BridgeKernels.o build.none_d_inl1_hrd0/CrossSectionKernels.o build.none_d_inl1_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_d_inl1_hrd0/check.exe build.none_d_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_d_inl1_hrd0'  -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_gg_ttxgg_cpp build.none_d_inl1_hrd0/RandomNumberKernels.o build.none_d_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_d_inl1_hrd0/fcheck.exe build.none_d_inl1_hrd0/fcheck_sa.o build.none_d_inl1_hrd0/fsampler.o -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_d_inl1_hrd0'  -lgfortran -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_gg_ttxgg_cpp build.none_d_inl1_hrd0/RandomNumberKernels.o build.none_d_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.none_d_inl1_hrd0/libmg5amc_gg_ttxgg_cuda.so build.none_d_inl1_hrd0/gCPPProcess.o build.none_d_inl1_hrd0/gMatrixElementKernels.o build.none_d_inl1_hrd0/gBridgeKernels.o build.none_d_inl1_hrd0/gCrossSectionKernels.o build.none_d_inl1_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl1_hrd0/runTest.exe build.none_d_inl1_hrd0/CPPProcess.o build.none_d_inl1_hrd0/MatrixElementKernels.o build.none_d_inl1_hrd0/BridgeKernels.o build.none_d_inl1_hrd0/CrossSectionKernels.o build.none_d_inl1_hrd0/RandomNumberKernels.o build.none_d_inl1_hrd0/RamboSamplingKernels.o build.none_d_inl1_hrd0/testxxx.o  build.none_d_inl1_hrd0/testmisc.o  build.none_d_inl1_hrd0/runTest.o build.none_d_inl1_hrd0/gCPPProcess.o build.none_d_inl1_hrd0/gMatrixElementKernels.o build.none_d_inl1_hrd0/gBridgeKernels.o build.none_d_inl1_hrd0/gCrossSectionKernels.o build.none_d_inl1_hrd0/gRandomNumberKernels.o build.none_d_inl1_hrd0/gRamboSamplingKernels.o build.none_d_inl1_hrd0/testxxx_cu.o  build.none_d_inl1_hrd0/testmisc_cu.o  build.none_d_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl1_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl1_hrd0/gcheck.exe build.none_d_inl1_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl1_hrd0'  -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_gg_ttxgg_cuda build.none_d_inl1_hrd0/gRandomNumberKernels.o build.none_d_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_d_inl1_hrd0/fgcheck.exe build.none_d_inl1_hrd0/fcheck_sa.o build.none_d_inl1_hrd0/fsampler_cu.o -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_d_inl1_hrd0'  -lgfortran -L../../lib/build.none_d_inl1_hrd0 -lmg5amc_gg_ttxgg_cuda build.none_d_inl1_hrd0/gRandomNumberKernels.o build.none_d_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
 touch build.none_d_inl1_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_d_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.none_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.none_d_inl1_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_d_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.none_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.none_d_inl1_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.none_d_inl1_hrd0/libmg5amc_gg_ttxgg_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_d_inl1_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.none_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.none_d_inl1_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
 CUDACPP_BUILDDIR='build.512y_d_inl1_hrd0'
 make -f cudacpp.mk
@@ -6503,82 +6564,84 @@ HELINL=1
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.512y_d_inl1_hrd0 for tag=512y_d_inl1_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.512y_d_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.512y_d_inl1_hrd0/gcheck_sa.o
+mkdir -p build.512y_d_inl1_hrd0
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.512y_d_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.512y_d_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512y_d_inl1_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512y_d_inl1_hrd0/gBridgeKernels.o
 AVX=512y
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.512y_d_inl1_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512y_d_inl1_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512y_d_inl1_hrd0/gBridgeKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512y_d_inl1_hrd0/gCrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.512y_d_inl1_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512y_d_inl1_hrd0/fbridge_cu.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.512y_d_inl1_hrd0/Parameters_sm.o
-mkdir -p ../lib/build.512y_d_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512y_d_inl1_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512y_d_inl1_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512y_d_inl1_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512y_d_inl1_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512y_d_inl1_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512y_d_inl1_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.512y_d_inl1_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.512y_d_inl1_hrd0/CPPProcess.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.512y_d_inl1_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.512y_d_inl1_hrd0/BridgeKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.512y_d_inl1_hrd0/Parameters_sm.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.512y_d_inl1_hrd0/CrossSectionKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.512y_d_inl1_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.512y_d_inl1_hrd0/fbridge.o
+mkdir -p ../lib/build.512y_d_inl1_hrd0
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.512y_d_inl1_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.512y_d_inl1_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.512y_d_inl1_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512y_d_inl1_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512y_d_inl1_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.512y_d_inl1_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512y_d_inl1_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512y_d_inl1_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.512y_d_inl1_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.512y_d_inl1_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.512y_d_inl1_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.512y_d_inl1_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512y_d_inl1_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512y_d_inl1_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.512y_d_inl1_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.512y_d_inl1_hrd0/libmg5amc_common.so build.512y_d_inl1_hrd0/Parameters_sm.o build.512y_d_inl1_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512y_d_inl1_hrd0/libmg5amc_gg_ttxgg_cuda.so build.512y_d_inl1_hrd0/gCPPProcess.o build.512y_d_inl1_hrd0/gMatrixElementKernels.o build.512y_d_inl1_hrd0/gBridgeKernels.o build.512y_d_inl1_hrd0/gCrossSectionKernels.o build.512y_d_inl1_hrd0/fbridge_cu.o -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512y_d_inl1_hrd0/libmg5amc_gg_ttxgg_cpp.so build.512y_d_inl1_hrd0/CPPProcess.o build.512y_d_inl1_hrd0/MatrixElementKernels.o build.512y_d_inl1_hrd0/BridgeKernels.o build.512y_d_inl1_hrd0/CrossSectionKernels.o build.512y_d_inl1_hrd0/fbridge.o -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl1_hrd0/runTest.exe build.512y_d_inl1_hrd0/CPPProcess.o build.512y_d_inl1_hrd0/MatrixElementKernels.o build.512y_d_inl1_hrd0/BridgeKernels.o build.512y_d_inl1_hrd0/CrossSectionKernels.o build.512y_d_inl1_hrd0/RandomNumberKernels.o build.512y_d_inl1_hrd0/RamboSamplingKernels.o build.512y_d_inl1_hrd0/testxxx.o  build.512y_d_inl1_hrd0/testmisc.o  build.512y_d_inl1_hrd0/runTest.o build.512y_d_inl1_hrd0/gCPPProcess.o build.512y_d_inl1_hrd0/gMatrixElementKernels.o build.512y_d_inl1_hrd0/gBridgeKernels.o build.512y_d_inl1_hrd0/gCrossSectionKernels.o build.512y_d_inl1_hrd0/gRandomNumberKernels.o build.512y_d_inl1_hrd0/gRamboSamplingKernels.o build.512y_d_inl1_hrd0/testxxx_cu.o  build.512y_d_inl1_hrd0/testmisc_cu.o  build.512y_d_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_d_inl1_hrd0/check.exe build.512y_d_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_gg_ttxgg_cpp build.512y_d_inl1_hrd0/RandomNumberKernels.o build.512y_d_inl1_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_d_inl1_hrd0/fcheck.exe build.512y_d_inl1_hrd0/fcheck_sa.o build.512y_d_inl1_hrd0/fsampler.o -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_gg_ttxgg_cpp build.512y_d_inl1_hrd0/RandomNumberKernels.o build.512y_d_inl1_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl1_hrd0/gcheck.exe build.512y_d_inl1_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_gg_ttxgg_cuda build.512y_d_inl1_hrd0/gRandomNumberKernels.o build.512y_d_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl1_hrd0/fgcheck.exe build.512y_d_inl1_hrd0/fcheck_sa.o build.512y_d_inl1_hrd0/fsampler_cu.o -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_gg_ttxgg_cuda build.512y_d_inl1_hrd0/gRandomNumberKernels.o build.512y_d_inl1_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512y_d_inl1_hrd0/libmg5amc_gg_ttxgg_cuda.so build.512y_d_inl1_hrd0/gCPPProcess.o build.512y_d_inl1_hrd0/gMatrixElementKernels.o build.512y_d_inl1_hrd0/gBridgeKernels.o build.512y_d_inl1_hrd0/gCrossSectionKernels.o build.512y_d_inl1_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl1_hrd0/gcheck.exe build.512y_d_inl1_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl1_hrd0'  -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_gg_ttxgg_cuda build.512y_d_inl1_hrd0/gRandomNumberKernels.o build.512y_d_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl1_hrd0/fgcheck.exe build.512y_d_inl1_hrd0/fcheck_sa.o build.512y_d_inl1_hrd0/fsampler_cu.o -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl1_hrd0'  -lgfortran -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_gg_ttxgg_cuda build.512y_d_inl1_hrd0/gRandomNumberKernels.o build.512y_d_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512y_d_inl1_hrd0/libmg5amc_gg_ttxgg_cpp.so build.512y_d_inl1_hrd0/CPPProcess.o build.512y_d_inl1_hrd0/MatrixElementKernels.o build.512y_d_inl1_hrd0/BridgeKernels.o build.512y_d_inl1_hrd0/CrossSectionKernels.o build.512y_d_inl1_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_d_inl1_hrd0/runTest.exe build.512y_d_inl1_hrd0/CPPProcess.o build.512y_d_inl1_hrd0/MatrixElementKernels.o build.512y_d_inl1_hrd0/BridgeKernels.o build.512y_d_inl1_hrd0/CrossSectionKernels.o build.512y_d_inl1_hrd0/RandomNumberKernels.o build.512y_d_inl1_hrd0/RamboSamplingKernels.o build.512y_d_inl1_hrd0/testxxx.o  build.512y_d_inl1_hrd0/testmisc.o  build.512y_d_inl1_hrd0/runTest.o build.512y_d_inl1_hrd0/gCPPProcess.o build.512y_d_inl1_hrd0/gMatrixElementKernels.o build.512y_d_inl1_hrd0/gBridgeKernels.o build.512y_d_inl1_hrd0/gCrossSectionKernels.o build.512y_d_inl1_hrd0/gRandomNumberKernels.o build.512y_d_inl1_hrd0/gRamboSamplingKernels.o build.512y_d_inl1_hrd0/testxxx_cu.o  build.512y_d_inl1_hrd0/testmisc_cu.o  build.512y_d_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_d_inl1_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_d_inl1_hrd0/check.exe build.512y_d_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_d_inl1_hrd0'  -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_gg_ttxgg_cpp build.512y_d_inl1_hrd0/RandomNumberKernels.o build.512y_d_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_d_inl1_hrd0/fcheck.exe build.512y_d_inl1_hrd0/fcheck_sa.o build.512y_d_inl1_hrd0/fsampler.o -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_d_inl1_hrd0'  -lgfortran -L../../lib/build.512y_d_inl1_hrd0 -lmg5amc_gg_ttxgg_cpp build.512y_d_inl1_hrd0/RandomNumberKernels.o build.512y_d_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
 touch build.512y_d_inl1_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_d_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.512y_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_d_inl1_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_d_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512y_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_d_inl1_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.512y_d_inl1_hrd0/libmg5amc_gg_ttxgg_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_d_inl1_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512y_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_d_inl1_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:08:40
+DATE: 2022-09-25_00:19:23
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl1_hrd0/gcheck.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl1_hrd0/gcheck.exe -p 64 256 2 OMP=
 Process                     = SIGMA_SM_GG_TTXGG_CUDA [nvcc 11.7.99 (gcc 11.2.0)] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
-EvtsPerSec[Rmb+ME]     (23) = ( 3.452885e+05                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 3.480546e+05                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 3.482567e+05                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 5.454872e+04                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 5.464877e+04                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 5.465340e+04                 )  sec^-1
 MeanMatrixElemValue         = ( 2.520822e+00 +- 1.235793e+00 )  GeV^-4
-TOTAL       :     0.646590 sec
-real	0m0.939s
-==PROF== Profiling "sigmaKin": launch__registers_per_thread 255
-==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100%
+TOTAL       :     3.310115 sec
+real	0m3.744s
+   launch__registers_per_thread N/A
+   sm__sass_average_branch_targets_threads_uniform.pct N/A
 .........................................................................
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl1_hrd0/gcheck.exe -p 2048 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl1_hrd0/gcheck.exe -p 2048 256 2 OMP=
 Process                     = SIGMA_SM_GG_TTXGG_CUDA [nvcc 11.7.99 (gcc 11.2.0)] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
-EvtsPerSec[Rmb+ME]     (23) = ( 3.837595e+05                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 3.867223e+05                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 3.868472e+05                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 6.267049e+04                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 6.278426e+04                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 6.278756e+04                 )  sec^-1
 MeanMatrixElemValue         = ( 1.559350e+01 +- 8.724727e+00 )  GeV^-4
-TOTAL       :     4.726024 sec
-real	0m5.048s
+TOTAL       :    27.457109 sec
+real	0m27.929s
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl1_hrd0/gcheck.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl1_hrd0/fgcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl1_hrd0/gcheck.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl1_hrd0/fgcheck.exe 2 64 2
 Avg ME (C++/CUDA)   = 6.626675e-04
 Avg ME (F77/CUDA)   = 6.6266731198158122E-004
 Relative difference = 2.837296513854949e-07
@@ -6586,12 +6649,12 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:08:51 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -nocpp -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:20:20 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -nocpp -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
 CUDACPP_BUILDDIR='build.none_f_inl0_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -6601,51 +6664,52 @@ HELINL=0
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.none_f_inl0_hrd0 for tag=none_f_inl0_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.none_f_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gcheck_sa.cu -o build.none_f_inl0_hrd0/gcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gCPPProcess.cu -o build.none_f_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gcheck_sa.cu -o build.none_f_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gCPPProcess.cu -o build.none_f_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.none_f_inl0_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gBridgeKernels.cu -o build.none_f_inl0_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.none_f_inl0_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fbridge.cc -o build.none_f_inl0_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.none_f_inl0_hrd0/gRandomNumberKernels.o
 AVX=none
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.none_f_inl0_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gBridgeKernels.cu -o build.none_f_inl0_hrd0/gBridgeKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.none_f_inl0_hrd0/gCrossSectionKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fbridge.cc -o build.none_f_inl0_hrd0/fbridge_cu.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -c Parameters_sm.cc -o build.none_f_inl0_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -c read_slha.cc -o build.none_f_inl0_hrd0/read_slha.o
-mkdir -p ../lib/build.none_f_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.none_f_inl0_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.none_f_inl0_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.none_f_inl0_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.none_f_inl0_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.none_f_inl0_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.none_f_inl0_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.none_f_inl0_hrd0/BridgeKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.none_f_inl0_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.none_f_inl0_hrd0/fbridge.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.none_f_inl0_hrd0/RandomNumberKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -c Parameters_sm.cc -o build.none_f_inl0_hrd0/Parameters_sm.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.none_f_inl0_hrd0/RamboSamplingKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -c read_slha.cc -o build.none_f_inl0_hrd0/read_slha.o
+mkdir -p ../lib/build.none_f_inl0_hrd0
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.none_f_inl0_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testxxx.cc -o build.none_f_inl0_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testxxx.cc -o build.none_f_inl0_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.none_f_inl0_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testmisc.cc -o build.none_f_inl0_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testmisc.cc -o build.none_f_inl0_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.none_f_inl0_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu runTest.cc -o build.none_f_inl0_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu runTest.cc -o build.none_f_inl0_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.none_f_inl0_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fsampler.cc -o build.none_f_inl0_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fsampler.cc -o build.none_f_inl0_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.none_f_inl0_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.none_f_inl0_hrd0/libmg5amc_common.so build.none_f_inl0_hrd0/Parameters_sm.o build.none_f_inl0_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.none_f_inl0_hrd0/libmg5amc_gg_ttxgg_cpp.so build.none_f_inl0_hrd0/CPPProcess.o build.none_f_inl0_hrd0/MatrixElementKernels.o build.none_f_inl0_hrd0/BridgeKernels.o build.none_f_inl0_hrd0/CrossSectionKernels.o build.none_f_inl0_hrd0/fbridge.o -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_f_inl0_hrd0/check.exe build.none_f_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_gg_ttxgg_cpp build.none_f_inl0_hrd0/RandomNumberKernels.o build.none_f_inl0_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_f_inl0_hrd0/fcheck.exe build.none_f_inl0_hrd0/fcheck_sa.o build.none_f_inl0_hrd0/fsampler.o -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_gg_ttxgg_cpp build.none_f_inl0_hrd0/RandomNumberKernels.o build.none_f_inl0_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.none_f_inl0_hrd0/libmg5amc_gg_ttxgg_cuda.so build.none_f_inl0_hrd0/gCPPProcess.o build.none_f_inl0_hrd0/gMatrixElementKernels.o build.none_f_inl0_hrd0/gBridgeKernels.o build.none_f_inl0_hrd0/gCrossSectionKernels.o build.none_f_inl0_hrd0/fbridge_cu.o -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl0_hrd0/runTest.exe build.none_f_inl0_hrd0/CPPProcess.o build.none_f_inl0_hrd0/MatrixElementKernels.o build.none_f_inl0_hrd0/BridgeKernels.o build.none_f_inl0_hrd0/CrossSectionKernels.o build.none_f_inl0_hrd0/RandomNumberKernels.o build.none_f_inl0_hrd0/RamboSamplingKernels.o build.none_f_inl0_hrd0/testxxx.o  build.none_f_inl0_hrd0/testmisc.o  build.none_f_inl0_hrd0/runTest.o build.none_f_inl0_hrd0/gCPPProcess.o build.none_f_inl0_hrd0/gMatrixElementKernels.o build.none_f_inl0_hrd0/gBridgeKernels.o build.none_f_inl0_hrd0/gCrossSectionKernels.o build.none_f_inl0_hrd0/gRandomNumberKernels.o build.none_f_inl0_hrd0/gRamboSamplingKernels.o build.none_f_inl0_hrd0/testxxx_cu.o  build.none_f_inl0_hrd0/testmisc_cu.o  build.none_f_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl0_hrd0/gcheck.exe build.none_f_inl0_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_gg_ttxgg_cuda build.none_f_inl0_hrd0/gRandomNumberKernels.o build.none_f_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl0_hrd0/fgcheck.exe build.none_f_inl0_hrd0/fcheck_sa.o build.none_f_inl0_hrd0/fsampler_cu.o -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_gg_ttxgg_cuda build.none_f_inl0_hrd0/gRandomNumberKernels.o build.none_f_inl0_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.none_f_inl0_hrd0/libmg5amc_gg_ttxgg_cpp.so build.none_f_inl0_hrd0/CPPProcess.o build.none_f_inl0_hrd0/MatrixElementKernels.o build.none_f_inl0_hrd0/BridgeKernels.o build.none_f_inl0_hrd0/CrossSectionKernels.o build.none_f_inl0_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_f_inl0_hrd0/check.exe build.none_f_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_f_inl0_hrd0'  -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_gg_ttxgg_cpp build.none_f_inl0_hrd0/RandomNumberKernels.o build.none_f_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_f_inl0_hrd0/fcheck.exe build.none_f_inl0_hrd0/fcheck_sa.o build.none_f_inl0_hrd0/fsampler.o -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_f_inl0_hrd0'  -lgfortran -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_gg_ttxgg_cpp build.none_f_inl0_hrd0/RandomNumberKernels.o build.none_f_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.none_f_inl0_hrd0/libmg5amc_gg_ttxgg_cuda.so build.none_f_inl0_hrd0/gCPPProcess.o build.none_f_inl0_hrd0/gMatrixElementKernels.o build.none_f_inl0_hrd0/gBridgeKernels.o build.none_f_inl0_hrd0/gCrossSectionKernels.o build.none_f_inl0_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl0_hrd0/runTest.exe build.none_f_inl0_hrd0/CPPProcess.o build.none_f_inl0_hrd0/MatrixElementKernels.o build.none_f_inl0_hrd0/BridgeKernels.o build.none_f_inl0_hrd0/CrossSectionKernels.o build.none_f_inl0_hrd0/RandomNumberKernels.o build.none_f_inl0_hrd0/RamboSamplingKernels.o build.none_f_inl0_hrd0/testxxx.o  build.none_f_inl0_hrd0/testmisc.o  build.none_f_inl0_hrd0/runTest.o build.none_f_inl0_hrd0/gCPPProcess.o build.none_f_inl0_hrd0/gMatrixElementKernels.o build.none_f_inl0_hrd0/gBridgeKernels.o build.none_f_inl0_hrd0/gCrossSectionKernels.o build.none_f_inl0_hrd0/gRandomNumberKernels.o build.none_f_inl0_hrd0/gRamboSamplingKernels.o build.none_f_inl0_hrd0/testxxx_cu.o  build.none_f_inl0_hrd0/testmisc_cu.o  build.none_f_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl0_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl0_hrd0/gcheck.exe build.none_f_inl0_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl0_hrd0'  -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_gg_ttxgg_cuda build.none_f_inl0_hrd0/gRandomNumberKernels.o build.none_f_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl0_hrd0/fgcheck.exe build.none_f_inl0_hrd0/fcheck_sa.o build.none_f_inl0_hrd0/fsampler_cu.o -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl0_hrd0'  -lgfortran -L../../lib/build.none_f_inl0_hrd0 -lmg5amc_gg_ttxgg_cuda build.none_f_inl0_hrd0/gRandomNumberKernels.o build.none_f_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
 touch build.none_f_inl0_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_f_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.none_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.none_f_inl0_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_f_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.none_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.none_f_inl0_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.none_f_inl0_hrd0/libmg5amc_gg_ttxgg_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_f_inl0_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.none_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.none_f_inl0_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
 CUDACPP_BUILDDIR='build.512y_f_inl0_hrd0'
 make -f cudacpp.mk
@@ -6656,82 +6720,83 @@ HELINL=0
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.512y_f_inl0_hrd0 for tag=512y_f_inl0_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.512y_f_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gcheck_sa.cu -o build.512y_f_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gcheck_sa.cu -o build.512y_f_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gCPPProcess.cu -o build.512y_f_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512y_f_inl0_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512y_f_inl0_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512y_f_inl0_hrd0/gCrossSectionKernels.o
 AVX=512y
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gCPPProcess.cu -o build.512y_f_inl0_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512y_f_inl0_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512y_f_inl0_hrd0/gBridgeKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512y_f_inl0_hrd0/gCrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -c Parameters_sm.cc -o build.512y_f_inl0_hrd0/Parameters_sm.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512y_f_inl0_hrd0/fbridge_cu.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -c read_slha.cc -o build.512y_f_inl0_hrd0/read_slha.o
-mkdir -p ../lib/build.512y_f_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512y_f_inl0_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512y_f_inl0_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512y_f_inl0_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512y_f_inl0_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512y_f_inl0_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.512y_f_inl0_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.512y_f_inl0_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.512y_f_inl0_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.512y_f_inl0_hrd0/BridgeKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.512y_f_inl0_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.512y_f_inl0_hrd0/fbridge.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.512y_f_inl0_hrd0/RamboSamplingKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.512y_f_inl0_hrd0/RandomNumberKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -c Parameters_sm.cc -o build.512y_f_inl0_hrd0/Parameters_sm.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.512y_f_inl0_hrd0/RamboSamplingKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -c read_slha.cc -o build.512y_f_inl0_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.512y_f_inl0_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512y_f_inl0_hrd0/testxxx_cu.o
+mkdir -p ../lib/build.512y_f_inl0_hrd0
