diff options
| author | Brad King <brad.king@kitware.com> | 2022-03-04 18:51:49 (GMT) |
|---|---|---|
| committer | Brad King <brad.king@kitware.com> | 2022-03-10 14:27:29 (GMT) |
| commit | d1b48bfabd6157309b3056967e6e30cc0ce07983 (patch) | |
| tree | 3ce109b078bf5da4d866f6e2994bbce8246e4df1 /Modules/CUDA | |
| parent | 632752d62e8de2730796f509dbb10551351309c2 (diff) | |
| download | CMake-d1b48bfabd6157309b3056967e6e30cc0ce07983.zip CMake-d1b48bfabd6157309b3056967e6e30cc0ce07983.tar.gz CMake-d1b48bfabd6157309b3056967e6e30cc0ce07983.tar.bz2 | |
CUDA: Add support for CUDA_ARCHITECTURES=native
CUDA 11.6 added the `nvcc -arch=native` flag to automatically compile
for the host GPUs' architectures. Add support for specifying this
special `native` value in `CMAKE_CUDA_ARCHITECTURES` and
`CUDA_ARCHITECTURES`. During the compiler ABI detection step,
detect the native architectures so we can pass them explicitly
when using Clang or older versions of nvcc.
Fixes: #22375
Diffstat (limited to 'Modules/CUDA')
| -rw-r--r-- | Modules/CUDA/architectures.cmake | 40 |
1 files changed, 40 insertions, 0 deletions
diff --git a/Modules/CUDA/architectures.cmake b/Modules/CUDA/architectures.cmake index fa3a5a1..521243b 100644 --- a/Modules/CUDA/architectures.cmake +++ b/Modules/CUDA/architectures.cmake @@ -44,3 +44,43 @@ if(CMAKE_CUDA_COMPILER_TOOLKIT_VERSION VERSION_GREATER_EQUAL 11.4 AND (NOT CMAKE_CUDA_COMPILER_ID STREQUAL "Clang")) list(APPEND CMAKE_CUDA_ARCHITECTURES_ALL 87) endif() + +# FIXME(#23161): Detect architectures early since we test them during +# compiler detection. We already have code to detect them later during +# compiler testing, so we should not need to do this here. +if(NOT CMAKE_GENERATOR MATCHES "Visual Studio") + set(_CUDA_ARCHS_EXE "${CMAKE_PLATFORM_INFO_DIR}/CMakeDetermineCUDACompilerArchs.bin") + execute_process( + COMMAND "${_CUDA_NVCC_EXECUTABLE}" -o "${_CUDA_ARCHS_EXE}" --cudart=static "${CMAKE_ROOT}/Modules/CMakeCUDACompilerABI.cu" + RESULT_VARIABLE _CUDA_ARCHS_RESULT + OUTPUT_VARIABLE _CUDA_ARCHS_OUTPUT + ERROR_VARIABLE _CUDA_ARCHS_OUTPUT + ) + if(_CUDA_ARCHS_RESULT EQUAL 0) + execute_process( + COMMAND "${_CUDA_ARCHS_EXE}" + RESULT_VARIABLE _CUDA_ARCHS_RESULT + OUTPUT_VARIABLE _CUDA_ARCHS_OUTPUT + ERROR_VARIABLE _CUDA_ARCHS_OUTPUT + OUTPUT_STRIP_TRAILING_WHITESPACE + ) + endif() + if(_CUDA_ARCHS_RESULT EQUAL 0) + set(_CUDA_ARCHITECTURES_NATIVE "${_CUDA_ARCHS_OUTPUT}") + list(REMOVE_DUPLICATES _CUDA_ARCHITECTURES_NATIVE) + else() + if (NOT _CUDA_ARCHS_RESULT MATCHES "[0-9]+") + set(_CUDA_ARCHS_STATUS " (${_CUDA_ARCHS_RESULT})") + else() + set(_CUDA_ARCHS_STATUS "") + endif() + string(REPLACE "\n" "\n " _CUDA_ARCHS_OUTPUT " ${_CUDA_ARCHS_OUTPUT}") + file(APPEND ${CMAKE_BINARY_DIR}${CMAKE_FILES_DIRECTORY}/CMakeError.log + "Detecting the CUDA native architecture(s) failed with " + "the following output:\n${_CUDA_ARCHS_OUTPUT}\n\n") + set(_CUDA_ARCHS_OUTPUT "") + endif() + unset(_CUDA_ARCHS_EXE) + unset(_CUDA_ARCHS_RESULT) + unset(_CUDA_ARCHS_OUTPUT) +endif() |