Disabled the project-wide maxrregcount flag by default since it is only beneficial for resource-heavy kernels. The maximum register count should be defined per kernel instead if needed.

2019-07-22 12:58:28 +03:00
parent a8caad1ade
commit 0db61dd411
1 changed files with 0 additions and 1 deletions
--- a/src/core/CMakeLists.txt
+++ b/src/core/CMakeLists.txt
@@ -19,7 +19,6 @@ set(CUDA_ARCH_FLAGS -gencode arch=compute_37,code=sm_37
                    -gencode arch=compute_60,code=sm_60
                    -gencode arch=compute_61,code=sm_61
                    -lineinfo
-                    --maxrregcount=255
                    -ftz=true
                    -std=c++11) #--maxrregcount=255 -ftz=true #ftz = flush denormalized floats to zero
 # -Xptxas -dlcm=ca opt-in to cache all global loads to L1/texture cache