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.512y_f_inl0_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512y_f_inl0_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512y_f_inl0_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512y_f_inl0_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.512y_f_inl0_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu runTest.cc -o build.512y_f_inl0_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu runTest.cc -o build.512y_f_inl0_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.512y_f_inl0_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512y_f_inl0_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512y_f_inl0_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.512y_f_inl0_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.512y_f_inl0_hrd0/libmg5amc_common.so build.512y_f_inl0_hrd0/Parameters_sm.o build.512y_f_inl0_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512y_f_inl0_hrd0/libmg5amc_gg_ttxgg_cuda.so build.512y_f_inl0_hrd0/gCPPProcess.o build.512y_f_inl0_hrd0/gMatrixElementKernels.o build.512y_f_inl0_hrd0/gBridgeKernels.o build.512y_f_inl0_hrd0/gCrossSectionKernels.o build.512y_f_inl0_hrd0/fbridge_cu.o -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512y_f_inl0_hrd0/libmg5amc_gg_ttxgg_cpp.so build.512y_f_inl0_hrd0/CPPProcess.o build.512y_f_inl0_hrd0/MatrixElementKernels.o build.512y_f_inl0_hrd0/BridgeKernels.o build.512y_f_inl0_hrd0/CrossSectionKernels.o build.512y_f_inl0_hrd0/fbridge.o -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl0_hrd0/runTest.exe build.512y_f_inl0_hrd0/CPPProcess.o build.512y_f_inl0_hrd0/MatrixElementKernels.o build.512y_f_inl0_hrd0/BridgeKernels.o build.512y_f_inl0_hrd0/CrossSectionKernels.o build.512y_f_inl0_hrd0/RandomNumberKernels.o build.512y_f_inl0_hrd0/RamboSamplingKernels.o build.512y_f_inl0_hrd0/testxxx.o  build.512y_f_inl0_hrd0/testmisc.o  build.512y_f_inl0_hrd0/runTest.o build.512y_f_inl0_hrd0/gCPPProcess.o build.512y_f_inl0_hrd0/gMatrixElementKernels.o build.512y_f_inl0_hrd0/gBridgeKernels.o build.512y_f_inl0_hrd0/gCrossSectionKernels.o build.512y_f_inl0_hrd0/gRandomNumberKernels.o build.512y_f_inl0_hrd0/gRamboSamplingKernels.o build.512y_f_inl0_hrd0/testxxx_cu.o  build.512y_f_inl0_hrd0/testmisc_cu.o  build.512y_f_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_f_inl0_hrd0/check.exe build.512y_f_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_gg_ttxgg_cpp build.512y_f_inl0_hrd0/RandomNumberKernels.o build.512y_f_inl0_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_f_inl0_hrd0/fcheck.exe build.512y_f_inl0_hrd0/fcheck_sa.o build.512y_f_inl0_hrd0/fsampler.o -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_gg_ttxgg_cpp build.512y_f_inl0_hrd0/RandomNumberKernels.o build.512y_f_inl0_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl0_hrd0/gcheck.exe build.512y_f_inl0_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_gg_ttxgg_cuda build.512y_f_inl0_hrd0/gRandomNumberKernels.o build.512y_f_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl0_hrd0/fgcheck.exe build.512y_f_inl0_hrd0/fcheck_sa.o build.512y_f_inl0_hrd0/fsampler_cu.o -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_gg_ttxgg_cuda build.512y_f_inl0_hrd0/gRandomNumberKernels.o build.512y_f_inl0_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512y_f_inl0_hrd0/libmg5amc_gg_ttxgg_cuda.so build.512y_f_inl0_hrd0/gCPPProcess.o build.512y_f_inl0_hrd0/gMatrixElementKernels.o build.512y_f_inl0_hrd0/gBridgeKernels.o build.512y_f_inl0_hrd0/gCrossSectionKernels.o build.512y_f_inl0_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl0_hrd0/gcheck.exe build.512y_f_inl0_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl0_hrd0'  -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_gg_ttxgg_cuda build.512y_f_inl0_hrd0/gRandomNumberKernels.o build.512y_f_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl0_hrd0/fgcheck.exe build.512y_f_inl0_hrd0/fcheck_sa.o build.512y_f_inl0_hrd0/fsampler_cu.o -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl0_hrd0'  -lgfortran -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_gg_ttxgg_cuda build.512y_f_inl0_hrd0/gRandomNumberKernels.o build.512y_f_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512y_f_inl0_hrd0/libmg5amc_gg_ttxgg_cpp.so build.512y_f_inl0_hrd0/CPPProcess.o build.512y_f_inl0_hrd0/MatrixElementKernels.o build.512y_f_inl0_hrd0/BridgeKernels.o build.512y_f_inl0_hrd0/CrossSectionKernels.o build.512y_f_inl0_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_f_inl0_hrd0/check.exe build.512y_f_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_f_inl0_hrd0'  -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_gg_ttxgg_cpp build.512y_f_inl0_hrd0/RandomNumberKernels.o build.512y_f_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_f_inl0_hrd0/fcheck.exe build.512y_f_inl0_hrd0/fcheck_sa.o build.512y_f_inl0_hrd0/fsampler.o -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_f_inl0_hrd0'  -lgfortran -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_gg_ttxgg_cpp build.512y_f_inl0_hrd0/RandomNumberKernels.o build.512y_f_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl0_hrd0/runTest.exe build.512y_f_inl0_hrd0/CPPProcess.o build.512y_f_inl0_hrd0/MatrixElementKernels.o build.512y_f_inl0_hrd0/BridgeKernels.o build.512y_f_inl0_hrd0/CrossSectionKernels.o build.512y_f_inl0_hrd0/RandomNumberKernels.o build.512y_f_inl0_hrd0/RamboSamplingKernels.o build.512y_f_inl0_hrd0/testxxx.o  build.512y_f_inl0_hrd0/testmisc.o  build.512y_f_inl0_hrd0/runTest.o build.512y_f_inl0_hrd0/gCPPProcess.o build.512y_f_inl0_hrd0/gMatrixElementKernels.o build.512y_f_inl0_hrd0/gBridgeKernels.o build.512y_f_inl0_hrd0/gCrossSectionKernels.o build.512y_f_inl0_hrd0/gRandomNumberKernels.o build.512y_f_inl0_hrd0/gRamboSamplingKernels.o build.512y_f_inl0_hrd0/testxxx_cu.o  build.512y_f_inl0_hrd0/testmisc_cu.o  build.512y_f_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.512y_f_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl0_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
 touch build.512y_f_inl0_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_f_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.512y_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_f_inl0_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_f_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512y_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_f_inl0_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.512y_f_inl0_hrd0/libmg5amc_gg_ttxgg_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_f_inl0_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512y_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_f_inl0_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:09:19
+DATE: 2022-09-25_00:21:27
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/gcheck.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/gcheck.exe -p 64 256 2 OMP=
 Process                     = SIGMA_SM_GG_TTXGG_CUDA [nvcc 11.7.99 (gcc 11.2.0)] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK
 FP precision                = FLOAT (NaN/abnormal=0, zero=0)
-EvtsPerSec[Rmb+ME]     (23) = ( 6.583958e+05                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 6.639118e+05                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 6.644029e+05                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 2.952728e+05                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 2.969132e+05                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 2.970197e+05                 )  sec^-1
 MeanMatrixElemValue         = ( 2.514920e+00 +- 1.234274e+00 )  GeV^-4
-TOTAL       :     0.547328 sec
-real	0m0.827s
-==PROF== Profiling "sigmaKin": launch__registers_per_thread 255
-==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100%
+TOTAL       :     2.578652 sec
+real	0m3.027s
+   launch__registers_per_thread N/A
+   sm__sass_average_branch_targets_threads_uniform.pct N/A
 .........................................................................
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/gcheck.exe -p 2048 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/gcheck.exe -p 2048 256 2 OMP=
 Process                     = SIGMA_SM_GG_TTXGG_CUDA [nvcc 11.7.99 (gcc 11.2.0)] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK
 FP precision                = FLOAT (NaN/abnormal=0, zero=0)
-EvtsPerSec[Rmb+ME]     (23) = ( 8.604932e+05                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 8.679409e+05                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 8.682726e+05                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 3.073359e+05                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 3.087554e+05                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 3.087941e+05                 )  sec^-1
 MeanMatrixElemValue         = ( 1.560346e+01 +- 8.742512e+00 )  GeV^-4
-TOTAL       :     2.390598 sec
-real	0m2.694s
+TOTAL       :     7.510916 sec
+real	0m7.956s
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/gcheck.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/fgcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/gcheck.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/fgcheck.exe 2 64 2
 Avg ME (C++/CUDA)   = 6.626454e-04
 Avg ME (F77/CUDA)   = 6.6262612081027100E-004
 Relative difference = 2.909427837126023e-05
@@ -6739,12 +6804,12 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:09:28 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -nocpp -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:22:02 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -nocpp -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
 CUDACPP_BUILDDIR='build.none_f_inl1_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -6754,51 +6819,52 @@ HELINL=1
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.none_f_inl1_hrd0 for tag=none_f_inl1_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.none_f_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.none_f_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.none_f_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.none_f_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.none_f_inl1_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.none_f_inl1_hrd0/gBridgeKernels.o
 AVX=none
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.none_f_inl1_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.none_f_inl1_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.none_f_inl1_hrd0/gBridgeKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.none_f_inl1_hrd0/gCrossSectionKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.none_f_inl1_hrd0/fbridge_cu.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.none_f_inl1_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.none_f_inl1_hrd0/read_slha.o
-mkdir -p ../lib/build.none_f_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.none_f_inl1_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.none_f_inl1_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.none_f_inl1_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.none_f_inl1_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.none_f_inl1_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.none_f_inl1_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.none_f_inl1_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.none_f_inl1_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.none_f_inl1_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.none_f_inl1_hrd0/BridgeKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.none_f_inl1_hrd0/read_slha.o
+mkdir -p ../lib/build.none_f_inl1_hrd0
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.none_f_inl1_hrd0/CrossSectionKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.none_f_inl1_hrd0/Parameters_sm.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.none_f_inl1_hrd0/fbridge.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.none_f_inl1_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.none_f_inl1_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.none_f_inl1_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.none_f_inl1_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.none_f_inl1_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.none_f_inl1_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.none_f_inl1_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.none_f_inl1_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.none_f_inl1_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.none_f_inl1_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.none_f_inl1_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.none_f_inl1_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.none_f_inl1_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.none_f_inl1_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math    -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.none_f_inl1_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.none_f_inl1_hrd0/libmg5amc_common.so build.none_f_inl1_hrd0/Parameters_sm.o build.none_f_inl1_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.none_f_inl1_hrd0/libmg5amc_gg_ttxgg_cpp.so build.none_f_inl1_hrd0/CPPProcess.o build.none_f_inl1_hrd0/MatrixElementKernels.o build.none_f_inl1_hrd0/BridgeKernels.o build.none_f_inl1_hrd0/CrossSectionKernels.o build.none_f_inl1_hrd0/fbridge.o -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_f_inl1_hrd0/check.exe build.none_f_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_gg_ttxgg_cpp build.none_f_inl1_hrd0/RandomNumberKernels.o build.none_f_inl1_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_f_inl1_hrd0/fcheck.exe build.none_f_inl1_hrd0/fcheck_sa.o build.none_f_inl1_hrd0/fsampler.o -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_gg_ttxgg_cpp build.none_f_inl1_hrd0/RandomNumberKernels.o build.none_f_inl1_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.none_f_inl1_hrd0/libmg5amc_gg_ttxgg_cuda.so build.none_f_inl1_hrd0/gCPPProcess.o build.none_f_inl1_hrd0/gMatrixElementKernels.o build.none_f_inl1_hrd0/gBridgeKernels.o build.none_f_inl1_hrd0/gCrossSectionKernels.o build.none_f_inl1_hrd0/fbridge_cu.o -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl1_hrd0/runTest.exe build.none_f_inl1_hrd0/CPPProcess.o build.none_f_inl1_hrd0/MatrixElementKernels.o build.none_f_inl1_hrd0/BridgeKernels.o build.none_f_inl1_hrd0/CrossSectionKernels.o build.none_f_inl1_hrd0/RandomNumberKernels.o build.none_f_inl1_hrd0/RamboSamplingKernels.o build.none_f_inl1_hrd0/testxxx.o  build.none_f_inl1_hrd0/testmisc.o  build.none_f_inl1_hrd0/runTest.o build.none_f_inl1_hrd0/gCPPProcess.o build.none_f_inl1_hrd0/gMatrixElementKernels.o build.none_f_inl1_hrd0/gBridgeKernels.o build.none_f_inl1_hrd0/gCrossSectionKernels.o build.none_f_inl1_hrd0/gRandomNumberKernels.o build.none_f_inl1_hrd0/gRamboSamplingKernels.o build.none_f_inl1_hrd0/testxxx_cu.o  build.none_f_inl1_hrd0/testmisc_cu.o  build.none_f_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl1_hrd0/gcheck.exe build.none_f_inl1_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_gg_ttxgg_cuda build.none_f_inl1_hrd0/gRandomNumberKernels.o build.none_f_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl1_hrd0/fgcheck.exe build.none_f_inl1_hrd0/fcheck_sa.o build.none_f_inl1_hrd0/fsampler_cu.o -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_gg_ttxgg_cuda build.none_f_inl1_hrd0/gRandomNumberKernels.o build.none_f_inl1_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.none_f_inl1_hrd0/libmg5amc_gg_ttxgg_cpp.so build.none_f_inl1_hrd0/CPPProcess.o build.none_f_inl1_hrd0/MatrixElementKernels.o build.none_f_inl1_hrd0/BridgeKernels.o build.none_f_inl1_hrd0/CrossSectionKernels.o build.none_f_inl1_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_f_inl1_hrd0/check.exe build.none_f_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_f_inl1_hrd0'  -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_gg_ttxgg_cpp build.none_f_inl1_hrd0/RandomNumberKernels.o build.none_f_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.none_f_inl1_hrd0/fcheck.exe build.none_f_inl1_hrd0/fcheck_sa.o build.none_f_inl1_hrd0/fsampler.o -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.none_f_inl1_hrd0'  -lgfortran -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_gg_ttxgg_cpp build.none_f_inl1_hrd0/RandomNumberKernels.o build.none_f_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.none_f_inl1_hrd0/libmg5amc_gg_ttxgg_cuda.so build.none_f_inl1_hrd0/gCPPProcess.o build.none_f_inl1_hrd0/gMatrixElementKernels.o build.none_f_inl1_hrd0/gBridgeKernels.o build.none_f_inl1_hrd0/gCrossSectionKernels.o build.none_f_inl1_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl1_hrd0/runTest.exe build.none_f_inl1_hrd0/CPPProcess.o build.none_f_inl1_hrd0/MatrixElementKernels.o build.none_f_inl1_hrd0/BridgeKernels.o build.none_f_inl1_hrd0/CrossSectionKernels.o build.none_f_inl1_hrd0/RandomNumberKernels.o build.none_f_inl1_hrd0/RamboSamplingKernels.o build.none_f_inl1_hrd0/testxxx.o  build.none_f_inl1_hrd0/testmisc.o  build.none_f_inl1_hrd0/runTest.o build.none_f_inl1_hrd0/gCPPProcess.o build.none_f_inl1_hrd0/gMatrixElementKernels.o build.none_f_inl1_hrd0/gBridgeKernels.o build.none_f_inl1_hrd0/gCrossSectionKernels.o build.none_f_inl1_hrd0/gRandomNumberKernels.o build.none_f_inl1_hrd0/gRamboSamplingKernels.o build.none_f_inl1_hrd0/testxxx_cu.o  build.none_f_inl1_hrd0/testmisc_cu.o  build.none_f_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl1_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl1_hrd0/gcheck.exe build.none_f_inl1_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl1_hrd0'  -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_gg_ttxgg_cuda build.none_f_inl1_hrd0/gRandomNumberKernels.o build.none_f_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.none_f_inl1_hrd0/fgcheck.exe build.none_f_inl1_hrd0/fcheck_sa.o build.none_f_inl1_hrd0/fsampler_cu.o -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.none_f_inl1_hrd0'  -lgfortran -L../../lib/build.none_f_inl1_hrd0 -lmg5amc_gg_ttxgg_cuda build.none_f_inl1_hrd0/gRandomNumberKernels.o build.none_f_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
 touch build.none_f_inl1_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_f_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.none_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.none_f_inl1_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_f_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.none_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.none_f_inl1_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.none_f_inl1_hrd0/libmg5amc_gg_ttxgg_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.none_f_inl1_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.none_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.none_f_inl1_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
 CUDACPP_BUILDDIR='build.512y_f_inl1_hrd0'
 make -f cudacpp.mk
@@ -6809,82 +6875,83 @@ HELINL=1
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.512y_f_inl1_hrd0 for tag=512y_f_inl1_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.512y_f_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.512y_f_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.512y_f_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.512y_f_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512y_f_inl1_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512y_f_inl1_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512y_f_inl1_hrd0/gCrossSectionKernels.o
 AVX=512y
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.512y_f_inl1_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512y_f_inl1_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512y_f_inl1_hrd0/gBridgeKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512y_f_inl1_hrd0/gCrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.512y_f_inl1_hrd0/Parameters_sm.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512y_f_inl1_hrd0/fbridge_cu.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.512y_f_inl1_hrd0/read_slha.o
-mkdir -p ../lib/build.512y_f_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512y_f_inl1_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512y_f_inl1_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512y_f_inl1_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512y_f_inl1_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512y_f_inl1_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.512y_f_inl1_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.512y_f_inl1_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.512y_f_inl1_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.512y_f_inl1_hrd0/BridgeKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.512y_f_inl1_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.512y_f_inl1_hrd0/fbridge.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.512y_f_inl1_hrd0/Parameters_sm.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.512y_f_inl1_hrd0/RandomNumberKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.512y_f_inl1_hrd0/read_slha.o
+mkdir -p ../lib/build.512y_f_inl1_hrd0
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.512y_f_inl1_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.512y_f_inl1_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512y_f_inl1_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512y_f_inl1_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.512y_f_inl1_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512y_f_inl1_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512y_f_inl1_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.512y_f_inl1_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.512y_f_inl1_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.512y_f_inl1_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.512y_f_inl1_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512y_f_inl1_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512y_f_inl1_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -mprefer-vector-width=256  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.512y_f_inl1_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.512y_f_inl1_hrd0/libmg5amc_common.so build.512y_f_inl1_hrd0/Parameters_sm.o build.512y_f_inl1_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512y_f_inl1_hrd0/libmg5amc_gg_ttxgg_cuda.so build.512y_f_inl1_hrd0/gCPPProcess.o build.512y_f_inl1_hrd0/gMatrixElementKernels.o build.512y_f_inl1_hrd0/gBridgeKernels.o build.512y_f_inl1_hrd0/gCrossSectionKernels.o build.512y_f_inl1_hrd0/fbridge_cu.o -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512y_f_inl1_hrd0/libmg5amc_gg_ttxgg_cpp.so build.512y_f_inl1_hrd0/CPPProcess.o build.512y_f_inl1_hrd0/MatrixElementKernels.o build.512y_f_inl1_hrd0/BridgeKernels.o build.512y_f_inl1_hrd0/CrossSectionKernels.o build.512y_f_inl1_hrd0/fbridge.o -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl1_hrd0/runTest.exe build.512y_f_inl1_hrd0/CPPProcess.o build.512y_f_inl1_hrd0/MatrixElementKernels.o build.512y_f_inl1_hrd0/BridgeKernels.o build.512y_f_inl1_hrd0/CrossSectionKernels.o build.512y_f_inl1_hrd0/RandomNumberKernels.o build.512y_f_inl1_hrd0/RamboSamplingKernels.o build.512y_f_inl1_hrd0/testxxx.o  build.512y_f_inl1_hrd0/testmisc.o  build.512y_f_inl1_hrd0/runTest.o build.512y_f_inl1_hrd0/gCPPProcess.o build.512y_f_inl1_hrd0/gMatrixElementKernels.o build.512y_f_inl1_hrd0/gBridgeKernels.o build.512y_f_inl1_hrd0/gCrossSectionKernels.o build.512y_f_inl1_hrd0/gRandomNumberKernels.o build.512y_f_inl1_hrd0/gRamboSamplingKernels.o build.512y_f_inl1_hrd0/testxxx_cu.o  build.512y_f_inl1_hrd0/testmisc_cu.o  build.512y_f_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_f_inl1_hrd0/check.exe build.512y_f_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_gg_ttxgg_cpp build.512y_f_inl1_hrd0/RandomNumberKernels.o build.512y_f_inl1_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_f_inl1_hrd0/fcheck.exe build.512y_f_inl1_hrd0/fcheck_sa.o build.512y_f_inl1_hrd0/fsampler.o -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_gg_ttxgg_cpp build.512y_f_inl1_hrd0/RandomNumberKernels.o build.512y_f_inl1_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl1_hrd0/gcheck.exe build.512y_f_inl1_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_gg_ttxgg_cuda build.512y_f_inl1_hrd0/gRandomNumberKernels.o build.512y_f_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl1_hrd0/fgcheck.exe build.512y_f_inl1_hrd0/fcheck_sa.o build.512y_f_inl1_hrd0/fsampler_cu.o -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_gg_ttxgg_cuda build.512y_f_inl1_hrd0/gRandomNumberKernels.o build.512y_f_inl1_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512y_f_inl1_hrd0/libmg5amc_gg_ttxgg_cuda.so build.512y_f_inl1_hrd0/gCPPProcess.o build.512y_f_inl1_hrd0/gMatrixElementKernels.o build.512y_f_inl1_hrd0/gBridgeKernels.o build.512y_f_inl1_hrd0/gCrossSectionKernels.o build.512y_f_inl1_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl1_hrd0/gcheck.exe build.512y_f_inl1_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl1_hrd0'  -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_gg_ttxgg_cuda build.512y_f_inl1_hrd0/gRandomNumberKernels.o build.512y_f_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl1_hrd0/fgcheck.exe build.512y_f_inl1_hrd0/fcheck_sa.o build.512y_f_inl1_hrd0/fsampler_cu.o -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl1_hrd0'  -lgfortran -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_gg_ttxgg_cuda build.512y_f_inl1_hrd0/gRandomNumberKernels.o build.512y_f_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512y_f_inl1_hrd0/libmg5amc_gg_ttxgg_cpp.so build.512y_f_inl1_hrd0/CPPProcess.o build.512y_f_inl1_hrd0/MatrixElementKernels.o build.512y_f_inl1_hrd0/BridgeKernels.o build.512y_f_inl1_hrd0/CrossSectionKernels.o build.512y_f_inl1_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512y_f_inl1_hrd0/runTest.exe build.512y_f_inl1_hrd0/CPPProcess.o build.512y_f_inl1_hrd0/MatrixElementKernels.o build.512y_f_inl1_hrd0/BridgeKernels.o build.512y_f_inl1_hrd0/CrossSectionKernels.o build.512y_f_inl1_hrd0/RandomNumberKernels.o build.512y_f_inl1_hrd0/RamboSamplingKernels.o build.512y_f_inl1_hrd0/testxxx.o  build.512y_f_inl1_hrd0/testmisc.o  build.512y_f_inl1_hrd0/runTest.o build.512y_f_inl1_hrd0/gCPPProcess.o build.512y_f_inl1_hrd0/gMatrixElementKernels.o build.512y_f_inl1_hrd0/gBridgeKernels.o build.512y_f_inl1_hrd0/gCrossSectionKernels.o build.512y_f_inl1_hrd0/gRandomNumberKernels.o build.512y_f_inl1_hrd0/gRamboSamplingKernels.o build.512y_f_inl1_hrd0/testxxx_cu.o  build.512y_f_inl1_hrd0/testmisc_cu.o  build.512y_f_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512y_f_inl1_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_f_inl1_hrd0/check.exe build.512y_f_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_f_inl1_hrd0'  -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_gg_ttxgg_cpp build.512y_f_inl1_hrd0/RandomNumberKernels.o build.512y_f_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512y_f_inl1_hrd0/fcheck.exe build.512y_f_inl1_hrd0/fcheck_sa.o build.512y_f_inl1_hrd0/fsampler.o -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512y_f_inl1_hrd0'  -lgfortran -L../../lib/build.512y_f_inl1_hrd0 -lmg5amc_gg_ttxgg_cpp build.512y_f_inl1_hrd0/RandomNumberKernels.o build.512y_f_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
 touch build.512y_f_inl1_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_f_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.512y_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_f_inl1_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_f_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512y_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_f_inl1_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.512y_f_inl1_hrd0/libmg5amc_gg_ttxgg_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512y_f_inl1_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512y_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.512y_f_inl1_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:10:20
+DATE: 2022-09-25_00:25:24
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl1_hrd0/gcheck.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl1_hrd0/gcheck.exe -p 64 256 2 OMP=
 Process                     = SIGMA_SM_GG_TTXGG_CUDA [nvcc 11.7.99 (gcc 11.2.0)] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK
 FP precision                = FLOAT (NaN/abnormal=0, zero=0)
-EvtsPerSec[Rmb+ME]     (23) = ( 5.789035e+05                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 5.833256e+05                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 5.838134e+05                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 2.524983e+05                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 2.536605e+05                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 2.537392e+05                 )  sec^-1
 MeanMatrixElemValue         = ( 2.514920e+00 +- 1.234274e+00 )  GeV^-4
-TOTAL       :     0.582943 sec
-real	0m0.877s
-==PROF== Profiling "sigmaKin": launch__registers_per_thread 255
-==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100%
+TOTAL       :     2.567937 sec
+real	0m3.013s
+   launch__registers_per_thread N/A
+   sm__sass_average_branch_targets_threads_uniform.pct N/A
 .........................................................................
