Verified Commit 8b7d0d05 authored by Guilherme Amadio's avatar Guilherme Amadio
Browse files

Use virtual architecture to setup default CUDA_ARCH

This allows to set CUDA_NVCC_FLAGS containing something like
-code=sm_75 to compile not to PTX, but to binary code for a
particular GPU architecture. This is useful to avoid large
startup times due to the CUDA runtime compiling the PTX just
in time later.
parent e295ae2c
......@@ -133,7 +133,7 @@ if(CUDA)
set(CUDA_ARCH 30 CACHE STRING "CUDA device architecture.")
set(CUDA_ARCH "-arch=sm_${CUDA_ARCH}")
set(CUDA_ARCH "-arch=compute_${CUDA_ARCH}")
Supports Markdown
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment