Skip to content

pass user defined CUDA_NVCC_FLAGS and HIP_HIPCC_FLAGS #2168

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
wanghan-iapcm merged 1 commit into from
Dec 7, 2022
Merged

pass user defined CUDA_NVCC_FLAGS and HIP_HIPCC_FLAGS #2168

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 7 additions & 0 deletions source/lib/src/cuda/CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,6 +34,7 @@ if (${CUDA_VERSION_MAJOR} GREATER "11" OR (${CUDA_VERSION_MAJOR} STREQUAL "11" A
# nvcc flags
set(CUDA_NVCC_FLAGS -arch=all; # embeds a compiled code image for all supported architectures (sm_*), and a PTX program for the highest major virtual architecture
-O3; -Xcompiler -fPIC;
${CUDA_NVCC_FLAGS}
)
elseif (${CUDA_VERSION_MAJOR} STREQUAL "11" AND ${CUDA_VERSION_MINOR} GREATER "0")
# nvcc flags
Expand All @@ -46,6 +47,7 @@ elseif (${CUDA_VERSION_MAJOR} STREQUAL "11" AND ${CUDA_VERSION_MINOR} GREATER "0
-gencode arch=compute_80,code=sm_80; # Anpere - A100
-gencode arch=compute_86,code=sm_86; # Anpere - RTX 3090
-O3; -Xcompiler -fPIC;
${CUDA_NVCC_FLAGS}
)
elseif (${CUDA_VERSION_MAJOR} STREQUAL "11" AND ${CUDA_VERSION_MINOR} STREQUAL "0")
# nvcc flags
Expand All @@ -57,6 +59,7 @@ elseif (${CUDA_VERSION_MAJOR} STREQUAL "11" AND ${CUDA_VERSION_MINOR} STREQUAL "
-gencode arch=compute_75,code=sm_75; # Turing - RTX 2080, Titan RTX, Quadro R8000
-gencode arch=compute_80,code=sm_80; # Anpere - A100
-O3; -Xcompiler -fPIC;
${CUDA_NVCC_FLAGS}
)
elseif (${CUDA_VERSION_MAJOR} STREQUAL "10")
set(CUDA_NVCC_FLAGS -gencode arch=compute_30,code=sm_30; # Tesla K10, Quadro K600 K420 K410,
Expand All @@ -70,6 +73,7 @@ elseif (${CUDA_VERSION_MAJOR} STREQUAL "10")
-gencode arch=compute_70,code=sm_70; # Volta - GV100/Tesla V100, GTX 1180 (GV104)
-gencode arch=compute_75,code=sm_75; # Turing - RTX 2080, Titan RTX, Quadro R8000
-O3; -Xcompiler -fPIC;
${CUDA_NVCC_FLAGS}
)
elseif (${CUDA_VERSION_MAJOR} STREQUAL "9")
set(CUDA_NVCC_FLAGS -gencode arch=compute_30,code=sm_30;
Expand All @@ -82,6 +86,7 @@ elseif (${CUDA_VERSION_MAJOR} STREQUAL "9")
-gencode arch=compute_61,code=sm_61; # Pascal - GTX 1080, GTX 1070, GTX 1060, GTX 1050, GTX 1030, Titan Xp, Tesla P40, Tesla P4, Discrete GPU on the NVIDIA Drive PX2
-gencode arch=compute_70,code=sm_70; # Volta - GV100/Tesla V100, GTX 1180 (GV104)
-O3; -Xcompiler -fPIC;
${CUDA_NVCC_FLAGS}
)
elseif (${CUDA_VERSION_MAJOR} STREQUAL "8")
set(CUDA_NVCC_FLAGS -gencode arch=compute_30,code=sm_30;
Expand All @@ -93,6 +98,7 @@ elseif (${CUDA_VERSION_MAJOR} STREQUAL "8")
-gencode arch=compute_60,code=sm_60; # Pascal – GP100/Tesla P100 – DGX-1 (Generic Pascal)
-gencode arch=compute_61,code=sm_61; # Pascal - GTX 1080, GTX 1070, GTX 1060, GTX 1050, GTX 1030, Titan Xp, Tesla P40, Tesla P4, Discrete GPU on the NVIDIA Drive PX2
-O3; -Xcompiler -fPIC;
${CUDA_NVCC_FLAGS}
)
elseif (${CUDA_VERSION_MAJOR} STREQUAL "7")
set(CUDA_NVCC_FLAGS -gencode arch=compute_30,code=sm_30;
Expand All @@ -102,6 +108,7 @@ elseif (${CUDA_VERSION_MAJOR} STREQUAL "7")
-gencode arch=compute_52,code=sm_52; # Tesla M40, Tesla M40, Quadro M6000...
-gencode arch=compute_53,code=sm_53;
-O3; -Xcompiler -fPIC;
${CUDA_NVCC_FLAGS}
)
else ()
message(FATAL_ERROR "unsupported CUDA_VERSION " ${CUDA_VERSION} ", please use a newer version (>=7.0) of CUDA toolkit!")
Expand Down
2 changes: 1 addition & 1 deletion source/lib/src/rocm/CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@ add_definitions("-DCUB_IGNORE_DEPRECATED_CPP_DIALECT")

message(STATUS "HIP major version is " ${HIP_VERSION_MAJOR})

set (HIP_HIPCC_FLAGS -fno-gpu-rdc; -fPIC --std=c++14) # --amdgpu-target=gfx906
set (HIP_HIPCC_FLAGS -fno-gpu-rdc; -fPIC --std=c++14 ${HIP_HIPCC_FLAGS}) # --amdgpu-target=gfx906
if (HIP_VERSION VERSION_LESS 3.5.1)
set (HIP_HIPCC_FLAGS -hc; ${HIP_HIPCC_FLAGS})
endif()
Expand Down