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl1_hrd0/gcheck.exe -p 2048 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl1_hrd0/gcheck.exe -p 2048 256 2 OMP=
 Process                     = SIGMA_SM_GG_TTXGG_CUDA [nvcc 11.7.99 (gcc 11.2.0)] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK
 FP precision                = FLOAT (NaN/abnormal=0, zero=0)
-EvtsPerSec[Rmb+ME]     (23) = ( 7.705136e+05                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 7.764924e+05                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 7.767556e+05                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 2.628167e+05                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 2.638348e+05                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 2.638627e+05                 )  sec^-1
 MeanMatrixElemValue         = ( 1.560346e+01 +- 8.742513e+00 )  GeV^-4
-TOTAL       :     2.603417 sec
-real	0m2.904s
+TOTAL       :     8.365761 sec
+real	0m8.837s
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl1_hrd0/gcheck.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl1_hrd0/fgcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl1_hrd0/gcheck.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl1_hrd0/fgcheck.exe 2 64 2
 Avg ME (C++/CUDA)   = 6.626455e-04
 Avg ME (F77/CUDA)   = 6.6262612743291094E-004
 Relative difference = 2.9235189990763262e-05
@@ -6892,35 +6959,35 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:10:29 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -noneonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:25:59 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -noneonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -noneonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
 CUDACPP_BUILDDIR='build.none_d_inl0_hrd0'
 make: Nothing to be done for `all'.
 
-DATE: 2022-08-31_21:10:30
+DATE: 2022-09-25_00:26:00
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/check.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/check.exe -p 64 256 2 OMP=
 Process                     = SIGMA_SM_GG_TTXGG_CPP [gcc 11.2.0] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CPP:DBL+CXS:CURHST+RMBHST+MESHST/none+NAVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = SCALAR ('none': ~vector[1], no SIMD)
-EvtsPerSec[Rmb+ME]     (23) = ( 1.739230e+03                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 1.741064e+03                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 1.741064e+03                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 1.741665e+03                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 1.743491e+03                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 1.743491e+03                 )  sec^-1
 MeanMatrixElemValue         = ( 2.520822e+00 +- 1.235793e+00 )  GeV^-4
-TOTAL       :    18.859583 sec
-real	0m18.867s
+TOTAL       :    18.844301 sec
+real	0m18.851s
 =Symbols in CPPProcess.o= (~sse4: 4587) (avx2:    0) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 6.626675e-04
 Avg ME (F77/C++)    = 6.6266731198141176E-004
 Relative difference = 2.8372990711072594e-07
@@ -6928,35 +6995,35 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:10:51 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -noneonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:26:34 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -noneonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -noneonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
 CUDACPP_BUILDDIR='build.none_d_inl1_hrd0'
 make: Nothing to be done for `all'.
 
-DATE: 2022-08-31_21:10:51
+DATE: 2022-09-25_00:26:34
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl1_hrd0/check.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl1_hrd0/check.exe -p 64 256 2 OMP=
 Process                     = SIGMA_SM_GG_TTXGG_CPP [gcc 11.2.0] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CPP:DBL+CXS:CURHST+RMBHST+MESHST/none+NAVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = SCALAR ('none': ~vector[1], no SIMD)
-EvtsPerSec[Rmb+ME]     (23) = ( 3.858853e+02                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 3.859758e+02                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 3.859758e+02                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 3.854821e+02                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 3.855719e+02                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 3.855719e+02                 )  sec^-1
 MeanMatrixElemValue         = ( 2.520822e+00 +- 1.235793e+00 )  GeV^-4
-TOTAL       :    84.967880 sec
-real	1m24.975s
+TOTAL       :    85.086632 sec
+real	1m25.094s
 =Symbols in CPPProcess.o= (~sse4:22568) (avx2:    0) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl1_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl1_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl1_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl1_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 6.626675e-04
 Avg ME (F77/C++)    = 6.6266731198140461E-004
 Relative difference = 2.8372991790910424e-07
@@ -6964,35 +7031,35 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:12:20 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -noneonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:28:16 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -noneonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -noneonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
 CUDACPP_BUILDDIR='build.none_f_inl0_hrd0'
 make: Nothing to be done for `all'.
 
-DATE: 2022-08-31_21:12:20
+DATE: 2022-09-25_00:28:16
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/check.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/check.exe -p 64 256 2 OMP=
 Process                     = SIGMA_SM_GG_TTXGG_CPP [gcc 11.2.0] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CPP:FLT+CXS:CURHST+RMBHST+MESHST/none+NAVBRK
 FP precision                = FLOAT (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = SCALAR ('none': ~vector[1], no SIMD)
-EvtsPerSec[Rmb+ME]     (23) = ( 1.822187e+03                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 1.823738e+03                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 1.823738e+03                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 1.827063e+03                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 1.828629e+03                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 1.828629e+03                 )  sec^-1
 MeanMatrixElemValue         = ( 2.517793e+00 +- 1.234876e+00 )  GeV^-4
-TOTAL       :    17.999226 sec
-real	0m18.006s
+TOTAL       :    17.951159 sec
+real	0m17.958s
 =Symbols in CPPProcess.o= (~sse4: 3250) (avx2:    0) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 6.627471e-04
 Avg ME (F77/C++)    = 6.6274711684331800E-004
 Relative difference = 2.5414397095057302e-08
@@ -7000,35 +7067,35 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:12:41 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -noneonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:28:50 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -noneonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -noneonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
 CUDACPP_BUILDDIR='build.none_f_inl1_hrd0'
 make: Nothing to be done for `all'.
 
-DATE: 2022-08-31_21:12:41
+DATE: 2022-09-25_00:28:50
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl1_hrd0/check.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl1_hrd0/check.exe -p 64 256 2 OMP=
 Process                     = SIGMA_SM_GG_TTXGG_CPP [gcc 11.2.0] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CPP:FLT+CXS:CURHST+RMBHST+MESHST/none+NAVBRK
 FP precision                = FLOAT (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = SCALAR ('none': ~vector[1], no SIMD)
-EvtsPerSec[Rmb+ME]     (23) = ( 4.987495e+02                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 4.988663e+02                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 4.988663e+02                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 4.991035e+02                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 4.992194e+02                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 4.992194e+02                 )  sec^-1
 MeanMatrixElemValue         = ( 2.517715e+00 +- 1.234827e+00 )  GeV^-4
-TOTAL       :    65.739990 sec
-real	1m5.747s
+TOTAL       :    65.693573 sec
+real	1m5.700s
 =Symbols in CPPProcess.o= (~sse4:17741) (avx2:    0) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl1_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl1_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl1_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl1_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 6.627521e-04
 Avg ME (F77/C++)    = 6.6275209667122220E-004
 Relative difference = 5.022658987584929e-09
@@ -7036,13 +7103,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:13:52 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -sse4only  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:30:12 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -sse4only  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -sse4only implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
 CUDACPP_BUILDDIR='build.sse4_d_inl0_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -7052,22 +7119,18 @@ HELINL=0
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.sse4_d_inl0_hrd0 for tag=sse4_d_inl0_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.sse4_d_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gcheck_sa.cu -o build.sse4_d_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gcheck_sa.cu -o build.sse4_d_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gCPPProcess.cu -o build.sse4_d_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.sse4_d_inl0_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gBridgeKernels.cu -o build.sse4_d_inl0_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.sse4_d_inl0_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fbridge.cc -o build.sse4_d_inl0_hrd0/fbridge_cu.o
 AVX=sse4
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gCPPProcess.cu -o build.sse4_d_inl0_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.sse4_d_inl0_hrd0/gMatrixElementKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -c Parameters_sm.cc -o build.sse4_d_inl0_hrd0/Parameters_sm.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gBridgeKernels.cu -o build.sse4_d_inl0_hrd0/gBridgeKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -c read_slha.cc -o build.sse4_d_inl0_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.sse4_d_inl0_hrd0/gCrossSectionKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fbridge.cc -o build.sse4_d_inl0_hrd0/fbridge_cu.o
-mkdir -p ../lib/build.sse4_d_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.sse4_d_inl0_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.sse4_d_inl0_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.sse4_d_inl0_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.sse4_d_inl0_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.sse4_d_inl0_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.sse4_d_inl0_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.sse4_d_inl0_hrd0/MatrixElementKernels.o
@@ -7076,47 +7139,52 @@ ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.sse4_d_inl0_hrd0/fbridge.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.sse4_d_inl0_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.sse4_d_inl0_hrd0/RamboSamplingKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.sse4_d_inl0_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testxxx.cc -o build.sse4_d_inl0_hrd0/testxxx_cu.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -c Parameters_sm.cc -o build.sse4_d_inl0_hrd0/Parameters_sm.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -c read_slha.cc -o build.sse4_d_inl0_hrd0/read_slha.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testxxx.cc -o build.sse4_d_inl0_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.sse4_d_inl0_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testmisc.cc -o build.sse4_d_inl0_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testmisc.cc -o build.sse4_d_inl0_hrd0/testmisc_cu.o
+mkdir -p ../lib/build.sse4_d_inl0_hrd0
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.sse4_d_inl0_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu runTest.cc -o build.sse4_d_inl0_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu runTest.cc -o build.sse4_d_inl0_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.sse4_d_inl0_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fsampler.cc -o build.sse4_d_inl0_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fsampler.cc -o build.sse4_d_inl0_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.sse4_d_inl0_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.sse4_d_inl0_hrd0/libmg5amc_common.so build.sse4_d_inl0_hrd0/Parameters_sm.o build.sse4_d_inl0_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.sse4_d_inl0_hrd0/libmg5amc_gg_ttxgg_cuda.so build.sse4_d_inl0_hrd0/gCPPProcess.o build.sse4_d_inl0_hrd0/gMatrixElementKernels.o build.sse4_d_inl0_hrd0/gBridgeKernels.o build.sse4_d_inl0_hrd0/gCrossSectionKernels.o build.sse4_d_inl0_hrd0/fbridge_cu.o -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.sse4_d_inl0_hrd0/libmg5amc_gg_ttxgg_cpp.so build.sse4_d_inl0_hrd0/CPPProcess.o build.sse4_d_inl0_hrd0/MatrixElementKernels.o build.sse4_d_inl0_hrd0/BridgeKernels.o build.sse4_d_inl0_hrd0/CrossSectionKernels.o build.sse4_d_inl0_hrd0/fbridge.o -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl0_hrd0/runTest.exe build.sse4_d_inl0_hrd0/CPPProcess.o build.sse4_d_inl0_hrd0/MatrixElementKernels.o build.sse4_d_inl0_hrd0/BridgeKernels.o build.sse4_d_inl0_hrd0/CrossSectionKernels.o build.sse4_d_inl0_hrd0/RandomNumberKernels.o build.sse4_d_inl0_hrd0/RamboSamplingKernels.o build.sse4_d_inl0_hrd0/testxxx.o  build.sse4_d_inl0_hrd0/testmisc.o  build.sse4_d_inl0_hrd0/runTest.o build.sse4_d_inl0_hrd0/gCPPProcess.o build.sse4_d_inl0_hrd0/gMatrixElementKernels.o build.sse4_d_inl0_hrd0/gBridgeKernels.o build.sse4_d_inl0_hrd0/gCrossSectionKernels.o build.sse4_d_inl0_hrd0/gRandomNumberKernels.o build.sse4_d_inl0_hrd0/gRamboSamplingKernels.o build.sse4_d_inl0_hrd0/testxxx_cu.o  build.sse4_d_inl0_hrd0/testmisc_cu.o  build.sse4_d_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_d_inl0_hrd0/check.exe build.sse4_d_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_gg_ttxgg_cpp build.sse4_d_inl0_hrd0/RandomNumberKernels.o build.sse4_d_inl0_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_d_inl0_hrd0/fcheck.exe build.sse4_d_inl0_hrd0/fcheck_sa.o build.sse4_d_inl0_hrd0/fsampler.o -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_gg_ttxgg_cpp build.sse4_d_inl0_hrd0/RandomNumberKernels.o build.sse4_d_inl0_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl0_hrd0/gcheck.exe build.sse4_d_inl0_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_gg_ttxgg_cuda build.sse4_d_inl0_hrd0/gRandomNumberKernels.o build.sse4_d_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl0_hrd0/fgcheck.exe build.sse4_d_inl0_hrd0/fcheck_sa.o build.sse4_d_inl0_hrd0/fsampler_cu.o -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_gg_ttxgg_cuda build.sse4_d_inl0_hrd0/gRandomNumberKernels.o build.sse4_d_inl0_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.sse4_d_inl0_hrd0/libmg5amc_gg_ttxgg_cuda.so build.sse4_d_inl0_hrd0/gCPPProcess.o build.sse4_d_inl0_hrd0/gMatrixElementKernels.o build.sse4_d_inl0_hrd0/gBridgeKernels.o build.sse4_d_inl0_hrd0/gCrossSectionKernels.o build.sse4_d_inl0_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl0_hrd0/gcheck.exe build.sse4_d_inl0_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl0_hrd0'  -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_gg_ttxgg_cuda build.sse4_d_inl0_hrd0/gRandomNumberKernels.o build.sse4_d_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl0_hrd0/fgcheck.exe build.sse4_d_inl0_hrd0/fcheck_sa.o build.sse4_d_inl0_hrd0/fsampler_cu.o -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl0_hrd0'  -lgfortran -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_gg_ttxgg_cuda build.sse4_d_inl0_hrd0/gRandomNumberKernels.o build.sse4_d_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.sse4_d_inl0_hrd0/libmg5amc_gg_ttxgg_cpp.so build.sse4_d_inl0_hrd0/CPPProcess.o build.sse4_d_inl0_hrd0/MatrixElementKernels.o build.sse4_d_inl0_hrd0/BridgeKernels.o build.sse4_d_inl0_hrd0/CrossSectionKernels.o build.sse4_d_inl0_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl0_hrd0/runTest.exe build.sse4_d_inl0_hrd0/CPPProcess.o build.sse4_d_inl0_hrd0/MatrixElementKernels.o build.sse4_d_inl0_hrd0/BridgeKernels.o build.sse4_d_inl0_hrd0/CrossSectionKernels.o build.sse4_d_inl0_hrd0/RandomNumberKernels.o build.sse4_d_inl0_hrd0/RamboSamplingKernels.o build.sse4_d_inl0_hrd0/testxxx.o  build.sse4_d_inl0_hrd0/testmisc.o  build.sse4_d_inl0_hrd0/runTest.o build.sse4_d_inl0_hrd0/gCPPProcess.o build.sse4_d_inl0_hrd0/gMatrixElementKernels.o build.sse4_d_inl0_hrd0/gBridgeKernels.o build.sse4_d_inl0_hrd0/gCrossSectionKernels.o build.sse4_d_inl0_hrd0/gRandomNumberKernels.o build.sse4_d_inl0_hrd0/gRamboSamplingKernels.o build.sse4_d_inl0_hrd0/testxxx_cu.o  build.sse4_d_inl0_hrd0/testmisc_cu.o  build.sse4_d_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl0_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_d_inl0_hrd0/check.exe build.sse4_d_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_d_inl0_hrd0'  -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_gg_ttxgg_cpp build.sse4_d_inl0_hrd0/RandomNumberKernels.o build.sse4_d_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_d_inl0_hrd0/fcheck.exe build.sse4_d_inl0_hrd0/fcheck_sa.o build.sse4_d_inl0_hrd0/fsampler.o -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_d_inl0_hrd0'  -lgfortran -L../../lib/build.sse4_d_inl0_hrd0 -lmg5amc_gg_ttxgg_cpp build.sse4_d_inl0_hrd0/RandomNumberKernels.o build.sse4_d_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
 touch build.sse4_d_inl0_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_d_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.sse4_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_d_inl0_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_d_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.sse4_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_d_inl0_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.sse4_d_inl0_hrd0/libmg5amc_gg_ttxgg_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_d_inl0_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.sse4_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_d_inl0_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:13:53
+DATE: 2022-09-25_00:30:22
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/check.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/check.exe -p 64 256 2 OMP=
 Process                     = SIGMA_SM_GG_TTXGG_CPP [gcc 11.2.0] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CPP:DBL+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 3.336181e+03                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 3.342952e+03                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 3.342952e+03                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 3.343096e+03                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 3.349822e+03                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 3.349822e+03                 )  sec^-1
 MeanMatrixElemValue         = ( 2.520822e+00 +- 1.235793e+00 )  GeV^-4
-TOTAL       :     9.836524 sec
-real	0m9.843s
+TOTAL       :     9.816214 sec
+real	0m9.823s
 =Symbols in CPPProcess.o= (~sse4:12894) (avx2:    0) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 6.626675e-04
 Avg ME (F77/C++)    = 6.6266731198141144E-004
 Relative difference = 2.837299076015613e-07
@@ -7124,13 +7192,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:14:05 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -sse4only  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:30:47 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -sse4only  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -sse4only implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
 CUDACPP_BUILDDIR='build.sse4_d_inl1_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -7140,22 +7208,18 @@ HELINL=1
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.sse4_d_inl1_hrd0 for tag=sse4_d_inl1_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.sse4_d_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.sse4_d_inl1_hrd0/gcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.sse4_d_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.sse4_d_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.sse4_d_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.sse4_d_inl1_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.sse4_d_inl1_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.sse4_d_inl1_hrd0/gCrossSectionKernels.o
 AVX=sse4
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.sse4_d_inl1_hrd0/gMatrixElementKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.sse4_d_inl1_hrd0/gBridgeKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.sse4_d_inl1_hrd0/gCrossSectionKernels.o
-mkdir -p ../lib/build.sse4_d_inl1_hrd0
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.sse4_d_inl1_hrd0/Parameters_sm.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.sse4_d_inl1_hrd0/fbridge_cu.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.sse4_d_inl1_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.sse4_d_inl1_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.sse4_d_inl1_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.sse4_d_inl1_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.sse4_d_inl1_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.sse4_d_inl1_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.sse4_d_inl1_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.sse4_d_inl1_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.sse4_d_inl1_hrd0/MatrixElementKernels.o
@@ -7163,48 +7227,53 @@ ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.sse4_d_inl1_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.sse4_d_inl1_hrd0/fbridge.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.sse4_d_inl1_hrd0/RandomNumberKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.sse4_d_inl1_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.sse4_d_inl1_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.sse4_d_inl1_hrd0/testxxx_cu.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.sse4_d_inl1_hrd0/Parameters_sm.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.sse4_d_inl1_hrd0/read_slha.o
+mkdir -p ../lib/build.sse4_d_inl1_hrd0
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.sse4_d_inl1_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.sse4_d_inl1_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.sse4_d_inl1_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.sse4_d_inl1_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.sse4_d_inl1_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.sse4_d_inl1_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.sse4_d_inl1_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.sse4_d_inl1_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.sse4_d_inl1_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.sse4_d_inl1_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.sse4_d_inl1_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.sse4_d_inl1_hrd0/libmg5amc_common.so build.sse4_d_inl1_hrd0/Parameters_sm.o build.sse4_d_inl1_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.sse4_d_inl1_hrd0/libmg5amc_gg_ttxgg_cuda.so build.sse4_d_inl1_hrd0/gCPPProcess.o build.sse4_d_inl1_hrd0/gMatrixElementKernels.o build.sse4_d_inl1_hrd0/gBridgeKernels.o build.sse4_d_inl1_hrd0/gCrossSectionKernels.o build.sse4_d_inl1_hrd0/fbridge_cu.o -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.sse4_d_inl1_hrd0/libmg5amc_gg_ttxgg_cpp.so build.sse4_d_inl1_hrd0/CPPProcess.o build.sse4_d_inl1_hrd0/MatrixElementKernels.o build.sse4_d_inl1_hrd0/BridgeKernels.o build.sse4_d_inl1_hrd0/CrossSectionKernels.o build.sse4_d_inl1_hrd0/fbridge.o -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl1_hrd0/runTest.exe build.sse4_d_inl1_hrd0/CPPProcess.o build.sse4_d_inl1_hrd0/MatrixElementKernels.o build.sse4_d_inl1_hrd0/BridgeKernels.o build.sse4_d_inl1_hrd0/CrossSectionKernels.o build.sse4_d_inl1_hrd0/RandomNumberKernels.o build.sse4_d_inl1_hrd0/RamboSamplingKernels.o build.sse4_d_inl1_hrd0/testxxx.o  build.sse4_d_inl1_hrd0/testmisc.o  build.sse4_d_inl1_hrd0/runTest.o build.sse4_d_inl1_hrd0/gCPPProcess.o build.sse4_d_inl1_hrd0/gMatrixElementKernels.o build.sse4_d_inl1_hrd0/gBridgeKernels.o build.sse4_d_inl1_hrd0/gCrossSectionKernels.o build.sse4_d_inl1_hrd0/gRandomNumberKernels.o build.sse4_d_inl1_hrd0/gRamboSamplingKernels.o build.sse4_d_inl1_hrd0/testxxx_cu.o  build.sse4_d_inl1_hrd0/testmisc_cu.o  build.sse4_d_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_d_inl1_hrd0/check.exe build.sse4_d_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_gg_ttxgg_cpp build.sse4_d_inl1_hrd0/RandomNumberKernels.o build.sse4_d_inl1_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_d_inl1_hrd0/fcheck.exe build.sse4_d_inl1_hrd0/fcheck_sa.o build.sse4_d_inl1_hrd0/fsampler.o -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_gg_ttxgg_cpp build.sse4_d_inl1_hrd0/RandomNumberKernels.o build.sse4_d_inl1_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl1_hrd0/gcheck.exe build.sse4_d_inl1_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_gg_ttxgg_cuda build.sse4_d_inl1_hrd0/gRandomNumberKernels.o build.sse4_d_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl1_hrd0/fgcheck.exe build.sse4_d_inl1_hrd0/fcheck_sa.o build.sse4_d_inl1_hrd0/fsampler_cu.o -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_gg_ttxgg_cuda build.sse4_d_inl1_hrd0/gRandomNumberKernels.o build.sse4_d_inl1_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.sse4_d_inl1_hrd0/libmg5amc_gg_ttxgg_cuda.so build.sse4_d_inl1_hrd0/gCPPProcess.o build.sse4_d_inl1_hrd0/gMatrixElementKernels.o build.sse4_d_inl1_hrd0/gBridgeKernels.o build.sse4_d_inl1_hrd0/gCrossSectionKernels.o build.sse4_d_inl1_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl1_hrd0/gcheck.exe build.sse4_d_inl1_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl1_hrd0'  -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_gg_ttxgg_cuda build.sse4_d_inl1_hrd0/gRandomNumberKernels.o build.sse4_d_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl1_hrd0/fgcheck.exe build.sse4_d_inl1_hrd0/fcheck_sa.o build.sse4_d_inl1_hrd0/fsampler_cu.o -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl1_hrd0'  -lgfortran -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_gg_ttxgg_cuda build.sse4_d_inl1_hrd0/gRandomNumberKernels.o build.sse4_d_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.sse4_d_inl1_hrd0/libmg5amc_gg_ttxgg_cpp.so build.sse4_d_inl1_hrd0/CPPProcess.o build.sse4_d_inl1_hrd0/MatrixElementKernels.o build.sse4_d_inl1_hrd0/BridgeKernels.o build.sse4_d_inl1_hrd0/CrossSectionKernels.o build.sse4_d_inl1_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_d_inl1_hrd0/runTest.exe build.sse4_d_inl1_hrd0/CPPProcess.o build.sse4_d_inl1_hrd0/MatrixElementKernels.o build.sse4_d_inl1_hrd0/BridgeKernels.o build.sse4_d_inl1_hrd0/CrossSectionKernels.o build.sse4_d_inl1_hrd0/RandomNumberKernels.o build.sse4_d_inl1_hrd0/RamboSamplingKernels.o build.sse4_d_inl1_hrd0/testxxx.o  build.sse4_d_inl1_hrd0/testmisc.o  build.sse4_d_inl1_hrd0/runTest.o build.sse4_d_inl1_hrd0/gCPPProcess.o build.sse4_d_inl1_hrd0/gMatrixElementKernels.o build.sse4_d_inl1_hrd0/gBridgeKernels.o build.sse4_d_inl1_hrd0/gCrossSectionKernels.o build.sse4_d_inl1_hrd0/gRandomNumberKernels.o build.sse4_d_inl1_hrd0/gRamboSamplingKernels.o build.sse4_d_inl1_hrd0/testxxx_cu.o  build.sse4_d_inl1_hrd0/testmisc_cu.o  build.sse4_d_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_d_inl1_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_d_inl1_hrd0/check.exe build.sse4_d_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_d_inl1_hrd0'  -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_gg_ttxgg_cpp build.sse4_d_inl1_hrd0/RandomNumberKernels.o build.sse4_d_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_d_inl1_hrd0/fcheck.exe build.sse4_d_inl1_hrd0/fcheck_sa.o build.sse4_d_inl1_hrd0/fsampler.o -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_d_inl1_hrd0'  -lgfortran -L../../lib/build.sse4_d_inl1_hrd0 -lmg5amc_gg_ttxgg_cpp build.sse4_d_inl1_hrd0/RandomNumberKernels.o build.sse4_d_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
 touch build.sse4_d_inl1_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_d_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.sse4_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_d_inl1_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_d_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.sse4_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_d_inl1_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.sse4_d_inl1_hrd0/libmg5amc_gg_ttxgg_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_d_inl1_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.sse4_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_d_inl1_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:14:06
+DATE: 2022-09-25_00:31:45
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl1_hrd0/check.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl1_hrd0/check.exe -p 64 256 2 OMP=
 Process                     = SIGMA_SM_GG_TTXGG_CPP [gcc 11.2.0] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CPP:DBL+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 2.782392e+03                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 2.787056e+03                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 2.787056e+03                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 2.787510e+03                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 2.792303e+03                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 2.792303e+03                 )  sec^-1
 MeanMatrixElemValue         = ( 2.520822e+00 +- 1.235793e+00 )  GeV^-4
-TOTAL       :    11.792595 sec
-real	0m11.799s
+TOTAL       :    11.770974 sec
+real	0m11.778s
 =Symbols in CPPProcess.o= (~sse4:72714) (avx2:    0) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl1_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl1_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl1_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl1_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 6.626675e-04
 Avg ME (F77/C++)    = 6.6266731198141231E-004
 Relative difference = 2.8372990629266697e-07
@@ -7212,13 +7281,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:14:23 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -sse4only -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:32:12 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -sse4only -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -sse4only implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
 CUDACPP_BUILDDIR='build.sse4_f_inl0_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -7228,71 +7297,72 @@ HELINL=0
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.sse4_f_inl0_hrd0 for tag=sse4_f_inl0_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.sse4_f_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gcheck_sa.cu -o build.sse4_f_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gcheck_sa.cu -o build.sse4_f_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gCPPProcess.cu -o build.sse4_f_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.sse4_f_inl0_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gBridgeKernels.cu -o build.sse4_f_inl0_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.sse4_f_inl0_hrd0/gCrossSectionKernels.o
 AVX=sse4
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gCPPProcess.cu -o build.sse4_f_inl0_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.sse4_f_inl0_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gBridgeKernels.cu -o build.sse4_f_inl0_hrd0/gBridgeKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.sse4_f_inl0_hrd0/gCrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -c Parameters_sm.cc -o build.sse4_f_inl0_hrd0/Parameters_sm.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fbridge.cc -o build.sse4_f_inl0_hrd0/fbridge_cu.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -c read_slha.cc -o build.sse4_f_inl0_hrd0/read_slha.o
-mkdir -p ../lib/build.sse4_f_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.sse4_f_inl0_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.sse4_f_inl0_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fbridge.cc -o build.sse4_f_inl0_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.sse4_f_inl0_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.sse4_f_inl0_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.sse4_f_inl0_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.sse4_f_inl0_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.sse4_f_inl0_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.sse4_f_inl0_hrd0/BridgeKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.sse4_f_inl0_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.sse4_f_inl0_hrd0/fbridge.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.sse4_f_inl0_hrd0/RandomNumberKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -c Parameters_sm.cc -o build.sse4_f_inl0_hrd0/Parameters_sm.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.sse4_f_inl0_hrd0/RamboSamplingKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -c read_slha.cc -o build.sse4_f_inl0_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.sse4_f_inl0_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testxxx.cc -o build.sse4_f_inl0_hrd0/testxxx_cu.o
+mkdir -p ../lib/build.sse4_f_inl0_hrd0
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testxxx.cc -o build.sse4_f_inl0_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.sse4_f_inl0_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testmisc.cc -o build.sse4_f_inl0_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testmisc.cc -o build.sse4_f_inl0_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.sse4_f_inl0_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu runTest.cc -o build.sse4_f_inl0_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu runTest.cc -o build.sse4_f_inl0_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.sse4_f_inl0_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fsampler.cc -o build.sse4_f_inl0_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fsampler.cc -o build.sse4_f_inl0_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.sse4_f_inl0_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.sse4_f_inl0_hrd0/libmg5amc_common.so build.sse4_f_inl0_hrd0/Parameters_sm.o build.sse4_f_inl0_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.sse4_f_inl0_hrd0/libmg5amc_gg_ttxgg_cuda.so build.sse4_f_inl0_hrd0/gCPPProcess.o build.sse4_f_inl0_hrd0/gMatrixElementKernels.o build.sse4_f_inl0_hrd0/gBridgeKernels.o build.sse4_f_inl0_hrd0/gCrossSectionKernels.o build.sse4_f_inl0_hrd0/fbridge_cu.o -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.sse4_f_inl0_hrd0/libmg5amc_gg_ttxgg_cpp.so build.sse4_f_inl0_hrd0/CPPProcess.o build.sse4_f_inl0_hrd0/MatrixElementKernels.o build.sse4_f_inl0_hrd0/BridgeKernels.o build.sse4_f_inl0_hrd0/CrossSectionKernels.o build.sse4_f_inl0_hrd0/fbridge.o -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl0_hrd0/runTest.exe build.sse4_f_inl0_hrd0/CPPProcess.o build.sse4_f_inl0_hrd0/MatrixElementKernels.o build.sse4_f_inl0_hrd0/BridgeKernels.o build.sse4_f_inl0_hrd0/CrossSectionKernels.o build.sse4_f_inl0_hrd0/RandomNumberKernels.o build.sse4_f_inl0_hrd0/RamboSamplingKernels.o build.sse4_f_inl0_hrd0/testxxx.o  build.sse4_f_inl0_hrd0/testmisc.o  build.sse4_f_inl0_hrd0/runTest.o build.sse4_f_inl0_hrd0/gCPPProcess.o build.sse4_f_inl0_hrd0/gMatrixElementKernels.o build.sse4_f_inl0_hrd0/gBridgeKernels.o build.sse4_f_inl0_hrd0/gCrossSectionKernels.o build.sse4_f_inl0_hrd0/gRandomNumberKernels.o build.sse4_f_inl0_hrd0/gRamboSamplingKernels.o build.sse4_f_inl0_hrd0/testxxx_cu.o  build.sse4_f_inl0_hrd0/testmisc_cu.o  build.sse4_f_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_f_inl0_hrd0/check.exe build.sse4_f_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_gg_ttxgg_cpp build.sse4_f_inl0_hrd0/RandomNumberKernels.o build.sse4_f_inl0_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_f_inl0_hrd0/fcheck.exe build.sse4_f_inl0_hrd0/fcheck_sa.o build.sse4_f_inl0_hrd0/fsampler.o -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_gg_ttxgg_cpp build.sse4_f_inl0_hrd0/RandomNumberKernels.o build.sse4_f_inl0_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl0_hrd0/gcheck.exe build.sse4_f_inl0_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_gg_ttxgg_cuda build.sse4_f_inl0_hrd0/gRandomNumberKernels.o build.sse4_f_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl0_hrd0/fgcheck.exe build.sse4_f_inl0_hrd0/fcheck_sa.o build.sse4_f_inl0_hrd0/fsampler_cu.o -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_gg_ttxgg_cuda build.sse4_f_inl0_hrd0/gRandomNumberKernels.o build.sse4_f_inl0_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.sse4_f_inl0_hrd0/libmg5amc_gg_ttxgg_cuda.so build.sse4_f_inl0_hrd0/gCPPProcess.o build.sse4_f_inl0_hrd0/gMatrixElementKernels.o build.sse4_f_inl0_hrd0/gBridgeKernels.o build.sse4_f_inl0_hrd0/gCrossSectionKernels.o build.sse4_f_inl0_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl0_hrd0/gcheck.exe build.sse4_f_inl0_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl0_hrd0'  -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_gg_ttxgg_cuda build.sse4_f_inl0_hrd0/gRandomNumberKernels.o build.sse4_f_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.sse4_f_inl0_hrd0/libmg5amc_gg_ttxgg_cpp.so build.sse4_f_inl0_hrd0/CPPProcess.o build.sse4_f_inl0_hrd0/MatrixElementKernels.o build.sse4_f_inl0_hrd0/BridgeKernels.o build.sse4_f_inl0_hrd0/CrossSectionKernels.o build.sse4_f_inl0_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl0_hrd0/fgcheck.exe build.sse4_f_inl0_hrd0/fcheck_sa.o build.sse4_f_inl0_hrd0/fsampler_cu.o -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl0_hrd0'  -lgfortran -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_gg_ttxgg_cuda build.sse4_f_inl0_hrd0/gRandomNumberKernels.o build.sse4_f_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_f_inl0_hrd0/fcheck.exe build.sse4_f_inl0_hrd0/fcheck_sa.o build.sse4_f_inl0_hrd0/fsampler.o -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_f_inl0_hrd0'  -lgfortran -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_gg_ttxgg_cpp build.sse4_f_inl0_hrd0/RandomNumberKernels.o build.sse4_f_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_f_inl0_hrd0/check.exe build.sse4_f_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_f_inl0_hrd0'  -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_gg_ttxgg_cpp build.sse4_f_inl0_hrd0/RandomNumberKernels.o build.sse4_f_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl0_hrd0/runTest.exe build.sse4_f_inl0_hrd0/CPPProcess.o build.sse4_f_inl0_hrd0/MatrixElementKernels.o build.sse4_f_inl0_hrd0/BridgeKernels.o build.sse4_f_inl0_hrd0/CrossSectionKernels.o build.sse4_f_inl0_hrd0/RandomNumberKernels.o build.sse4_f_inl0_hrd0/RamboSamplingKernels.o build.sse4_f_inl0_hrd0/testxxx.o  build.sse4_f_inl0_hrd0/testmisc.o  build.sse4_f_inl0_hrd0/runTest.o build.sse4_f_inl0_hrd0/gCPPProcess.o build.sse4_f_inl0_hrd0/gMatrixElementKernels.o build.sse4_f_inl0_hrd0/gBridgeKernels.o build.sse4_f_inl0_hrd0/gCrossSectionKernels.o build.sse4_f_inl0_hrd0/gRandomNumberKernels.o build.sse4_f_inl0_hrd0/gRamboSamplingKernels.o build.sse4_f_inl0_hrd0/testxxx_cu.o  build.sse4_f_inl0_hrd0/testmisc_cu.o  build.sse4_f_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.sse4_f_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl0_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
 touch build.sse4_f_inl0_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_f_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.sse4_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_f_inl0_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_f_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.sse4_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_f_inl0_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.sse4_f_inl0_hrd0/libmg5amc_gg_ttxgg_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_f_inl0_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.sse4_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_f_inl0_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:14:24
+DATE: 2022-09-25_00:32:22
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/check.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/check.exe -p 64 256 2 OMP=
 Process                     = SIGMA_SM_GG_TTXGG_CPP [gcc 11.2.0] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CPP:FLT+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK
 FP precision                = FLOAT (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 6.873277e+03                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 6.896028e+03                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 6.896028e+03                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 6.884133e+03                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 6.907134e+03                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 6.907134e+03                 )  sec^-1
 MeanMatrixElemValue         = ( 2.517793e+00 +- 1.234876e+00 )  GeV^-4
-TOTAL       :     4.777401 sec
-real	0m4.784s
+TOTAL       :     4.769748 sec
+real	0m4.776s
 =Symbols in CPPProcess.o= (~sse4:13397) (avx2:    0) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 6.627540e-04
 Avg ME (F77/C++)    = 6.6275400974055709E-004
 Relative difference = 1.4697092891509761e-08
@@ -7300,13 +7370,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:14:31 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -sse4only -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:32:42 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -sse4only -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -sse4only implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
 CUDACPP_BUILDDIR='build.sse4_f_inl1_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -7316,71 +7386,72 @@ HELINL=1
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.sse4_f_inl1_hrd0 for tag=sse4_f_inl1_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.sse4_f_inl1_hrd0
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.sse4_f_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.sse4_f_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.sse4_f_inl1_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.sse4_f_inl1_hrd0/gBridgeKernels.o
 AVX=sse4
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.sse4_f_inl1_hrd0/gcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.sse4_f_inl1_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.sse4_f_inl1_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.sse4_f_inl1_hrd0/gBridgeKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.sse4_f_inl1_hrd0/gCrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.sse4_f_inl1_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.sse4_f_inl1_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.sse4_f_inl1_hrd0/fbridge_cu.o
-mkdir -p ../lib/build.sse4_f_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.sse4_f_inl1_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.sse4_f_inl1_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.sse4_f_inl1_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.sse4_f_inl1_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.sse4_f_inl1_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.sse4_f_inl1_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.sse4_f_inl1_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.sse4_f_inl1_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.sse4_f_inl1_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.sse4_f_inl1_hrd0/BridgeKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.sse4_f_inl1_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.sse4_f_inl1_hrd0/fbridge.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.sse4_f_inl1_hrd0/RandomNumberKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.sse4_f_inl1_hrd0/testxxx.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.sse4_f_inl1_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.sse4_f_inl1_hrd0/testxxx_cu.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.sse4_f_inl1_hrd0/Parameters_sm.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.sse4_f_inl1_hrd0/testxxx.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.sse4_f_inl1_hrd0/read_slha.o
+mkdir -p ../lib/build.sse4_f_inl1_hrd0
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.sse4_f_inl1_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.sse4_f_inl1_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.sse4_f_inl1_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.sse4_f_inl1_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.sse4_f_inl1_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.sse4_f_inl1_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.sse4_f_inl1_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.sse4_f_inl1_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.sse4_f_inl1_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.sse4_f_inl1_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=nehalem  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.sse4_f_inl1_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.sse4_f_inl1_hrd0/libmg5amc_common.so build.sse4_f_inl1_hrd0/Parameters_sm.o build.sse4_f_inl1_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.sse4_f_inl1_hrd0/libmg5amc_gg_ttxgg_cuda.so build.sse4_f_inl1_hrd0/gCPPProcess.o build.sse4_f_inl1_hrd0/gMatrixElementKernels.o build.sse4_f_inl1_hrd0/gBridgeKernels.o build.sse4_f_inl1_hrd0/gCrossSectionKernels.o build.sse4_f_inl1_hrd0/fbridge_cu.o -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.sse4_f_inl1_hrd0/libmg5amc_gg_ttxgg_cpp.so build.sse4_f_inl1_hrd0/CPPProcess.o build.sse4_f_inl1_hrd0/MatrixElementKernels.o build.sse4_f_inl1_hrd0/BridgeKernels.o build.sse4_f_inl1_hrd0/CrossSectionKernels.o build.sse4_f_inl1_hrd0/fbridge.o -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl1_hrd0/runTest.exe build.sse4_f_inl1_hrd0/CPPProcess.o build.sse4_f_inl1_hrd0/MatrixElementKernels.o build.sse4_f_inl1_hrd0/BridgeKernels.o build.sse4_f_inl1_hrd0/CrossSectionKernels.o build.sse4_f_inl1_hrd0/RandomNumberKernels.o build.sse4_f_inl1_hrd0/RamboSamplingKernels.o build.sse4_f_inl1_hrd0/testxxx.o  build.sse4_f_inl1_hrd0/testmisc.o  build.sse4_f_inl1_hrd0/runTest.o build.sse4_f_inl1_hrd0/gCPPProcess.o build.sse4_f_inl1_hrd0/gMatrixElementKernels.o build.sse4_f_inl1_hrd0/gBridgeKernels.o build.sse4_f_inl1_hrd0/gCrossSectionKernels.o build.sse4_f_inl1_hrd0/gRandomNumberKernels.o build.sse4_f_inl1_hrd0/gRamboSamplingKernels.o build.sse4_f_inl1_hrd0/testxxx_cu.o  build.sse4_f_inl1_hrd0/testmisc_cu.o  build.sse4_f_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_f_inl1_hrd0/check.exe build.sse4_f_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_gg_ttxgg_cpp build.sse4_f_inl1_hrd0/RandomNumberKernels.o build.sse4_f_inl1_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_f_inl1_hrd0/fcheck.exe build.sse4_f_inl1_hrd0/fcheck_sa.o build.sse4_f_inl1_hrd0/fsampler.o -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_gg_ttxgg_cpp build.sse4_f_inl1_hrd0/RandomNumberKernels.o build.sse4_f_inl1_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl1_hrd0/gcheck.exe build.sse4_f_inl1_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_gg_ttxgg_cuda build.sse4_f_inl1_hrd0/gRandomNumberKernels.o build.sse4_f_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl1_hrd0/fgcheck.exe build.sse4_f_inl1_hrd0/fcheck_sa.o build.sse4_f_inl1_hrd0/fsampler_cu.o -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_gg_ttxgg_cuda build.sse4_f_inl1_hrd0/gRandomNumberKernels.o build.sse4_f_inl1_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.sse4_f_inl1_hrd0/libmg5amc_gg_ttxgg_cuda.so build.sse4_f_inl1_hrd0/gCPPProcess.o build.sse4_f_inl1_hrd0/gMatrixElementKernels.o build.sse4_f_inl1_hrd0/gBridgeKernels.o build.sse4_f_inl1_hrd0/gCrossSectionKernels.o build.sse4_f_inl1_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl1_hrd0/gcheck.exe build.sse4_f_inl1_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl1_hrd0'  -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_gg_ttxgg_cuda build.sse4_f_inl1_hrd0/gRandomNumberKernels.o build.sse4_f_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl1_hrd0/fgcheck.exe build.sse4_f_inl1_hrd0/fcheck_sa.o build.sse4_f_inl1_hrd0/fsampler_cu.o -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl1_hrd0'  -lgfortran -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_gg_ttxgg_cuda build.sse4_f_inl1_hrd0/gRandomNumberKernels.o build.sse4_f_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.sse4_f_inl1_hrd0/libmg5amc_gg_ttxgg_cpp.so build.sse4_f_inl1_hrd0/CPPProcess.o build.sse4_f_inl1_hrd0/MatrixElementKernels.o build.sse4_f_inl1_hrd0/BridgeKernels.o build.sse4_f_inl1_hrd0/CrossSectionKernels.o build.sse4_f_inl1_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.sse4_f_inl1_hrd0/runTest.exe build.sse4_f_inl1_hrd0/CPPProcess.o build.sse4_f_inl1_hrd0/MatrixElementKernels.o build.sse4_f_inl1_hrd0/BridgeKernels.o build.sse4_f_inl1_hrd0/CrossSectionKernels.o build.sse4_f_inl1_hrd0/RandomNumberKernels.o build.sse4_f_inl1_hrd0/RamboSamplingKernels.o build.sse4_f_inl1_hrd0/testxxx.o  build.sse4_f_inl1_hrd0/testmisc.o  build.sse4_f_inl1_hrd0/runTest.o build.sse4_f_inl1_hrd0/gCPPProcess.o build.sse4_f_inl1_hrd0/gMatrixElementKernels.o build.sse4_f_inl1_hrd0/gBridgeKernels.o build.sse4_f_inl1_hrd0/gCrossSectionKernels.o build.sse4_f_inl1_hrd0/gRandomNumberKernels.o build.sse4_f_inl1_hrd0/gRamboSamplingKernels.o build.sse4_f_inl1_hrd0/testxxx_cu.o  build.sse4_f_inl1_hrd0/testmisc_cu.o  build.sse4_f_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.sse4_f_inl1_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_f_inl1_hrd0/check.exe build.sse4_f_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_f_inl1_hrd0'  -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_gg_ttxgg_cpp build.sse4_f_inl1_hrd0/RandomNumberKernels.o build.sse4_f_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.sse4_f_inl1_hrd0/fcheck.exe build.sse4_f_inl1_hrd0/fcheck_sa.o build.sse4_f_inl1_hrd0/fsampler.o -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.sse4_f_inl1_hrd0'  -lgfortran -L../../lib/build.sse4_f_inl1_hrd0 -lmg5amc_gg_ttxgg_cpp build.sse4_f_inl1_hrd0/RandomNumberKernels.o build.sse4_f_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
 touch build.sse4_f_inl1_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_f_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.sse4_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_f_inl1_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_f_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.sse4_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_f_inl1_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.sse4_f_inl1_hrd0/libmg5amc_gg_ttxgg_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.sse4_f_inl1_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.sse4_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.sse4_f_inl1_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:14:32
+DATE: 2022-09-25_00:33:43
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl1_hrd0/check.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl1_hrd0/check.exe -p 64 256 2 OMP=
 Process                     = SIGMA_SM_GG_TTXGG_CPP [gcc 11.2.0] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CPP:FLT+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK
 FP precision                = FLOAT (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 6.056537e+03                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 6.074891e+03                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 6.074891e+03                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 6.075127e+03                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 6.092928e+03                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 6.092928e+03                 )  sec^-1
 MeanMatrixElemValue         = ( 2.518116e+00 +- 1.234928e+00 )  GeV^-4
-TOTAL       :     5.420806 sec
-real	0m5.427s
+TOTAL       :     5.404193 sec
+real	0m5.411s
 =Symbols in CPPProcess.o= (~sse4:74344) (avx2:    0) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl1_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl1_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl1_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl1_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 6.627546e-04
 Avg ME (F77/C++)    = 6.6275456215294376E-004
 Relative difference = 5.7105686204481305e-08
@@ -7388,13 +7459,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:14:42 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -avx2only  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:34:04 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -avx2only  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -avx2only implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
 CUDACPP_BUILDDIR='build.avx2_d_inl0_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -7404,22 +7475,18 @@ HELINL=0
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.avx2_d_inl0_hrd0 for tag=avx2_d_inl0_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.avx2_d_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gcheck_sa.cu -o build.avx2_d_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gcheck_sa.cu -o build.avx2_d_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gCPPProcess.cu -o build.avx2_d_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.avx2_d_inl0_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gBridgeKernels.cu -o build.avx2_d_inl0_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.avx2_d_inl0_hrd0/gCrossSectionKernels.o
 AVX=avx2
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gCPPProcess.cu -o build.avx2_d_inl0_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.avx2_d_inl0_hrd0/gMatrixElementKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gBridgeKernels.cu -o build.avx2_d_inl0_hrd0/gBridgeKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -c Parameters_sm.cc -o build.avx2_d_inl0_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -c read_slha.cc -o build.avx2_d_inl0_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.avx2_d_inl0_hrd0/gCrossSectionKernels.o
-mkdir -p ../lib/build.avx2_d_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fbridge.cc -o build.avx2_d_inl0_hrd0/fbridge_cu.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.avx2_d_inl0_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.avx2_d_inl0_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fbridge.cc -o build.avx2_d_inl0_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.avx2_d_inl0_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.avx2_d_inl0_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.avx2_d_inl0_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.avx2_d_inl0_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.avx2_d_inl0_hrd0/MatrixElementKernels.o
@@ -7427,48 +7494,53 @@ ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.avx2_d_inl0_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.avx2_d_inl0_hrd0/fbridge.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.avx2_d_inl0_hrd0/RandomNumberKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.avx2_d_inl0_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.avx2_d_inl0_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testxxx.cc -o build.avx2_d_inl0_hrd0/testxxx_cu.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -c Parameters_sm.cc -o build.avx2_d_inl0_hrd0/Parameters_sm.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testxxx.cc -o build.avx2_d_inl0_hrd0/testxxx_cu.o
+mkdir -p ../lib/build.avx2_d_inl0_hrd0
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -c read_slha.cc -o build.avx2_d_inl0_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.avx2_d_inl0_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testmisc.cc -o build.avx2_d_inl0_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testmisc.cc -o build.avx2_d_inl0_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.avx2_d_inl0_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu runTest.cc -o build.avx2_d_inl0_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu runTest.cc -o build.avx2_d_inl0_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.avx2_d_inl0_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fsampler.cc -o build.avx2_d_inl0_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fsampler.cc -o build.avx2_d_inl0_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.avx2_d_inl0_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.avx2_d_inl0_hrd0/libmg5amc_common.so build.avx2_d_inl0_hrd0/Parameters_sm.o build.avx2_d_inl0_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.avx2_d_inl0_hrd0/libmg5amc_gg_ttxgg_cuda.so build.avx2_d_inl0_hrd0/gCPPProcess.o build.avx2_d_inl0_hrd0/gMatrixElementKernels.o build.avx2_d_inl0_hrd0/gBridgeKernels.o build.avx2_d_inl0_hrd0/gCrossSectionKernels.o build.avx2_d_inl0_hrd0/fbridge_cu.o -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.avx2_d_inl0_hrd0/libmg5amc_gg_ttxgg_cpp.so build.avx2_d_inl0_hrd0/CPPProcess.o build.avx2_d_inl0_hrd0/MatrixElementKernels.o build.avx2_d_inl0_hrd0/BridgeKernels.o build.avx2_d_inl0_hrd0/CrossSectionKernels.o build.avx2_d_inl0_hrd0/fbridge.o -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl0_hrd0/runTest.exe build.avx2_d_inl0_hrd0/CPPProcess.o build.avx2_d_inl0_hrd0/MatrixElementKernels.o build.avx2_d_inl0_hrd0/BridgeKernels.o build.avx2_d_inl0_hrd0/CrossSectionKernels.o build.avx2_d_inl0_hrd0/RandomNumberKernels.o build.avx2_d_inl0_hrd0/RamboSamplingKernels.o build.avx2_d_inl0_hrd0/testxxx.o  build.avx2_d_inl0_hrd0/testmisc.o  build.avx2_d_inl0_hrd0/runTest.o build.avx2_d_inl0_hrd0/gCPPProcess.o build.avx2_d_inl0_hrd0/gMatrixElementKernels.o build.avx2_d_inl0_hrd0/gBridgeKernels.o build.avx2_d_inl0_hrd0/gCrossSectionKernels.o build.avx2_d_inl0_hrd0/gRandomNumberKernels.o build.avx2_d_inl0_hrd0/gRamboSamplingKernels.o build.avx2_d_inl0_hrd0/testxxx_cu.o  build.avx2_d_inl0_hrd0/testmisc_cu.o  build.avx2_d_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_d_inl0_hrd0/check.exe build.avx2_d_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_gg_ttxgg_cpp build.avx2_d_inl0_hrd0/RandomNumberKernels.o build.avx2_d_inl0_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_d_inl0_hrd0/fcheck.exe build.avx2_d_inl0_hrd0/fcheck_sa.o build.avx2_d_inl0_hrd0/fsampler.o -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_gg_ttxgg_cpp build.avx2_d_inl0_hrd0/RandomNumberKernels.o build.avx2_d_inl0_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl0_hrd0/gcheck.exe build.avx2_d_inl0_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_gg_ttxgg_cuda build.avx2_d_inl0_hrd0/gRandomNumberKernels.o build.avx2_d_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl0_hrd0/fgcheck.exe build.avx2_d_inl0_hrd0/fcheck_sa.o build.avx2_d_inl0_hrd0/fsampler_cu.o -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_gg_ttxgg_cuda build.avx2_d_inl0_hrd0/gRandomNumberKernels.o build.avx2_d_inl0_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.avx2_d_inl0_hrd0/libmg5amc_gg_ttxgg_cuda.so build.avx2_d_inl0_hrd0/gCPPProcess.o build.avx2_d_inl0_hrd0/gMatrixElementKernels.o build.avx2_d_inl0_hrd0/gBridgeKernels.o build.avx2_d_inl0_hrd0/gCrossSectionKernels.o build.avx2_d_inl0_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl0_hrd0/gcheck.exe build.avx2_d_inl0_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl0_hrd0'  -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_gg_ttxgg_cuda build.avx2_d_inl0_hrd0/gRandomNumberKernels.o build.avx2_d_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl0_hrd0/fgcheck.exe build.avx2_d_inl0_hrd0/fcheck_sa.o build.avx2_d_inl0_hrd0/fsampler_cu.o -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl0_hrd0'  -lgfortran -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_gg_ttxgg_cuda build.avx2_d_inl0_hrd0/gRandomNumberKernels.o build.avx2_d_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.avx2_d_inl0_hrd0/libmg5amc_gg_ttxgg_cpp.so build.avx2_d_inl0_hrd0/CPPProcess.o build.avx2_d_inl0_hrd0/MatrixElementKernels.o build.avx2_d_inl0_hrd0/BridgeKernels.o build.avx2_d_inl0_hrd0/CrossSectionKernels.o build.avx2_d_inl0_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_d_inl0_hrd0/check.exe build.avx2_d_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_d_inl0_hrd0'  -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_gg_ttxgg_cpp build.avx2_d_inl0_hrd0/RandomNumberKernels.o build.avx2_d_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_d_inl0_hrd0/fcheck.exe build.avx2_d_inl0_hrd0/fcheck_sa.o build.avx2_d_inl0_hrd0/fsampler.o -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_d_inl0_hrd0'  -lgfortran -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_gg_ttxgg_cpp build.avx2_d_inl0_hrd0/RandomNumberKernels.o build.avx2_d_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl0_hrd0/runTest.exe build.avx2_d_inl0_hrd0/CPPProcess.o build.avx2_d_inl0_hrd0/MatrixElementKernels.o build.avx2_d_inl0_hrd0/BridgeKernels.o build.avx2_d_inl0_hrd0/CrossSectionKernels.o build.avx2_d_inl0_hrd0/RandomNumberKernels.o build.avx2_d_inl0_hrd0/RamboSamplingKernels.o build.avx2_d_inl0_hrd0/testxxx.o  build.avx2_d_inl0_hrd0/testmisc.o  build.avx2_d_inl0_hrd0/runTest.o build.avx2_d_inl0_hrd0/gCPPProcess.o build.avx2_d_inl0_hrd0/gMatrixElementKernels.o build.avx2_d_inl0_hrd0/gBridgeKernels.o build.avx2_d_inl0_hrd0/gCrossSectionKernels.o build.avx2_d_inl0_hrd0/gRandomNumberKernels.o build.avx2_d_inl0_hrd0/gRamboSamplingKernels.o build.avx2_d_inl0_hrd0/testxxx_cu.o  build.avx2_d_inl0_hrd0/testmisc_cu.o  build.avx2_d_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.avx2_d_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl0_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
 touch build.avx2_d_inl0_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_d_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.avx2_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_d_inl0_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_d_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.avx2_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_d_inl0_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.avx2_d_inl0_hrd0/libmg5amc_gg_ttxgg_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_d_inl0_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.avx2_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_d_inl0_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:14:43
+DATE: 2022-09-25_00:34:13
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/check.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/check.exe -p 64 256 2 OMP=
 Process                     = SIGMA_SM_GG_TTXGG_CPP [gcc 11.2.0] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CPP:DBL+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 6.634244e+03                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 6.660616e+03                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 6.660616e+03                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 6.646331e+03                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 6.672596e+03                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 6.672596e+03                 )  sec^-1
 MeanMatrixElemValue         = ( 2.520822e+00 +- 1.235793e+00 )  GeV^-4
-TOTAL       :     4.951548 sec
-real	0m4.958s
+TOTAL       :     4.942579 sec
+real	0m4.949s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2:10617) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 6.626675e-04
 Avg ME (F77/C++)    = 6.6266731198157342E-004
 Relative difference = 2.837296631655439e-07
@@ -7476,13 +7548,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:14:51 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -avx2only  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:34:33 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -avx2only  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -avx2only implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
 CUDACPP_BUILDDIR='build.avx2_d_inl1_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -7492,71 +7564,72 @@ HELINL=1
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.avx2_d_inl1_hrd0 for tag=avx2_d_inl1_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.avx2_d_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.avx2_d_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.avx2_d_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.avx2_d_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.avx2_d_inl1_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.avx2_d_inl1_hrd0/gBridgeKernels.o
 AVX=avx2
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.avx2_d_inl1_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.avx2_d_inl1_hrd0/gMatrixElementKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.avx2_d_inl1_hrd0/gBridgeKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.avx2_d_inl1_hrd0/gCrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.avx2_d_inl1_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.avx2_d_inl1_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.avx2_d_inl1_hrd0/fbridge_cu.o
-mkdir -p ../lib/build.avx2_d_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.avx2_d_inl1_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.avx2_d_inl1_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.avx2_d_inl1_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.avx2_d_inl1_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.avx2_d_inl1_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.avx2_d_inl1_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.avx2_d_inl1_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.avx2_d_inl1_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.avx2_d_inl1_hrd0/MatrixElementKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.avx2_d_inl1_hrd0/BridgeKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.avx2_d_inl1_hrd0/read_slha.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.avx2_d_inl1_hrd0/Parameters_sm.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.avx2_d_inl1_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.avx2_d_inl1_hrd0/fbridge.o
+mkdir -p ../lib/build.avx2_d_inl1_hrd0
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.avx2_d_inl1_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.avx2_d_inl1_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.avx2_d_inl1_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.avx2_d_inl1_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.avx2_d_inl1_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.avx2_d_inl1_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.avx2_d_inl1_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.avx2_d_inl1_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.avx2_d_inl1_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.avx2_d_inl1_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.avx2_d_inl1_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.avx2_d_inl1_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.avx2_d_inl1_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.avx2_d_inl1_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.avx2_d_inl1_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.avx2_d_inl1_hrd0/libmg5amc_common.so build.avx2_d_inl1_hrd0/Parameters_sm.o build.avx2_d_inl1_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.avx2_d_inl1_hrd0/libmg5amc_gg_ttxgg_cuda.so build.avx2_d_inl1_hrd0/gCPPProcess.o build.avx2_d_inl1_hrd0/gMatrixElementKernels.o build.avx2_d_inl1_hrd0/gBridgeKernels.o build.avx2_d_inl1_hrd0/gCrossSectionKernels.o build.avx2_d_inl1_hrd0/fbridge_cu.o -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.avx2_d_inl1_hrd0/libmg5amc_gg_ttxgg_cpp.so build.avx2_d_inl1_hrd0/CPPProcess.o build.avx2_d_inl1_hrd0/MatrixElementKernels.o build.avx2_d_inl1_hrd0/BridgeKernels.o build.avx2_d_inl1_hrd0/CrossSectionKernels.o build.avx2_d_inl1_hrd0/fbridge.o -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl1_hrd0/runTest.exe build.avx2_d_inl1_hrd0/CPPProcess.o build.avx2_d_inl1_hrd0/MatrixElementKernels.o build.avx2_d_inl1_hrd0/BridgeKernels.o build.avx2_d_inl1_hrd0/CrossSectionKernels.o build.avx2_d_inl1_hrd0/RandomNumberKernels.o build.avx2_d_inl1_hrd0/RamboSamplingKernels.o build.avx2_d_inl1_hrd0/testxxx.o  build.avx2_d_inl1_hrd0/testmisc.o  build.avx2_d_inl1_hrd0/runTest.o build.avx2_d_inl1_hrd0/gCPPProcess.o build.avx2_d_inl1_hrd0/gMatrixElementKernels.o build.avx2_d_inl1_hrd0/gBridgeKernels.o build.avx2_d_inl1_hrd0/gCrossSectionKernels.o build.avx2_d_inl1_hrd0/gRandomNumberKernels.o build.avx2_d_inl1_hrd0/gRamboSamplingKernels.o build.avx2_d_inl1_hrd0/testxxx_cu.o  build.avx2_d_inl1_hrd0/testmisc_cu.o  build.avx2_d_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_d_inl1_hrd0/check.exe build.avx2_d_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_gg_ttxgg_cpp build.avx2_d_inl1_hrd0/RandomNumberKernels.o build.avx2_d_inl1_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_d_inl1_hrd0/fcheck.exe build.avx2_d_inl1_hrd0/fcheck_sa.o build.avx2_d_inl1_hrd0/fsampler.o -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_gg_ttxgg_cpp build.avx2_d_inl1_hrd0/RandomNumberKernels.o build.avx2_d_inl1_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl1_hrd0/gcheck.exe build.avx2_d_inl1_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_gg_ttxgg_cuda build.avx2_d_inl1_hrd0/gRandomNumberKernels.o build.avx2_d_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl1_hrd0/fgcheck.exe build.avx2_d_inl1_hrd0/fcheck_sa.o build.avx2_d_inl1_hrd0/fsampler_cu.o -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_gg_ttxgg_cuda build.avx2_d_inl1_hrd0/gRandomNumberKernels.o build.avx2_d_inl1_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.avx2_d_inl1_hrd0/libmg5amc_gg_ttxgg_cuda.so build.avx2_d_inl1_hrd0/gCPPProcess.o build.avx2_d_inl1_hrd0/gMatrixElementKernels.o build.avx2_d_inl1_hrd0/gBridgeKernels.o build.avx2_d_inl1_hrd0/gCrossSectionKernels.o build.avx2_d_inl1_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl1_hrd0/gcheck.exe build.avx2_d_inl1_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl1_hrd0'  -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_gg_ttxgg_cuda build.avx2_d_inl1_hrd0/gRandomNumberKernels.o build.avx2_d_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl1_hrd0/fgcheck.exe build.avx2_d_inl1_hrd0/fcheck_sa.o build.avx2_d_inl1_hrd0/fsampler_cu.o -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl1_hrd0'  -lgfortran -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_gg_ttxgg_cuda build.avx2_d_inl1_hrd0/gRandomNumberKernels.o build.avx2_d_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.avx2_d_inl1_hrd0/libmg5amc_gg_ttxgg_cpp.so build.avx2_d_inl1_hrd0/CPPProcess.o build.avx2_d_inl1_hrd0/MatrixElementKernels.o build.avx2_d_inl1_hrd0/BridgeKernels.o build.avx2_d_inl1_hrd0/CrossSectionKernels.o build.avx2_d_inl1_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_d_inl1_hrd0/runTest.exe build.avx2_d_inl1_hrd0/CPPProcess.o build.avx2_d_inl1_hrd0/MatrixElementKernels.o build.avx2_d_inl1_hrd0/BridgeKernels.o build.avx2_d_inl1_hrd0/CrossSectionKernels.o build.avx2_d_inl1_hrd0/RandomNumberKernels.o build.avx2_d_inl1_hrd0/RamboSamplingKernels.o build.avx2_d_inl1_hrd0/testxxx.o  build.avx2_d_inl1_hrd0/testmisc.o  build.avx2_d_inl1_hrd0/runTest.o build.avx2_d_inl1_hrd0/gCPPProcess.o build.avx2_d_inl1_hrd0/gMatrixElementKernels.o build.avx2_d_inl1_hrd0/gBridgeKernels.o build.avx2_d_inl1_hrd0/gCrossSectionKernels.o build.avx2_d_inl1_hrd0/gRandomNumberKernels.o build.avx2_d_inl1_hrd0/gRamboSamplingKernels.o build.avx2_d_inl1_hrd0/testxxx_cu.o  build.avx2_d_inl1_hrd0/testmisc_cu.o  build.avx2_d_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_d_inl1_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_d_inl1_hrd0/check.exe build.avx2_d_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_d_inl1_hrd0'  -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_gg_ttxgg_cpp build.avx2_d_inl1_hrd0/RandomNumberKernels.o build.avx2_d_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_d_inl1_hrd0/fcheck.exe build.avx2_d_inl1_hrd0/fcheck_sa.o build.avx2_d_inl1_hrd0/fsampler.o -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_d_inl1_hrd0'  -lgfortran -L../../lib/build.avx2_d_inl1_hrd0 -lmg5amc_gg_ttxgg_cpp build.avx2_d_inl1_hrd0/RandomNumberKernels.o build.avx2_d_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
 touch build.avx2_d_inl1_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_d_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.avx2_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_d_inl1_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_d_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.avx2_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_d_inl1_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.avx2_d_inl1_hrd0/libmg5amc_gg_ttxgg_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_d_inl1_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.avx2_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_d_inl1_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:14:52
+DATE: 2022-09-25_00:35:37
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl1_hrd0/check.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl1_hrd0/check.exe -p 64 256 2 OMP=
 Process                     = SIGMA_SM_GG_TTXGG_CPP [gcc 11.2.0] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CPP:DBL+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 5.421023e+03                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 5.438571e+03                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 5.438571e+03                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 5.432806e+03                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 5.450271e+03                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 5.450271e+03                 )  sec^-1
 MeanMatrixElemValue         = ( 2.520822e+00 +- 1.235793e+00 )  GeV^-4
-TOTAL       :     6.057892 sec
-real	0m6.065s
+TOTAL       :     6.044456 sec
+real	0m6.051s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2:51187) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl1_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl1_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl1_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl1_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 6.626675e-04
 Avg ME (F77/C++)    = 6.6266731198156789E-004
 Relative difference = 2.837296715097453e-07
@@ -7564,13 +7637,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:15:04 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -avx2only -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:35:58 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -avx2only -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -avx2only implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
 CUDACPP_BUILDDIR='build.avx2_f_inl0_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -7580,71 +7653,72 @@ HELINL=0
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.avx2_f_inl0_hrd0 for tag=avx2_f_inl0_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.avx2_f_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gcheck_sa.cu -o build.avx2_f_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gcheck_sa.cu -o build.avx2_f_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gCPPProcess.cu -o build.avx2_f_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.avx2_f_inl0_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gBridgeKernels.cu -o build.avx2_f_inl0_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.avx2_f_inl0_hrd0/gCrossSectionKernels.o
 AVX=avx2
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gCPPProcess.cu -o build.avx2_f_inl0_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.avx2_f_inl0_hrd0/gMatrixElementKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gBridgeKernels.cu -o build.avx2_f_inl0_hrd0/gBridgeKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -c read_slha.cc -o build.avx2_f_inl0_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.avx2_f_inl0_hrd0/gCrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -c Parameters_sm.cc -o build.avx2_f_inl0_hrd0/Parameters_sm.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fbridge.cc -o build.avx2_f_inl0_hrd0/fbridge_cu.o
-mkdir -p ../lib/build.avx2_f_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.avx2_f_inl0_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.avx2_f_inl0_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fbridge.cc -o build.avx2_f_inl0_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.avx2_f_inl0_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.avx2_f_inl0_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.avx2_f_inl0_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.avx2_f_inl0_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.avx2_f_inl0_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.avx2_f_inl0_hrd0/BridgeKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.avx2_f_inl0_hrd0/CrossSectionKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.avx2_f_inl0_hrd0/fbridge.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.avx2_f_inl0_hrd0/RandomNumberKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -c Parameters_sm.cc -o build.avx2_f_inl0_hrd0/Parameters_sm.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -c read_slha.cc -o build.avx2_f_inl0_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.avx2_f_inl0_hrd0/RamboSamplingKernels.o
+mkdir -p ../lib/build.avx2_f_inl0_hrd0
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.avx2_f_inl0_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testxxx.cc -o build.avx2_f_inl0_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testxxx.cc -o build.avx2_f_inl0_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.avx2_f_inl0_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testmisc.cc -o build.avx2_f_inl0_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testmisc.cc -o build.avx2_f_inl0_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.avx2_f_inl0_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu runTest.cc -o build.avx2_f_inl0_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu runTest.cc -o build.avx2_f_inl0_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.avx2_f_inl0_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fsampler.cc -o build.avx2_f_inl0_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fsampler.cc -o build.avx2_f_inl0_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.avx2_f_inl0_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.avx2_f_inl0_hrd0/libmg5amc_common.so build.avx2_f_inl0_hrd0/Parameters_sm.o build.avx2_f_inl0_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.avx2_f_inl0_hrd0/libmg5amc_gg_ttxgg_cuda.so build.avx2_f_inl0_hrd0/gCPPProcess.o build.avx2_f_inl0_hrd0/gMatrixElementKernels.o build.avx2_f_inl0_hrd0/gBridgeKernels.o build.avx2_f_inl0_hrd0/gCrossSectionKernels.o build.avx2_f_inl0_hrd0/fbridge_cu.o -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.avx2_f_inl0_hrd0/libmg5amc_gg_ttxgg_cpp.so build.avx2_f_inl0_hrd0/CPPProcess.o build.avx2_f_inl0_hrd0/MatrixElementKernels.o build.avx2_f_inl0_hrd0/BridgeKernels.o build.avx2_f_inl0_hrd0/CrossSectionKernels.o build.avx2_f_inl0_hrd0/fbridge.o -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl0_hrd0/runTest.exe build.avx2_f_inl0_hrd0/CPPProcess.o build.avx2_f_inl0_hrd0/MatrixElementKernels.o build.avx2_f_inl0_hrd0/BridgeKernels.o build.avx2_f_inl0_hrd0/CrossSectionKernels.o build.avx2_f_inl0_hrd0/RandomNumberKernels.o build.avx2_f_inl0_hrd0/RamboSamplingKernels.o build.avx2_f_inl0_hrd0/testxxx.o  build.avx2_f_inl0_hrd0/testmisc.o  build.avx2_f_inl0_hrd0/runTest.o build.avx2_f_inl0_hrd0/gCPPProcess.o build.avx2_f_inl0_hrd0/gMatrixElementKernels.o build.avx2_f_inl0_hrd0/gBridgeKernels.o build.avx2_f_inl0_hrd0/gCrossSectionKernels.o build.avx2_f_inl0_hrd0/gRandomNumberKernels.o build.avx2_f_inl0_hrd0/gRamboSamplingKernels.o build.avx2_f_inl0_hrd0/testxxx_cu.o  build.avx2_f_inl0_hrd0/testmisc_cu.o  build.avx2_f_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_f_inl0_hrd0/check.exe build.avx2_f_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_gg_ttxgg_cpp build.avx2_f_inl0_hrd0/RandomNumberKernels.o build.avx2_f_inl0_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_f_inl0_hrd0/fcheck.exe build.avx2_f_inl0_hrd0/fcheck_sa.o build.avx2_f_inl0_hrd0/fsampler.o -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_gg_ttxgg_cpp build.avx2_f_inl0_hrd0/RandomNumberKernels.o build.avx2_f_inl0_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl0_hrd0/gcheck.exe build.avx2_f_inl0_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_gg_ttxgg_cuda build.avx2_f_inl0_hrd0/gRandomNumberKernels.o build.avx2_f_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl0_hrd0/fgcheck.exe build.avx2_f_inl0_hrd0/fcheck_sa.o build.avx2_f_inl0_hrd0/fsampler_cu.o -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_gg_ttxgg_cuda build.avx2_f_inl0_hrd0/gRandomNumberKernels.o build.avx2_f_inl0_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.avx2_f_inl0_hrd0/libmg5amc_gg_ttxgg_cuda.so build.avx2_f_inl0_hrd0/gCPPProcess.o build.avx2_f_inl0_hrd0/gMatrixElementKernels.o build.avx2_f_inl0_hrd0/gBridgeKernels.o build.avx2_f_inl0_hrd0/gCrossSectionKernels.o build.avx2_f_inl0_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl0_hrd0/gcheck.exe build.avx2_f_inl0_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl0_hrd0'  -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_gg_ttxgg_cuda build.avx2_f_inl0_hrd0/gRandomNumberKernels.o build.avx2_f_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl0_hrd0/fgcheck.exe build.avx2_f_inl0_hrd0/fcheck_sa.o build.avx2_f_inl0_hrd0/fsampler_cu.o -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl0_hrd0'  -lgfortran -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_gg_ttxgg_cuda build.avx2_f_inl0_hrd0/gRandomNumberKernels.o build.avx2_f_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.avx2_f_inl0_hrd0/libmg5amc_gg_ttxgg_cpp.so build.avx2_f_inl0_hrd0/CPPProcess.o build.avx2_f_inl0_hrd0/MatrixElementKernels.o build.avx2_f_inl0_hrd0/BridgeKernels.o build.avx2_f_inl0_hrd0/CrossSectionKernels.o build.avx2_f_inl0_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_f_inl0_hrd0/fcheck.exe build.avx2_f_inl0_hrd0/fcheck_sa.o build.avx2_f_inl0_hrd0/fsampler.o -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_f_inl0_hrd0'  -lgfortran -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_gg_ttxgg_cpp build.avx2_f_inl0_hrd0/RandomNumberKernels.o build.avx2_f_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl0_hrd0/runTest.exe build.avx2_f_inl0_hrd0/CPPProcess.o build.avx2_f_inl0_hrd0/MatrixElementKernels.o build.avx2_f_inl0_hrd0/BridgeKernels.o build.avx2_f_inl0_hrd0/CrossSectionKernels.o build.avx2_f_inl0_hrd0/RandomNumberKernels.o build.avx2_f_inl0_hrd0/RamboSamplingKernels.o build.avx2_f_inl0_hrd0/testxxx.o  build.avx2_f_inl0_hrd0/testmisc.o  build.avx2_f_inl0_hrd0/runTest.o build.avx2_f_inl0_hrd0/gCPPProcess.o build.avx2_f_inl0_hrd0/gMatrixElementKernels.o build.avx2_f_inl0_hrd0/gBridgeKernels.o build.avx2_f_inl0_hrd0/gCrossSectionKernels.o build.avx2_f_inl0_hrd0/gRandomNumberKernels.o build.avx2_f_inl0_hrd0/gRamboSamplingKernels.o build.avx2_f_inl0_hrd0/testxxx_cu.o  build.avx2_f_inl0_hrd0/testmisc_cu.o  build.avx2_f_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl0_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_f_inl0_hrd0/check.exe build.avx2_f_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_f_inl0_hrd0'  -L../../lib/build.avx2_f_inl0_hrd0 -lmg5amc_gg_ttxgg_cpp build.avx2_f_inl0_hrd0/RandomNumberKernels.o build.avx2_f_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
 touch build.avx2_f_inl0_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_f_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.avx2_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_f_inl0_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_f_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.avx2_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_f_inl0_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.avx2_f_inl0_hrd0/libmg5amc_gg_ttxgg_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_f_inl0_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.avx2_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_f_inl0_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:15:05
+DATE: 2022-09-25_00:36:08
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/check.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/check.exe -p 64 256 2 OMP=
 Process                     = SIGMA_SM_GG_TTXGG_CPP [gcc 11.2.0] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CPP:FLT+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK
 FP precision                = FLOAT (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 1.326489e+04                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 1.335051e+04                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 1.335051e+04                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 1.326202e+04                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 1.334830e+04                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 1.334830e+04                 )  sec^-1
 MeanMatrixElemValue         = ( 2.517556e+00 +- 1.234627e+00 )  GeV^-4
-TOTAL       :     2.479304 sec
+TOTAL       :     2.479828 sec
 real	0m2.486s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2:10873) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 6.627261e-04
 Avg ME (F77/C++)    = 6.6272607119444160E-004
 Relative difference = 4.3465254221897804e-08
@@ -7652,13 +7726,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:15:10 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -avx2only -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:36:26 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -avx2only -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -avx2only implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
 CUDACPP_BUILDDIR='build.avx2_f_inl1_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -7668,71 +7742,72 @@ HELINL=1
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.avx2_f_inl1_hrd0 for tag=avx2_f_inl1_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.avx2_f_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.avx2_f_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.avx2_f_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.avx2_f_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.avx2_f_inl1_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.avx2_f_inl1_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.avx2_f_inl1_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.avx2_f_inl1_hrd0/fbridge_cu.o
 AVX=avx2
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.avx2_f_inl1_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.avx2_f_inl1_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.avx2_f_inl1_hrd0/gBridgeKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.avx2_f_inl1_hrd0/gCrossSectionKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.avx2_f_inl1_hrd0/fbridge_cu.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.avx2_f_inl1_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.avx2_f_inl1_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.avx2_f_inl1_hrd0/gRandomNumberKernels.o
-mkdir -p ../lib/build.avx2_f_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.avx2_f_inl1_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.avx2_f_inl1_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.avx2_f_inl1_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.avx2_f_inl1_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.avx2_f_inl1_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.avx2_f_inl1_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.avx2_f_inl1_hrd0/BridgeKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.avx2_f_inl1_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.avx2_f_inl1_hrd0/fbridge.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.avx2_f_inl1_hrd0/RandomNumberKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.avx2_f_inl1_hrd0/CrossSectionKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.avx2_f_inl1_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.avx2_f_inl1_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.avx2_f_inl1_hrd0/testxxx_cu.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.avx2_f_inl1_hrd0/Parameters_sm.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.avx2_f_inl1_hrd0/testxxx_cu.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.avx2_f_inl1_hrd0/read_slha.o
+mkdir -p ../lib/build.avx2_f_inl1_hrd0
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.avx2_f_inl1_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.avx2_f_inl1_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.avx2_f_inl1_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.avx2_f_inl1_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.avx2_f_inl1_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.avx2_f_inl1_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.avx2_f_inl1_hrd0/fcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.avx2_f_inl1_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=haswell  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.avx2_f_inl1_hrd0/fsampler.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.avx2_f_inl1_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.avx2_f_inl1_hrd0/libmg5amc_common.so build.avx2_f_inl1_hrd0/Parameters_sm.o build.avx2_f_inl1_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.avx2_f_inl1_hrd0/libmg5amc_gg_ttxgg_cuda.so build.avx2_f_inl1_hrd0/gCPPProcess.o build.avx2_f_inl1_hrd0/gMatrixElementKernels.o build.avx2_f_inl1_hrd0/gBridgeKernels.o build.avx2_f_inl1_hrd0/gCrossSectionKernels.o build.avx2_f_inl1_hrd0/fbridge_cu.o -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.avx2_f_inl1_hrd0/libmg5amc_gg_ttxgg_cpp.so build.avx2_f_inl1_hrd0/CPPProcess.o build.avx2_f_inl1_hrd0/MatrixElementKernels.o build.avx2_f_inl1_hrd0/BridgeKernels.o build.avx2_f_inl1_hrd0/CrossSectionKernels.o build.avx2_f_inl1_hrd0/fbridge.o -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl1_hrd0/runTest.exe build.avx2_f_inl1_hrd0/CPPProcess.o build.avx2_f_inl1_hrd0/MatrixElementKernels.o build.avx2_f_inl1_hrd0/BridgeKernels.o build.avx2_f_inl1_hrd0/CrossSectionKernels.o build.avx2_f_inl1_hrd0/RandomNumberKernels.o build.avx2_f_inl1_hrd0/RamboSamplingKernels.o build.avx2_f_inl1_hrd0/testxxx.o  build.avx2_f_inl1_hrd0/testmisc.o  build.avx2_f_inl1_hrd0/runTest.o build.avx2_f_inl1_hrd0/gCPPProcess.o build.avx2_f_inl1_hrd0/gMatrixElementKernels.o build.avx2_f_inl1_hrd0/gBridgeKernels.o build.avx2_f_inl1_hrd0/gCrossSectionKernels.o build.avx2_f_inl1_hrd0/gRandomNumberKernels.o build.avx2_f_inl1_hrd0/gRamboSamplingKernels.o build.avx2_f_inl1_hrd0/testxxx_cu.o  build.avx2_f_inl1_hrd0/testmisc_cu.o  build.avx2_f_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_f_inl1_hrd0/check.exe build.avx2_f_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_gg_ttxgg_cpp build.avx2_f_inl1_hrd0/RandomNumberKernels.o build.avx2_f_inl1_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_f_inl1_hrd0/fcheck.exe build.avx2_f_inl1_hrd0/fcheck_sa.o build.avx2_f_inl1_hrd0/fsampler.o -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_gg_ttxgg_cpp build.avx2_f_inl1_hrd0/RandomNumberKernels.o build.avx2_f_inl1_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl1_hrd0/gcheck.exe build.avx2_f_inl1_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_gg_ttxgg_cuda build.avx2_f_inl1_hrd0/gRandomNumberKernels.o build.avx2_f_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl1_hrd0/fgcheck.exe build.avx2_f_inl1_hrd0/fcheck_sa.o build.avx2_f_inl1_hrd0/fsampler_cu.o -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_gg_ttxgg_cuda build.avx2_f_inl1_hrd0/gRandomNumberKernels.o build.avx2_f_inl1_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.avx2_f_inl1_hrd0/libmg5amc_gg_ttxgg_cuda.so build.avx2_f_inl1_hrd0/gCPPProcess.o build.avx2_f_inl1_hrd0/gMatrixElementKernels.o build.avx2_f_inl1_hrd0/gBridgeKernels.o build.avx2_f_inl1_hrd0/gCrossSectionKernels.o build.avx2_f_inl1_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl1_hrd0/gcheck.exe build.avx2_f_inl1_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl1_hrd0'  -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_gg_ttxgg_cuda build.avx2_f_inl1_hrd0/gRandomNumberKernels.o build.avx2_f_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl1_hrd0/fgcheck.exe build.avx2_f_inl1_hrd0/fcheck_sa.o build.avx2_f_inl1_hrd0/fsampler_cu.o -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl1_hrd0'  -lgfortran -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_gg_ttxgg_cuda build.avx2_f_inl1_hrd0/gRandomNumberKernels.o build.avx2_f_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.avx2_f_inl1_hrd0/libmg5amc_gg_ttxgg_cpp.so build.avx2_f_inl1_hrd0/CPPProcess.o build.avx2_f_inl1_hrd0/MatrixElementKernels.o build.avx2_f_inl1_hrd0/BridgeKernels.o build.avx2_f_inl1_hrd0/CrossSectionKernels.o build.avx2_f_inl1_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.avx2_f_inl1_hrd0/runTest.exe build.avx2_f_inl1_hrd0/CPPProcess.o build.avx2_f_inl1_hrd0/MatrixElementKernels.o build.avx2_f_inl1_hrd0/BridgeKernels.o build.avx2_f_inl1_hrd0/CrossSectionKernels.o build.avx2_f_inl1_hrd0/RandomNumberKernels.o build.avx2_f_inl1_hrd0/RamboSamplingKernels.o build.avx2_f_inl1_hrd0/testxxx.o  build.avx2_f_inl1_hrd0/testmisc.o  build.avx2_f_inl1_hrd0/runTest.o build.avx2_f_inl1_hrd0/gCPPProcess.o build.avx2_f_inl1_hrd0/gMatrixElementKernels.o build.avx2_f_inl1_hrd0/gBridgeKernels.o build.avx2_f_inl1_hrd0/gCrossSectionKernels.o build.avx2_f_inl1_hrd0/gRandomNumberKernels.o build.avx2_f_inl1_hrd0/gRamboSamplingKernels.o build.avx2_f_inl1_hrd0/testxxx_cu.o  build.avx2_f_inl1_hrd0/testmisc_cu.o  build.avx2_f_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.avx2_f_inl1_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_f_inl1_hrd0/check.exe build.avx2_f_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_f_inl1_hrd0'  -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_gg_ttxgg_cpp build.avx2_f_inl1_hrd0/RandomNumberKernels.o build.avx2_f_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.avx2_f_inl1_hrd0/fcheck.exe build.avx2_f_inl1_hrd0/fcheck_sa.o build.avx2_f_inl1_hrd0/fsampler.o -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.avx2_f_inl1_hrd0'  -lgfortran -L../../lib/build.avx2_f_inl1_hrd0 -lmg5amc_gg_ttxgg_cpp build.avx2_f_inl1_hrd0/RandomNumberKernels.o build.avx2_f_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
 touch build.avx2_f_inl1_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_f_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.avx2_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_f_inl1_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_f_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.avx2_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_f_inl1_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.avx2_f_inl1_hrd0/libmg5amc_gg_ttxgg_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.avx2_f_inl1_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.avx2_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.avx2_f_inl1_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:15:11
+DATE: 2022-09-25_00:37:30
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl1_hrd0/check.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl1_hrd0/check.exe -p 64 256 2 OMP=
 Process                     = SIGMA_SM_GG_TTXGG_CPP [gcc 11.2.0] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CPP:FLT+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK
 FP precision                = FLOAT (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 1.058731e+04                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 1.064182e+04                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 1.064182e+04                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 1.062633e+04                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 1.068101e+04                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 1.068101e+04                 )  sec^-1
 MeanMatrixElemValue         = ( 2.517788e+00 +- 1.234525e+00 )  GeV^-4
-TOTAL       :     3.104505 sec
-real	0m3.111s
+TOTAL       :     3.092917 sec
+real	0m3.099s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2:52471) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl1_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl1_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl1_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl1_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 6.627344e-04
 Avg ME (F77/C++)    = 6.6273438490734721E-004
 Relative difference = 2.277330529689946e-08
@@ -7740,35 +7815,35 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:15:19 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -512yonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:37:48 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -512yonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -512yonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
 CUDACPP_BUILDDIR='build.512y_d_inl0_hrd0'
 make: Nothing to be done for `all'.
 
-DATE: 2022-08-31_21:15:19
+DATE: 2022-09-25_00:37:49
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/check.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/check.exe -p 64 256 2 OMP=
 Process                     = SIGMA_SM_GG_TTXGG_CPP [gcc 11.2.0] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 7.501605e+03                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 7.535246e+03                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 7.535246e+03                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 7.503622e+03                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 7.536929e+03                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 7.536929e+03                 )  sec^-1
 MeanMatrixElemValue         = ( 2.520822e+00 +- 1.235793e+00 )  GeV^-4
-TOTAL       :     4.380205 sec
-real	0m4.388s
+TOTAL       :     4.378837 sec
+real	0m4.386s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2:10350) (512y:   12) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 6.626675e-04
 Avg ME (F77/C++)    = 6.6266731198157342E-004
 Relative difference = 2.837296631655439e-07
@@ -7776,35 +7851,35 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:15:26 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -512yonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:38:08 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -512yonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -512yonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
 CUDACPP_BUILDDIR='build.512y_d_inl1_hrd0'
 make: Nothing to be done for `all'.
 
-DATE: 2022-08-31_21:15:26
+DATE: 2022-09-25_00:38:08
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl1_hrd0/check.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl1_hrd0/check.exe -p 64 256 2 OMP=
 Process                     = SIGMA_SM_GG_TTXGG_CPP [gcc 11.2.0] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 6.860751e+03                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 6.888757e+03                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 6.888757e+03                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 6.875030e+03                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 6.903341e+03                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 6.903341e+03                 )  sec^-1
 MeanMatrixElemValue         = ( 2.520822e+00 +- 1.235793e+00 )  GeV^-4
-TOTAL       :     4.788489 sec
-real	0m4.795s
+TOTAL       :     4.778525 sec
+real	0m4.785s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2:41989) (512y:  182) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl1_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl1_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl1_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl1_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 6.626675e-04
 Avg ME (F77/C++)    = 6.6266731198156789E-004
 Relative difference = 2.837296715097453e-07
@@ -7812,35 +7887,35 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:15:35 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -512yonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:38:28 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -512yonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -512yonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
 CUDACPP_BUILDDIR='build.512y_f_inl0_hrd0'
 make: Nothing to be done for `all'.
 
-DATE: 2022-08-31_21:15:35
+DATE: 2022-09-25_00:38:29
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/check.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/check.exe -p 64 256 2 OMP=
 Process                     = SIGMA_SM_GG_TTXGG_CPP [gcc 11.2.0] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK
 FP precision                = FLOAT (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 1.484077e+04                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 1.494719e+04                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 1.494719e+04                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 1.475673e+04                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 1.486278e+04                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 1.486278e+04                 )  sec^-1
 MeanMatrixElemValue         = ( 2.517556e+00 +- 1.234627e+00 )  GeV^-4
-TOTAL       :     2.216792 sec
-real	0m2.224s
+TOTAL       :     2.229339 sec
+real	0m2.236s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2:10579) (512y:   13) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 6.627261e-04
 Avg ME (F77/C++)    = 6.6272607119444160E-004
 Relative difference = 4.3465254221897804e-08
@@ -7848,35 +7923,35 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:15:40 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -512yonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:38:46 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -512yonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -512yonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
 CUDACPP_BUILDDIR='build.512y_f_inl1_hrd0'
 make: Nothing to be done for `all'.
 
-DATE: 2022-08-31_21:15:40
+DATE: 2022-09-25_00:38:46
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl1_hrd0/check.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl1_hrd0/check.exe -p 64 256 2 OMP=
 Process                     = SIGMA_SM_GG_TTXGG_CPP [gcc 11.2.0] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK
 FP precision                = FLOAT (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 1.331836e+04                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 1.340442e+04                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 1.340442e+04                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 1.333937e+04                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 1.342521e+04                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 1.342521e+04                 )  sec^-1
 MeanMatrixElemValue         = ( 2.517788e+00 +- 1.234525e+00 )  GeV^-4
-TOTAL       :     2.469428 sec
-real	0m2.476s
+TOTAL       :     2.465497 sec
+real	0m2.472s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2:43606) (512y:    0) (512z:    0)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl1_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl1_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl1_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl1_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 6.627344e-04
 Avg ME (F77/C++)    = 6.6273438490734721E-004
 Relative difference = 2.277330529689946e-08
@@ -7884,13 +7959,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:15:45 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -512zonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:39:04 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -512zonly  ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -512zonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
 CUDACPP_BUILDDIR='build.512z_d_inl0_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -7900,71 +7975,72 @@ HELINL=0
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.512z_d_inl0_hrd0 for tag=512z_d_inl0_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.512z_d_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gcheck_sa.cu -o build.512z_d_inl0_hrd0/gcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gCPPProcess.cu -o build.512z_d_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gcheck_sa.cu -o build.512z_d_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gCPPProcess.cu -o build.512z_d_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512z_d_inl0_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512z_d_inl0_hrd0/gBridgeKernels.o
 AVX=512z
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512z_d_inl0_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512z_d_inl0_hrd0/gBridgeKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512z_d_inl0_hrd0/gCrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -c Parameters_sm.cc -o build.512z_d_inl0_hrd0/Parameters_sm.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512z_d_inl0_hrd0/fbridge_cu.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -c read_slha.cc -o build.512z_d_inl0_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512z_d_inl0_hrd0/gRandomNumberKernels.o
-mkdir -p ../lib/build.512z_d_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512z_d_inl0_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512z_d_inl0_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512z_d_inl0_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512z_d_inl0_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512z_d_inl0_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.512z_d_inl0_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.512z_d_inl0_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.512z_d_inl0_hrd0/MatrixElementKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -c Parameters_sm.cc -o build.512z_d_inl0_hrd0/Parameters_sm.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.512z_d_inl0_hrd0/BridgeKernels.o
+mkdir -p ../lib/build.512z_d_inl0_hrd0
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -c read_slha.cc -o build.512z_d_inl0_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.512z_d_inl0_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.512z_d_inl0_hrd0/fbridge.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.512z_d_inl0_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.512z_d_inl0_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.512z_d_inl0_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512z_d_inl0_hrd0/testxxx_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512z_d_inl0_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.512z_d_inl0_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512z_d_inl0_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512z_d_inl0_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.512z_d_inl0_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu runTest.cc -o build.512z_d_inl0_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu runTest.cc -o build.512z_d_inl0_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.512z_d_inl0_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512z_d_inl0_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512z_d_inl0_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.512z_d_inl0_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.512z_d_inl0_hrd0/libmg5amc_common.so build.512z_d_inl0_hrd0/Parameters_sm.o build.512z_d_inl0_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512z_d_inl0_hrd0/libmg5amc_gg_ttxgg_cuda.so build.512z_d_inl0_hrd0/gCPPProcess.o build.512z_d_inl0_hrd0/gMatrixElementKernels.o build.512z_d_inl0_hrd0/gBridgeKernels.o build.512z_d_inl0_hrd0/gCrossSectionKernels.o build.512z_d_inl0_hrd0/fbridge_cu.o -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512z_d_inl0_hrd0/libmg5amc_gg_ttxgg_cpp.so build.512z_d_inl0_hrd0/CPPProcess.o build.512z_d_inl0_hrd0/MatrixElementKernels.o build.512z_d_inl0_hrd0/BridgeKernels.o build.512z_d_inl0_hrd0/CrossSectionKernels.o build.512z_d_inl0_hrd0/fbridge.o -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl0_hrd0/runTest.exe build.512z_d_inl0_hrd0/CPPProcess.o build.512z_d_inl0_hrd0/MatrixElementKernels.o build.512z_d_inl0_hrd0/BridgeKernels.o build.512z_d_inl0_hrd0/CrossSectionKernels.o build.512z_d_inl0_hrd0/RandomNumberKernels.o build.512z_d_inl0_hrd0/RamboSamplingKernels.o build.512z_d_inl0_hrd0/testxxx.o  build.512z_d_inl0_hrd0/testmisc.o  build.512z_d_inl0_hrd0/runTest.o build.512z_d_inl0_hrd0/gCPPProcess.o build.512z_d_inl0_hrd0/gMatrixElementKernels.o build.512z_d_inl0_hrd0/gBridgeKernels.o build.512z_d_inl0_hrd0/gCrossSectionKernels.o build.512z_d_inl0_hrd0/gRandomNumberKernels.o build.512z_d_inl0_hrd0/gRamboSamplingKernels.o build.512z_d_inl0_hrd0/testxxx_cu.o  build.512z_d_inl0_hrd0/testmisc_cu.o  build.512z_d_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_d_inl0_hrd0/check.exe build.512z_d_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_gg_ttxgg_cpp build.512z_d_inl0_hrd0/RandomNumberKernels.o build.512z_d_inl0_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_d_inl0_hrd0/fcheck.exe build.512z_d_inl0_hrd0/fcheck_sa.o build.512z_d_inl0_hrd0/fsampler.o -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_gg_ttxgg_cpp build.512z_d_inl0_hrd0/RandomNumberKernels.o build.512z_d_inl0_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl0_hrd0/gcheck.exe build.512z_d_inl0_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_gg_ttxgg_cuda build.512z_d_inl0_hrd0/gRandomNumberKernels.o build.512z_d_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl0_hrd0/fgcheck.exe build.512z_d_inl0_hrd0/fcheck_sa.o build.512z_d_inl0_hrd0/fsampler_cu.o -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_gg_ttxgg_cuda build.512z_d_inl0_hrd0/gRandomNumberKernels.o build.512z_d_inl0_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512z_d_inl0_hrd0/libmg5amc_gg_ttxgg_cuda.so build.512z_d_inl0_hrd0/gCPPProcess.o build.512z_d_inl0_hrd0/gMatrixElementKernels.o build.512z_d_inl0_hrd0/gBridgeKernels.o build.512z_d_inl0_hrd0/gCrossSectionKernels.o build.512z_d_inl0_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl0_hrd0/gcheck.exe build.512z_d_inl0_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl0_hrd0'  -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_gg_ttxgg_cuda build.512z_d_inl0_hrd0/gRandomNumberKernels.o build.512z_d_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl0_hrd0/fgcheck.exe build.512z_d_inl0_hrd0/fcheck_sa.o build.512z_d_inl0_hrd0/fsampler_cu.o -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl0_hrd0'  -lgfortran -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_gg_ttxgg_cuda build.512z_d_inl0_hrd0/gRandomNumberKernels.o build.512z_d_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512z_d_inl0_hrd0/libmg5amc_gg_ttxgg_cpp.so build.512z_d_inl0_hrd0/CPPProcess.o build.512z_d_inl0_hrd0/MatrixElementKernels.o build.512z_d_inl0_hrd0/BridgeKernels.o build.512z_d_inl0_hrd0/CrossSectionKernels.o build.512z_d_inl0_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_d_inl0_hrd0/fcheck.exe build.512z_d_inl0_hrd0/fcheck_sa.o build.512z_d_inl0_hrd0/fsampler.o -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_d_inl0_hrd0'  -lgfortran -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_gg_ttxgg_cpp build.512z_d_inl0_hrd0/RandomNumberKernels.o build.512z_d_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_d_inl0_hrd0/check.exe build.512z_d_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_d_inl0_hrd0'  -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_gg_ttxgg_cpp build.512z_d_inl0_hrd0/RandomNumberKernels.o build.512z_d_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl0_hrd0/runTest.exe build.512z_d_inl0_hrd0/CPPProcess.o build.512z_d_inl0_hrd0/MatrixElementKernels.o build.512z_d_inl0_hrd0/BridgeKernels.o build.512z_d_inl0_hrd0/CrossSectionKernels.o build.512z_d_inl0_hrd0/RandomNumberKernels.o build.512z_d_inl0_hrd0/RamboSamplingKernels.o build.512z_d_inl0_hrd0/testxxx.o  build.512z_d_inl0_hrd0/testmisc.o  build.512z_d_inl0_hrd0/runTest.o build.512z_d_inl0_hrd0/gCPPProcess.o build.512z_d_inl0_hrd0/gMatrixElementKernels.o build.512z_d_inl0_hrd0/gBridgeKernels.o build.512z_d_inl0_hrd0/gCrossSectionKernels.o build.512z_d_inl0_hrd0/gRandomNumberKernels.o build.512z_d_inl0_hrd0/gRamboSamplingKernels.o build.512z_d_inl0_hrd0/testxxx_cu.o  build.512z_d_inl0_hrd0/testmisc_cu.o  build.512z_d_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.512z_d_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl0_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
 touch build.512z_d_inl0_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_d_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.512z_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_d_inl0_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_d_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512z_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_d_inl0_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.512z_d_inl0_hrd0/libmg5amc_gg_ttxgg_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_d_inl0_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512z_d_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_d_inl0_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:15:46
+DATE: 2022-09-25_00:39:14
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/check.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/check.exe -p 64 256 2 OMP=
 Process                     = SIGMA_SM_GG_TTXGG_CPP [gcc 11.2.0] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 6.442200e+03                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 6.467477e+03                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 6.467477e+03                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 6.459211e+03                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 6.486154e+03                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 6.486154e+03                 )  sec^-1
 MeanMatrixElemValue         = ( 2.520822e+00 +- 1.235793e+00 )  GeV^-4
-TOTAL       :     5.099242 sec
-real	0m5.106s
+TOTAL       :     5.085922 sec
+real	0m5.093s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2: 1266) (512y:   60) (512z: 9903)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 6.626675e-04
 Avg ME (F77/C++)    = 6.6266731198157342E-004
 Relative difference = 2.837296631655439e-07
@@ -7972,13 +8048,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:15:53 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -512zonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:39:34 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -512zonly  -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -512zonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
 CUDACPP_BUILDDIR='build.512z_d_inl1_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -7988,71 +8064,72 @@ HELINL=1
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.512z_d_inl1_hrd0 for tag=512z_d_inl1_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.512z_d_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.512z_d_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.512z_d_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.512z_d_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512z_d_inl1_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512z_d_inl1_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512z_d_inl1_hrd0/gCrossSectionKernels.o
 AVX=512z
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.512z_d_inl1_hrd0/gCPPProcess.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512z_d_inl1_hrd0/gMatrixElementKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.512z_d_inl1_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.512z_d_inl1_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512z_d_inl1_hrd0/gBridgeKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512z_d_inl1_hrd0/gCrossSectionKernels.o
-mkdir -p ../lib/build.512z_d_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512z_d_inl1_hrd0/fbridge_cu.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512z_d_inl1_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512z_d_inl1_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512z_d_inl1_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512z_d_inl1_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512z_d_inl1_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.512z_d_inl1_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.512z_d_inl1_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.512z_d_inl1_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.512z_d_inl1_hrd0/BridgeKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.512z_d_inl1_hrd0/CrossSectionKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.512z_d_inl1_hrd0/fbridge.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.512z_d_inl1_hrd0/RandomNumberKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.512z_d_inl1_hrd0/RamboSamplingKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.512z_d_inl1_hrd0/Parameters_sm.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.512z_d_inl1_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.512z_d_inl1_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512z_d_inl1_hrd0/testxxx_cu.o
+mkdir -p ../lib/build.512z_d_inl1_hrd0
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512z_d_inl1_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.512z_d_inl1_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512z_d_inl1_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512z_d_inl1_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.512z_d_inl1_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.512z_d_inl1_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.512z_d_inl1_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.512z_d_inl1_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512z_d_inl1_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512z_d_inl1_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_DOUBLE -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.512z_d_inl1_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.512z_d_inl1_hrd0/libmg5amc_common.so build.512z_d_inl1_hrd0/Parameters_sm.o build.512z_d_inl1_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512z_d_inl1_hrd0/libmg5amc_gg_ttxgg_cuda.so build.512z_d_inl1_hrd0/gCPPProcess.o build.512z_d_inl1_hrd0/gMatrixElementKernels.o build.512z_d_inl1_hrd0/gBridgeKernels.o build.512z_d_inl1_hrd0/gCrossSectionKernels.o build.512z_d_inl1_hrd0/fbridge_cu.o -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512z_d_inl1_hrd0/libmg5amc_gg_ttxgg_cpp.so build.512z_d_inl1_hrd0/CPPProcess.o build.512z_d_inl1_hrd0/MatrixElementKernels.o build.512z_d_inl1_hrd0/BridgeKernels.o build.512z_d_inl1_hrd0/CrossSectionKernels.o build.512z_d_inl1_hrd0/fbridge.o -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl1_hrd0/runTest.exe build.512z_d_inl1_hrd0/CPPProcess.o build.512z_d_inl1_hrd0/MatrixElementKernels.o build.512z_d_inl1_hrd0/BridgeKernels.o build.512z_d_inl1_hrd0/CrossSectionKernels.o build.512z_d_inl1_hrd0/RandomNumberKernels.o build.512z_d_inl1_hrd0/RamboSamplingKernels.o build.512z_d_inl1_hrd0/testxxx.o  build.512z_d_inl1_hrd0/testmisc.o  build.512z_d_inl1_hrd0/runTest.o build.512z_d_inl1_hrd0/gCPPProcess.o build.512z_d_inl1_hrd0/gMatrixElementKernels.o build.512z_d_inl1_hrd0/gBridgeKernels.o build.512z_d_inl1_hrd0/gCrossSectionKernels.o build.512z_d_inl1_hrd0/gRandomNumberKernels.o build.512z_d_inl1_hrd0/gRamboSamplingKernels.o build.512z_d_inl1_hrd0/testxxx_cu.o  build.512z_d_inl1_hrd0/testmisc_cu.o  build.512z_d_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_d_inl1_hrd0/check.exe build.512z_d_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_gg_ttxgg_cpp build.512z_d_inl1_hrd0/RandomNumberKernels.o build.512z_d_inl1_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_d_inl1_hrd0/fcheck.exe build.512z_d_inl1_hrd0/fcheck_sa.o build.512z_d_inl1_hrd0/fsampler.o -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_gg_ttxgg_cpp build.512z_d_inl1_hrd0/RandomNumberKernels.o build.512z_d_inl1_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl1_hrd0/gcheck.exe build.512z_d_inl1_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_gg_ttxgg_cuda build.512z_d_inl1_hrd0/gRandomNumberKernels.o build.512z_d_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl1_hrd0/fgcheck.exe build.512z_d_inl1_hrd0/fcheck_sa.o build.512z_d_inl1_hrd0/fsampler_cu.o -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_gg_ttxgg_cuda build.512z_d_inl1_hrd0/gRandomNumberKernels.o build.512z_d_inl1_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512z_d_inl1_hrd0/libmg5amc_gg_ttxgg_cuda.so build.512z_d_inl1_hrd0/gCPPProcess.o build.512z_d_inl1_hrd0/gMatrixElementKernels.o build.512z_d_inl1_hrd0/gBridgeKernels.o build.512z_d_inl1_hrd0/gCrossSectionKernels.o build.512z_d_inl1_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl1_hrd0/gcheck.exe build.512z_d_inl1_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl1_hrd0'  -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_gg_ttxgg_cuda build.512z_d_inl1_hrd0/gRandomNumberKernels.o build.512z_d_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl1_hrd0/fgcheck.exe build.512z_d_inl1_hrd0/fcheck_sa.o build.512z_d_inl1_hrd0/fsampler_cu.o -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl1_hrd0'  -lgfortran -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_gg_ttxgg_cuda build.512z_d_inl1_hrd0/gRandomNumberKernels.o build.512z_d_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512z_d_inl1_hrd0/libmg5amc_gg_ttxgg_cpp.so build.512z_d_inl1_hrd0/CPPProcess.o build.512z_d_inl1_hrd0/MatrixElementKernels.o build.512z_d_inl1_hrd0/BridgeKernels.o build.512z_d_inl1_hrd0/CrossSectionKernels.o build.512z_d_inl1_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_d_inl1_hrd0/runTest.exe build.512z_d_inl1_hrd0/CPPProcess.o build.512z_d_inl1_hrd0/MatrixElementKernels.o build.512z_d_inl1_hrd0/BridgeKernels.o build.512z_d_inl1_hrd0/CrossSectionKernels.o build.512z_d_inl1_hrd0/RandomNumberKernels.o build.512z_d_inl1_hrd0/RamboSamplingKernels.o build.512z_d_inl1_hrd0/testxxx.o  build.512z_d_inl1_hrd0/testmisc.o  build.512z_d_inl1_hrd0/runTest.o build.512z_d_inl1_hrd0/gCPPProcess.o build.512z_d_inl1_hrd0/gMatrixElementKernels.o build.512z_d_inl1_hrd0/gBridgeKernels.o build.512z_d_inl1_hrd0/gCrossSectionKernels.o build.512z_d_inl1_hrd0/gRandomNumberKernels.o build.512z_d_inl1_hrd0/gRamboSamplingKernels.o build.512z_d_inl1_hrd0/testxxx_cu.o  build.512z_d_inl1_hrd0/testmisc_cu.o  build.512z_d_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_d_inl1_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_d_inl1_hrd0/check.exe build.512z_d_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_d_inl1_hrd0'  -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_gg_ttxgg_cpp build.512z_d_inl1_hrd0/RandomNumberKernels.o build.512z_d_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_d_inl1_hrd0/fcheck.exe build.512z_d_inl1_hrd0/fcheck_sa.o build.512z_d_inl1_hrd0/fsampler.o -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_d_inl1_hrd0'  -lgfortran -L../../lib/build.512z_d_inl1_hrd0 -lmg5amc_gg_ttxgg_cpp build.512z_d_inl1_hrd0/RandomNumberKernels.o build.512z_d_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
 touch build.512z_d_inl1_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_d_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.512z_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_d_inl1_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_d_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512z_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_d_inl1_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.512z_d_inl1_hrd0/libmg5amc_gg_ttxgg_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_d_inl1_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512z_d_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_d_inl1_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:15:54
+DATE: 2022-09-25_00:40:38
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl1_hrd0/check.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl1_hrd0/check.exe -p 64 256 2 OMP=
 Process                     = SIGMA_SM_GG_TTXGG_CPP [gcc 11.2.0] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK
 FP precision                = DOUBLE (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 6.499808e+03                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 6.524867e+03                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 6.524867e+03                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 6.521506e+03                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 6.546711e+03                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 6.546711e+03                 )  sec^-1
 MeanMatrixElemValue         = ( 2.520822e+00 +- 1.235793e+00 )  GeV^-4
-TOTAL       :     5.054215 sec
-real	0m5.061s
+TOTAL       :     5.037447 sec
+real	0m5.044s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2: 1975) (512y:  308) (512z:40177)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl1_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl1_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl1_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl1_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 6.626675e-04
 Avg ME (F77/C++)    = 6.6266731198156789E-004
 Relative difference = 2.837296715097453e-07
@@ -8060,13 +8137,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:16:02 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -512zonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:40:58 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -512zonly -fltonly ' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -512zonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
 CUDACPP_BUILDDIR='build.512z_f_inl0_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -8076,22 +8153,18 @@ HELINL=0
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.512z_f_inl0_hrd0 for tag=512z_f_inl0_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.512z_f_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gcheck_sa.cu -o build.512z_f_inl0_hrd0/gcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gCPPProcess.cu -o build.512z_f_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gcheck_sa.cu -o build.512z_f_inl0_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gCPPProcess.cu -o build.512z_f_inl0_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512z_f_inl0_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512z_f_inl0_hrd0/gBridgeKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512z_f_inl0_hrd0/gCrossSectionKernels.o
 AVX=512z
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512z_f_inl0_hrd0/gMatrixElementKernels.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512z_f_inl0_hrd0/gBridgeKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512z_f_inl0_hrd0/gCrossSectionKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -c Parameters_sm.cc -o build.512z_f_inl0_hrd0/Parameters_sm.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -c read_slha.cc -o build.512z_f_inl0_hrd0/read_slha.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512z_f_inl0_hrd0/fbridge_cu.o
-mkdir -p ../lib/build.512z_f_inl0_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512z_f_inl0_hrd0/gRandomNumberKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512z_f_inl0_hrd0/gRamboSamplingKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512z_f_inl0_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512z_f_inl0_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512z_f_inl0_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.512z_f_inl0_hrd0/check_sa.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.512z_f_inl0_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.512z_f_inl0_hrd0/MatrixElementKernels.o
@@ -8099,48 +8172,53 @@ ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.512z_f_inl0_hrd0/CrossSectionKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.512z_f_inl0_hrd0/fbridge.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.512z_f_inl0_hrd0/RandomNumberKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.512z_f_inl0_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.512z_f_inl0_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512z_f_inl0_hrd0/testxxx_cu.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -c Parameters_sm.cc -o build.512z_f_inl0_hrd0/Parameters_sm.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512z_f_inl0_hrd0/testxxx_cu.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -c read_slha.cc -o build.512z_f_inl0_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.512z_f_inl0_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512z_f_inl0_hrd0/testmisc_cu.o
+mkdir -p ../lib/build.512z_f_inl0_hrd0
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512z_f_inl0_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.512z_f_inl0_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu runTest.cc -o build.512z_f_inl0_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu runTest.cc -o build.512z_f_inl0_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.512z_f_inl0_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512z_f_inl0_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512z_f_inl0_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.512z_f_inl0_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.512z_f_inl0_hrd0/libmg5amc_common.so build.512z_f_inl0_hrd0/Parameters_sm.o build.512z_f_inl0_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512z_f_inl0_hrd0/libmg5amc_gg_ttxgg_cuda.so build.512z_f_inl0_hrd0/gCPPProcess.o build.512z_f_inl0_hrd0/gMatrixElementKernels.o build.512z_f_inl0_hrd0/gBridgeKernels.o build.512z_f_inl0_hrd0/gCrossSectionKernels.o build.512z_f_inl0_hrd0/fbridge_cu.o -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512z_f_inl0_hrd0/libmg5amc_gg_ttxgg_cpp.so build.512z_f_inl0_hrd0/CPPProcess.o build.512z_f_inl0_hrd0/MatrixElementKernels.o build.512z_f_inl0_hrd0/BridgeKernels.o build.512z_f_inl0_hrd0/CrossSectionKernels.o build.512z_f_inl0_hrd0/fbridge.o -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl0_hrd0/runTest.exe build.512z_f_inl0_hrd0/CPPProcess.o build.512z_f_inl0_hrd0/MatrixElementKernels.o build.512z_f_inl0_hrd0/BridgeKernels.o build.512z_f_inl0_hrd0/CrossSectionKernels.o build.512z_f_inl0_hrd0/RandomNumberKernels.o build.512z_f_inl0_hrd0/RamboSamplingKernels.o build.512z_f_inl0_hrd0/testxxx.o  build.512z_f_inl0_hrd0/testmisc.o  build.512z_f_inl0_hrd0/runTest.o build.512z_f_inl0_hrd0/gCPPProcess.o build.512z_f_inl0_hrd0/gMatrixElementKernels.o build.512z_f_inl0_hrd0/gBridgeKernels.o build.512z_f_inl0_hrd0/gCrossSectionKernels.o build.512z_f_inl0_hrd0/gRandomNumberKernels.o build.512z_f_inl0_hrd0/gRamboSamplingKernels.o build.512z_f_inl0_hrd0/testxxx_cu.o  build.512z_f_inl0_hrd0/testmisc_cu.o  build.512z_f_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_f_inl0_hrd0/check.exe build.512z_f_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_gg_ttxgg_cpp build.512z_f_inl0_hrd0/RandomNumberKernels.o build.512z_f_inl0_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_f_inl0_hrd0/fcheck.exe build.512z_f_inl0_hrd0/fcheck_sa.o build.512z_f_inl0_hrd0/fsampler.o -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_gg_ttxgg_cpp build.512z_f_inl0_hrd0/RandomNumberKernels.o build.512z_f_inl0_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl0_hrd0/gcheck.exe build.512z_f_inl0_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_gg_ttxgg_cuda build.512z_f_inl0_hrd0/gRandomNumberKernels.o build.512z_f_inl0_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl0_hrd0/fgcheck.exe build.512z_f_inl0_hrd0/fcheck_sa.o build.512z_f_inl0_hrd0/fsampler_cu.o -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl0_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_gg_ttxgg_cuda build.512z_f_inl0_hrd0/gRandomNumberKernels.o build.512z_f_inl0_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512z_f_inl0_hrd0/libmg5amc_gg_ttxgg_cuda.so build.512z_f_inl0_hrd0/gCPPProcess.o build.512z_f_inl0_hrd0/gMatrixElementKernels.o build.512z_f_inl0_hrd0/gBridgeKernels.o build.512z_f_inl0_hrd0/gCrossSectionKernels.o build.512z_f_inl0_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512z_f_inl0_hrd0/libmg5amc_gg_ttxgg_cpp.so build.512z_f_inl0_hrd0/CPPProcess.o build.512z_f_inl0_hrd0/MatrixElementKernels.o build.512z_f_inl0_hrd0/BridgeKernels.o build.512z_f_inl0_hrd0/CrossSectionKernels.o build.512z_f_inl0_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl0_hrd0/gcheck.exe build.512z_f_inl0_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl0_hrd0'  -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_gg_ttxgg_cuda build.512z_f_inl0_hrd0/gRandomNumberKernels.o build.512z_f_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl0_hrd0/fgcheck.exe build.512z_f_inl0_hrd0/fcheck_sa.o build.512z_f_inl0_hrd0/fsampler_cu.o -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl0_hrd0'  -lgfortran -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_gg_ttxgg_cuda build.512z_f_inl0_hrd0/gRandomNumberKernels.o build.512z_f_inl0_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_f_inl0_hrd0/fcheck.exe build.512z_f_inl0_hrd0/fcheck_sa.o build.512z_f_inl0_hrd0/fsampler.o -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_f_inl0_hrd0'  -lgfortran -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_gg_ttxgg_cpp build.512z_f_inl0_hrd0/RandomNumberKernels.o build.512z_f_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl0_hrd0/runTest.exe build.512z_f_inl0_hrd0/CPPProcess.o build.512z_f_inl0_hrd0/MatrixElementKernels.o build.512z_f_inl0_hrd0/BridgeKernels.o build.512z_f_inl0_hrd0/CrossSectionKernels.o build.512z_f_inl0_hrd0/RandomNumberKernels.o build.512z_f_inl0_hrd0/RamboSamplingKernels.o build.512z_f_inl0_hrd0/testxxx.o  build.512z_f_inl0_hrd0/testmisc.o  build.512z_f_inl0_hrd0/runTest.o build.512z_f_inl0_hrd0/gCPPProcess.o build.512z_f_inl0_hrd0/gMatrixElementKernels.o build.512z_f_inl0_hrd0/gBridgeKernels.o build.512z_f_inl0_hrd0/gCrossSectionKernels.o build.512z_f_inl0_hrd0/gRandomNumberKernels.o build.512z_f_inl0_hrd0/gRamboSamplingKernels.o build.512z_f_inl0_hrd0/testxxx_cu.o  build.512z_f_inl0_hrd0/testmisc_cu.o  build.512z_f_inl0_hrd0/runTest_cu.o -ldl -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl0_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_f_inl0_hrd0/check.exe build.512z_f_inl0_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_f_inl0_hrd0'  -L../../lib/build.512z_f_inl0_hrd0 -lmg5amc_gg_ttxgg_cpp build.512z_f_inl0_hrd0/RandomNumberKernels.o build.512z_f_inl0_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
 touch build.512z_f_inl0_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_f_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.512z_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_f_inl0_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_f_inl0_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512z_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_f_inl0_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.512z_f_inl0_hrd0/libmg5amc_gg_ttxgg_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_f_inl0_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512z_f_inl0_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_f_inl0_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:16:03
+DATE: 2022-09-25_00:41:08
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/check.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/check.exe -p 64 256 2 OMP=
 Process                     = SIGMA_SM_GG_TTXGG_CPP [gcc 11.2.0] [inlineHel=0] [hardcodePARAM=0]
 Workflow summary            = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK
 FP precision                = FLOAT (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 1.296767e+04                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 1.305237e+04                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 1.305237e+04                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 1.297245e+04                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 1.305475e+04                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 1.305475e+04                 )  sec^-1
 MeanMatrixElemValue         = ( 2.517556e+00 +- 1.234627e+00 )  GeV^-4
-TOTAL       :     2.536305 sec
-real	0m2.543s
+TOTAL       :     2.535266 sec
+real	0m2.542s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2: 1370) (512y:   19) (512z: 9913)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 6.627263e-04
 Avg ME (F77/C++)    = 6.6272629010484529E-004
 Relative difference = 1.4930982341604305e-08
@@ -8148,13 +8226,13 @@ OK (relative difference <= 2E-4)
 =========================================================================
 
 TEST COMPLETED
-[doOne (1)] Wed Aug 31 21:16:09 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -512zonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/tput
+[doOne (1)] Sun Sep 25 00:41:25 CEST 2022 Will execute './throughputX.sh -makej -ggttgg -512zonly -fltonly -inlonly' from /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/tput
 WARNING! Option -512zonly implies -nocuda
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/test
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/test
 make: Nothing to be done for `all'.
 
-Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
+Building in /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg
 CUDACPP_BUILDDIR='build.512z_f_inl1_hrd0'
 make -f cudacpp.mk
 OMPFLAGS=
@@ -8164,71 +8242,72 @@ HELINL=1
 HRDCOD=0
 RNDGEN=hasCurand
 Building in BUILDDIR=build.512z_f_inl1_hrd0 for tag=512z_f_inl1_hrd0_hasCurand (USEBUILDDIR is set = 1)
-make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
+make[1]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
 make -C ../../src  -f cudacpp_src.mk
 mkdir -p build.512z_f_inl1_hrd0
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.512z_f_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gcheck_sa.cu -o build.512z_f_inl1_hrd0/gcheck_sa.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.512z_f_inl1_hrd0/gCPPProcess.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512z_f_inl1_hrd0/gMatrixElementKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512z_f_inl1_hrd0/gBridgeKernels.o
 AVX=512z
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gCPPProcess.cu -o build.512z_f_inl1_hrd0/gCPPProcess.o
-make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gMatrixElementKernels.cu -o build.512z_f_inl1_hrd0/gMatrixElementKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gBridgeKernels.cu -o build.512z_f_inl1_hrd0/gBridgeKernels.o
-mkdir -p ../lib/build.512z_f_inl1_hrd0
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.512z_f_inl1_hrd0/read_slha.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.512z_f_inl1_hrd0/Parameters_sm.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512z_f_inl1_hrd0/gCrossSectionKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512z_f_inl1_hrd0/fbridge_cu.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512z_f_inl1_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fno-fast-math -Xcompiler -fPIC -c gCrossSectionKernels.cu -o build.512z_f_inl1_hrd0/gCrossSectionKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fbridge.cc -o build.512z_f_inl1_hrd0/fbridge_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRandomNumberKernels.cu -o build.512z_f_inl1_hrd0/gRandomNumberKernels.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512z_f_inl1_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c check_sa.cc -o build.512z_f_inl1_hrd0/check_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c gRamboSamplingKernels.cu -o build.512z_f_inl1_hrd0/gRamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c CPPProcess.cc -o build.512z_f_inl1_hrd0/CPPProcess.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c MatrixElementKernels.cc -o build.512z_f_inl1_hrd0/MatrixElementKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c BridgeKernels.cc -o build.512z_f_inl1_hrd0/BridgeKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -fno-fast-math -fno-fast-math -I/usr/local/cuda-11.7/include/ -fPIC -c CrossSectionKernels.cc -o build.512z_f_inl1_hrd0/CrossSectionKernels.o
+make[2]: Entering directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fbridge.cc -o build.512z_f_inl1_hrd0/fbridge.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c read_slha.cc -o build.512z_f_inl1_hrd0/read_slha.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RandomNumberKernels.cc -o build.512z_f_inl1_hrd0/RandomNumberKernels.o
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I.  -fPIC -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -c Parameters_sm.cc -o build.512z_f_inl1_hrd0/Parameters_sm.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c RamboSamplingKernels.cc -o build.512z_f_inl1_hrd0/RamboSamplingKernels.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testxxx.cc -o build.512z_f_inl1_hrd0/testxxx.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512z_f_inl1_hrd0/testxxx_cu.o
+mkdir -p ../lib/build.512z_f_inl1_hrd0
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testxxx.cc -o build.512z_f_inl1_hrd0/testxxx_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c testmisc.cc -o build.512z_f_inl1_hrd0/testmisc.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512z_f_inl1_hrd0/testmisc_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu testmisc.cc -o build.512z_f_inl1_hrd0/testmisc_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c runTest.cc -o build.512z_f_inl1_hrd0/runTest.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.512z_f_inl1_hrd0/runTest_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I../../../../../test/googletest/googletest/include -I../../../../../test/googletest/googletest/include -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu runTest.cc -o build.512z_f_inl1_hrd0/runTest_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -I. -c fcheck_sa.f -o build.512z_f_inl1_hrd0/fcheck_sa.o
-ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512z_f_inl1_hrd0/fsampler_cu.o
+ccache /usr/local/cuda-11.7/bin/nvcc  -O3  -lineinfo -I. -I../../src -I../../../../../tools -I/usr/local/cuda-11.7/include/ -DUSE_NVTX -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -use_fast_math -std=c++17  -ccbin /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -Xcompiler -fPIC -c -x cu fsampler.cc -o build.512z_f_inl1_hrd0/fsampler_cu.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++  -O3  -std=c++17 -I. -I../../src -I../../../../../tools -DUSE_NVTX -Wall -Wshadow -Wextra -ffast-math   -march=skylake-avx512 -DMGONGPU_PVW512  -DMGONGPU_FPTYPE_FLOAT -DMGONGPU_INLINE_HELAMPS -I/usr/local/cuda-11.7/include/ -fPIC -c fsampler.cc -o build.512z_f_inl1_hrd0/fsampler.o
 ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o../lib/build.512z_f_inl1_hrd0/libmg5amc_common.so build.512z_f_inl1_hrd0/Parameters_sm.o build.512z_f_inl1_hrd0/read_slha.o
-make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
-ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512z_f_inl1_hrd0/libmg5amc_gg_ttxgg_cuda.so build.512z_f_inl1_hrd0/gCPPProcess.o build.512z_f_inl1_hrd0/gMatrixElementKernels.o build.512z_f_inl1_hrd0/gBridgeKernels.o build.512z_f_inl1_hrd0/gCrossSectionKernels.o build.512z_f_inl1_hrd0/fbridge_cu.o -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512z_f_inl1_hrd0/libmg5amc_gg_ttxgg_cpp.so build.512z_f_inl1_hrd0/CPPProcess.o build.512z_f_inl1_hrd0/MatrixElementKernels.o build.512z_f_inl1_hrd0/BridgeKernels.o build.512z_f_inl1_hrd0/CrossSectionKernels.o build.512z_f_inl1_hrd0/fbridge.o -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl1_hrd0/runTest.exe build.512z_f_inl1_hrd0/CPPProcess.o build.512z_f_inl1_hrd0/MatrixElementKernels.o build.512z_f_inl1_hrd0/BridgeKernels.o build.512z_f_inl1_hrd0/CrossSectionKernels.o build.512z_f_inl1_hrd0/RandomNumberKernels.o build.512z_f_inl1_hrd0/RamboSamplingKernels.o build.512z_f_inl1_hrd0/testxxx.o  build.512z_f_inl1_hrd0/testmisc.o  build.512z_f_inl1_hrd0/runTest.o build.512z_f_inl1_hrd0/gCPPProcess.o build.512z_f_inl1_hrd0/gMatrixElementKernels.o build.512z_f_inl1_hrd0/gBridgeKernels.o build.512z_f_inl1_hrd0/gCrossSectionKernels.o build.512z_f_inl1_hrd0/gRandomNumberKernels.o build.512z_f_inl1_hrd0/gRamboSamplingKernels.o build.512z_f_inl1_hrd0/testxxx_cu.o  build.512z_f_inl1_hrd0/testmisc_cu.o  build.512z_f_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lcuda -lgomp
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_f_inl1_hrd0/check.exe build.512z_f_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_gg_ttxgg_cpp build.512z_f_inl1_hrd0/RandomNumberKernels.o build.512z_f_inl1_hrd0/RamboSamplingKernels.o
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_f_inl1_hrd0/fcheck.exe build.512z_f_inl1_hrd0/fcheck_sa.o build.512z_f_inl1_hrd0/fsampler.o -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_gg_ttxgg_cpp build.512z_f_inl1_hrd0/RandomNumberKernels.o build.512z_f_inl1_hrd0/RamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl1_hrd0/gcheck.exe build.512z_f_inl1_hrd0/gcheck_sa.o -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_gg_ttxgg_cuda build.512z_f_inl1_hrd0/gRandomNumberKernels.o build.512z_f_inl1_hrd0/gRamboSamplingKernels.o
-ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl1_hrd0/fgcheck.exe build.512z_f_inl1_hrd0/fcheck_sa.o build.512z_f_inl1_hrd0/fsampler_cu.o -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl1_hrd0'  -L/usr/local/cuda-11.7/lib64/ -lcurand  -lgfortran -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_gg_ttxgg_cuda build.512z_f_inl1_hrd0/gRandomNumberKernels.o build.512z_f_inl1_hrd0/gRamboSamplingKernels.o
-make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
+make[2]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/src'
+ccache /usr/local/cuda-11.7/bin/nvcc --shared -o ../../lib/build.512z_f_inl1_hrd0/libmg5amc_gg_ttxgg_cuda.so build.512z_f_inl1_hrd0/gCPPProcess.o build.512z_f_inl1_hrd0/gMatrixElementKernels.o build.512z_f_inl1_hrd0/gBridgeKernels.o build.512z_f_inl1_hrd0/gCrossSectionKernels.o build.512z_f_inl1_hrd0/fbridge_cu.o -Xlinker -rpath,'$ORIGIN' -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl1_hrd0/gcheck.exe build.512z_f_inl1_hrd0/gcheck_sa.o -gencode arch=compute_60,code=compute_60 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=compute_70 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=compute_80 -gencode arch=compute_80,code=sm_80 -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl1_hrd0'  -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_gg_ttxgg_cuda build.512z_f_inl1_hrd0/gRandomNumberKernels.o build.512z_f_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl1_hrd0/fgcheck.exe build.512z_f_inl1_hrd0/fcheck_sa.o build.512z_f_inl1_hrd0/fsampler_cu.o -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl1_hrd0'  -lgfortran -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_gg_ttxgg_cuda build.512z_f_inl1_hrd0/gRandomNumberKernels.o build.512z_f_inl1_hrd0/gRamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -shared -o ../../lib/build.512z_f_inl1_hrd0/libmg5amc_gg_ttxgg_cpp.so build.512z_f_inl1_hrd0/CPPProcess.o build.512z_f_inl1_hrd0/MatrixElementKernels.o build.512z_f_inl1_hrd0/BridgeKernels.o build.512z_f_inl1_hrd0/CrossSectionKernels.o build.512z_f_inl1_hrd0/fbridge.o -Wl,-rpath,'$ORIGIN' -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common
+ccache /usr/local/cuda-11.7/bin/nvcc -o build.512z_f_inl1_hrd0/runTest.exe build.512z_f_inl1_hrd0/CPPProcess.o build.512z_f_inl1_hrd0/MatrixElementKernels.o build.512z_f_inl1_hrd0/BridgeKernels.o build.512z_f_inl1_hrd0/CrossSectionKernels.o build.512z_f_inl1_hrd0/RandomNumberKernels.o build.512z_f_inl1_hrd0/RamboSamplingKernels.o build.512z_f_inl1_hrd0/testxxx.o  build.512z_f_inl1_hrd0/testmisc.o  build.512z_f_inl1_hrd0/runTest.o build.512z_f_inl1_hrd0/gCPPProcess.o build.512z_f_inl1_hrd0/gMatrixElementKernels.o build.512z_f_inl1_hrd0/gBridgeKernels.o build.512z_f_inl1_hrd0/gCrossSectionKernels.o build.512z_f_inl1_hrd0/gRandomNumberKernels.o build.512z_f_inl1_hrd0/gRamboSamplingKernels.o build.512z_f_inl1_hrd0/testxxx_cu.o  build.512z_f_inl1_hrd0/testmisc_cu.o  build.512z_f_inl1_hrd0/runTest_cu.o -ldl -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common -L../../../../../test/googletest/build/lib/ -lgtest -lgtest_main -Xlinker -rpath,'$ORIGIN/../../../lib/build.512z_f_inl1_hrd0'  -lcuda -lgomp -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_f_inl1_hrd0/check.exe build.512z_f_inl1_hrd0/check_sa.o  -ldl -pthread -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_f_inl1_hrd0'  -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_gg_ttxgg_cpp build.512z_f_inl1_hrd0/RandomNumberKernels.o build.512z_f_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/g++ -o build.512z_f_inl1_hrd0/fcheck.exe build.512z_f_inl1_hrd0/fcheck_sa.o build.512z_f_inl1_hrd0/fsampler.o -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_common -Wl,-rpath,'$ORIGIN/../../../lib/build.512z_f_inl1_hrd0'  -lgfortran -L../../lib/build.512z_f_inl1_hrd0 -lmg5amc_gg_ttxgg_cpp build.512z_f_inl1_hrd0/RandomNumberKernels.o build.512z_f_inl1_hrd0/RamboSamplingKernels.o -L/usr/local/cuda-11.7/lib64/ -lcurand 
+make[1]: Leaving directory `/results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg'
 touch build.512z_f_inl1_hrd0/.cudacpplibs
-ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_f_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias  -lstdc++  -Wl,--no-relax   -fopenmp counters.o -L../../lib//build.512z_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_f_inl1_hrd0'
+ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_f_inl1_hrd0/cmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512z_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cpp -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_f_inl1_hrd0' -lstdc++  -Wl,--no-relax 
+if [ -f ../../lib//build.512z_f_inl1_hrd0/libmg5amc_gg_ttxgg_cuda.* ]; then ccache /cvmfs/sft.cern.ch/lcg/releases/gcc/11.2.0-ad950/x86_64-centos7/bin/gfortran -o build.512z_f_inl1_hrd0/gmadevent_cudacpp myamp.o genps.o unwgt.o setcuts.o get_color.o cuts.o cluster.o reweight.o initcluster.o addmothers.o setscales.o idenparts.o dummy_fct.o driver_cudacpp.o  auto_dsig1_cudacpp.o auto_dsig.o matrix1.o   -L../../lib/ -ldhelas -ldsample -lmodel -lgeneric -lpdf -lcernlib  -lbias   -fopenmp counters.o -L../../lib//build.512z_f_inl1_hrd0 -lmg5amc_common -lmg5amc_gg_ttxgg_cuda -Wl,-rpath,'$ORIGIN/../../../lib//build.512z_f_inl1_hrd0' -lstdc++  -Wl,--no-relax ; fi
 
-DATE: 2022-08-31_21:16:10
+DATE: 2022-09-25_00:42:27
 
-On 7b063fce6d12 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+On 1fca63fac403 [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla T4]:
 =========================================================================
-runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl1_hrd0/check.exe -p 64 256 2 OMP=
+runExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl1_hrd0/check.exe -p 64 256 2 OMP=
 Process                     = SIGMA_SM_GG_TTXGG_CPP [gcc 11.2.0] [inlineHel=1] [hardcodePARAM=0]
 Workflow summary            = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK
 FP precision                = FLOAT (NaN/abnormal=0, zero=0)
 Internal loops fptype_sv    = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES]
-EvtsPerSec[Rmb+ME]     (23) = ( 1.255324e+04                 )  sec^-1
-EvtsPerSec[MatrixElems] (3) = ( 1.262950e+04                 )  sec^-1
-EvtsPerSec[MECalcOnly] (3a) = ( 1.262950e+04                 )  sec^-1
+EvtsPerSec[Rmb+ME]     (23) = ( 1.262326e+04                 )  sec^-1
+EvtsPerSec[MatrixElems] (3) = ( 1.270086e+04                 )  sec^-1
+EvtsPerSec[MECalcOnly] (3a) = ( 1.270086e+04                 )  sec^-1
 MeanMatrixElemValue         = ( 2.517789e+00 +- 1.234526e+00 )  GeV^-4
-TOTAL       :     2.619929 sec
-real	0m2.626s
+TOTAL       :     2.605309 sec
+real	0m2.612s
 =Symbols in CPPProcess.o= (~sse4:    0) (avx2: 4314) (512y:    0) (512z:44524)
 -------------------------------------------------------------------------
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl1_hrd0/check.exe --common -p 2 64 2
-cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1661972119_2568/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl1_hrd0/fcheck.exe 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl1_hrd0/check.exe --common -p 2 64 2
+cmpExe /results/mg5amc-madgraph4gpu-2022-c1-e2-1664055235_2629/proc_1/madgraph4gpu/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl1_hrd0/fcheck.exe 2 64 2
 Avg ME (C++/C++)    = 6.627345e-04
 Avg ME (F77/C++)    = 6.6273453865877546E-004
 Relative difference = 5.8332221286277664e-08
diff --git a/mg5amc/madgraph4gpu-2022/mg5amc-madgraph4gpu-2022/jobs/good_1/version.json b/mg5amc/madgraph4gpu-2022/mg5amc-madgraph4gpu-2022/jobs/good_1/version.json
index 32bbe4bcc2e0ab2de000c74f5ff05d8febf654f9..d591fd2ad5fd439b4761d3b54f1f88fa2a476e6d 100644
--- a/mg5amc/madgraph4gpu-2022/mg5amc-madgraph4gpu-2022/jobs/good_1/version.json
+++ b/mg5amc/madgraph4gpu-2022/mg5amc-madgraph4gpu-2022/jobs/good_1/version.json
@@ -1 +1 @@
-{"version":"ci-v0.6","description":"Madgraph5_aMCatNLO madgraph4gpu benchmark (2022)","cvmfs_checksum":"05f5179a44c0e2051bbb092a63cf0daf","bmkdata_checksum":"4eb8273563af22b829ddbf985ae0b0a9","bmk_checksum":"9b7bedb12e18a214106591542f8b3093"}
+{"version":"ci-v0.7","description":"Madgraph5_aMCatNLO madgraph4gpu benchmark (2022)","cvmfs_checksum":"34ff738c57b9b7a8a398e4769cba101d","bmkdata_checksum":"d4c9152ed732e012ca54b6518bf3de93","bmk_checksum":"3c9f62f161ec52296be50b21648606b0"}
diff --git a/mg5amc/madgraph4gpu-2022/mg5amc-madgraph4gpu-2022/mg5amc-madgraph4gpu-2022-bmk.sh b/mg5amc/madgraph4gpu-2022/mg5amc-madgraph4gpu-2022/mg5amc-madgraph4gpu-2022-bmk.sh
index be59fa5a4bf1257c29560c3b1af3970410978ce6..1417ff3d45b06d9e2dfb8534394f9c3c02d12608 100755
--- a/mg5amc/madgraph4gpu-2022/mg5amc-madgraph4gpu-2022/mg5amc-madgraph4gpu-2022-bmk.sh
+++ b/mg5amc/madgraph4gpu-2022/mg5amc-madgraph4gpu-2022/mg5amc-madgraph4gpu-2022-bmk.sh
@@ -150,10 +150,10 @@ function doOne(){
     # Download madgraph4gpu if not yet done
     # NB: this is executed only in the first CI docker run with network access (BMK-779)
     download=1
-    # Checkout commit: 24 September 2022 within branch hack for PR #532
+    # Checkout commit: 25 September 2022 within branch hack for PR #532
     git clone https://github.com/madgraph5/madgraph4gpu.git ${workDir}/madgraph4gpu
     cd ${workDir}/madgraph4gpu
-    git reset --hard 417392117fa8c47bdaad96ae55de343e808f86fc
+    git reset --hard b40edd298171e08b5f52341d66adf2d9d70f4f5b
     # Implement here any custom changes to upstream madgraph4gpu as this becomes read-only in /bmk later on (BMK-1046)
     cd ${workDir}/madgraph4gpu/epochX/cudacpp/tput
     cp ./throughputX.sh ./throughputX.sh.old # KEEP IT IN THE IMAGE FOR REFERENCE