diff options
Diffstat (limited to 'Modules/FindCUDA.cmake')
| -rw-r--r-- | Modules/FindCUDA.cmake | 116 |
1 files changed, 89 insertions, 27 deletions
diff --git a/Modules/FindCUDA.cmake b/Modules/FindCUDA.cmake index a4dca54..04b5cf9 100644 --- a/Modules/FindCUDA.cmake +++ b/Modules/FindCUDA.cmake @@ -2,37 +2,52 @@ # FindCUDA # -------- # +# .. note:: +# +# The FindCUDA module has been superseded by first-class support +# for the CUDA language in CMake. It is no longer necessary to +# use this module or call ``find_package(CUDA)``. This module +# now exists only for compatibility with projects that have not +# been ported. +# +# Instead, list ``CUDA`` among the languages named in the top-level +# call to the :command:`project` command, or call the +# :command:`enable_language` command with ``CUDA``. +# Then one can add CUDA (``.cu``) sources to programs directly +# in calls to :command:`add_library` and :command:`add_executable`. +# # Tools for building CUDA C files: libraries and build dependencies. # -# This script locates the NVIDIA CUDA C tools. It should work on linux, -# windows, and mac and should be reasonably up to date with CUDA C +# This script locates the NVIDIA CUDA C tools. It should work on Linux, +# Windows, and macOS and should be reasonably up to date with CUDA C # releases. # -# This script makes use of the standard find_package arguments of -# <VERSION>, REQUIRED and QUIET. CUDA_FOUND will report if an +# This script makes use of the standard :command:`find_package` arguments of +# ``<VERSION>``, ``REQUIRED`` and ``QUIET``. ``CUDA_FOUND`` will report if an # acceptable version of CUDA was found. # -# The script will prompt the user to specify CUDA_TOOLKIT_ROOT_DIR if +# The script will prompt the user to specify ``CUDA_TOOLKIT_ROOT_DIR`` if # the prefix cannot be determined by the location of nvcc in the system -# path and REQUIRED is specified to find_package(). To use a different -# installed version of the toolkit set the environment variable -# CUDA_BIN_PATH before running cmake (e.g. -# CUDA_BIN_PATH=/usr/local/cuda1.0 instead of the default -# /usr/local/cuda) or set CUDA_TOOLKIT_ROOT_DIR after configuring. If -# you change the value of CUDA_TOOLKIT_ROOT_DIR, various components that +# path and ``REQUIRED`` is specified to :command:`find_package`. To use +# a different installed version of the toolkit set the environment variable +# ``CUDA_BIN_PATH`` before running cmake (e.g. +# ``CUDA_BIN_PATH=/usr/local/cuda1.0`` instead of the default +# ``/usr/local/cuda``) or set ``CUDA_TOOLKIT_ROOT_DIR`` after configuring. If +# you change the value of ``CUDA_TOOLKIT_ROOT_DIR``, various components that # depend on the path will be relocated. # -# It might be necessary to set CUDA_TOOLKIT_ROOT_DIR manually on certain -# platforms, or to use a cuda runtime not installed in the default -# location. In newer versions of the toolkit the cuda library is -# included with the graphics driver- be sure that the driver version -# matches what is needed by the cuda runtime version. +# It might be necessary to set ``CUDA_TOOLKIT_ROOT_DIR`` manually on certain +# platforms, or to use a CUDA runtime not installed in the default +# location. In newer versions of the toolkit the CUDA library is +# included with the graphics driver -- be sure that the driver version +# matches what is needed by the CUDA runtime version. # # The following variables affect the behavior of the macros in the # script (in alphebetical order). Note that any of these flags can be # changed multiple times in the same directory before calling -# CUDA_ADD_EXECUTABLE, CUDA_ADD_LIBRARY, CUDA_COMPILE, CUDA_COMPILE_PTX, -# CUDA_COMPILE_FATBIN, CUDA_COMPILE_CUBIN or CUDA_WRAP_SRCS:: +# ``CUDA_ADD_EXECUTABLE``, ``CUDA_ADD_LIBRARY``, ``CUDA_COMPILE``, +# ``CUDA_COMPILE_PTX``, ``CUDA_COMPILE_FATBIN``, ``CUDA_COMPILE_CUBIN`` +# or ``CUDA_WRAP_SRCS``:: # # CUDA_64_BIT_DEVICE_CODE (Default matches host bit size) # -- Set to ON to compile for 64 bit device code, OFF for 32 bit device code. @@ -325,7 +340,27 @@ # CUDA_nppc_LIBRARY -- NVIDIA Performance Primitives lib (core). # Only available for CUDA version 5.5+. # CUDA_nppi_LIBRARY -- NVIDIA Performance Primitives lib (image processing). -# Only available for CUDA version 5.5+. +# Only available for CUDA version 5.5 - 8.0. +# CUDA_nppial_LIBRARY -- NVIDIA Performance Primitives lib (image processing). +# Only available for CUDA version 9.0. +# CUDA_nppicc_LIBRARY -- NVIDIA Performance Primitives lib (image processing). +# Only available for CUDA version 9.0. +# CUDA_nppicom_LIBRARY -- NVIDIA Performance Primitives lib (image processing). +# Only available for CUDA version 9.0. +# CUDA_nppidei_LIBRARY -- NVIDIA Performance Primitives lib (image processing). +# Only available for CUDA version 9.0. +# CUDA_nppif_LIBRARY -- NVIDIA Performance Primitives lib (image processing). +# Only available for CUDA version 9.0. +# CUDA_nppig_LIBRARY -- NVIDIA Performance Primitives lib (image processing). +# Only available for CUDA version 9.0. +# CUDA_nppim_LIBRARY -- NVIDIA Performance Primitives lib (image processing). +# Only available for CUDA version 9.0. +# CUDA_nppist_LIBRARY -- NVIDIA Performance Primitives lib (image processing). +# Only available for CUDA version 9.0. +# CUDA_nppisu_LIBRARY -- NVIDIA Performance Primitives lib (image processing). +# Only available for CUDA version 9.0. +# CUDA_nppitc_LIBRARY -- NVIDIA Performance Primitives lib (image processing). +# Only available for CUDA version 9.0. # CUDA_npps_LIBRARY -- NVIDIA Performance Primitives lib (signal processing). # Only available for CUDA version 5.5+. # CUDA_nvcuvenc_LIBRARY -- CUDA Video Encoder library. @@ -546,7 +581,7 @@ mark_as_advanced( # Makefile and similar generators don't define CMAKE_CONFIGURATION_TYPES, so we # need to add another entry for the CMAKE_BUILD_TYPE. We also need to add the # standerd set of 4 build types (Debug, MinSizeRel, Release, and RelWithDebInfo) -# for completeness. We need run this loop in order to accomodate the addition +# for completeness. We need run this loop in order to accommodate the addition # of extra configuration types. Duplicate entries will be removed by # REMOVE_DUPLICATES. set(CUDA_configuration_types ${CMAKE_CONFIGURATION_TYPES} ${CMAKE_BUILD_TYPE} Debug MinSizeRel Release RelWithDebInfo) @@ -589,7 +624,6 @@ macro(cuda_unset_include_and_libraries) unset(CUDA_npps_LIBRARY CACHE) unset(CUDA_nvcuvenc_LIBRARY CACHE) unset(CUDA_nvcuvid_LIBRARY CACHE) - unset(CUDA_USE_STATIC_CUDA_RUNTIME CACHE) unset(CUDA_GPU_DETECT_OUTPUT CACHE) endmacro() @@ -632,8 +666,7 @@ if(NOT CUDA_TOOLKIT_ROOT_DIR AND NOT CMAKE_CROSSCOMPILING) find_path(CUDA_TOOLKIT_ROOT_DIR NAMES nvcc nvcc.exe PATHS /opt/cuda/bin - /usr/local/bin - /usr/local/cuda/bin + PATH_SUFFIXES cuda/bin DOC "Toolkit location." ) @@ -679,7 +712,11 @@ if(CMAKE_CROSSCOMPILING) # add known CUDA targetr root path to the set of directories we search for programs, libraries and headers set( CMAKE_FIND_ROOT_PATH "${CUDA_TOOLKIT_TARGET_DIR};${CMAKE_FIND_ROOT_PATH}") macro( cuda_find_host_program ) - find_host_program( ${ARGN} ) + if (COMMAND find_host_program) + find_host_program( ${ARGN} ) + else() + find_program( ${ARGN} ) + endif() endmacro() else() # for non-cross-compile, find_host_program == find_program and CUDA_TOOLKIT_TARGET_DIR == CUDA_TOOLKIT_ROOT_DIR @@ -798,12 +835,17 @@ endif() if(CUDA_cudart_static_LIBRARY) # If static cudart available, use it by default, but provide a user-visible option to disable it. option(CUDA_USE_STATIC_CUDA_RUNTIME "Use the static version of the CUDA runtime library if available" ON) - set(CUDA_CUDART_LIBRARY_VAR CUDA_cudart_static_LIBRARY) else() # If not available, silently disable the option. set(CUDA_USE_STATIC_CUDA_RUNTIME OFF CACHE INTERNAL "") +endif() + +if(CUDA_USE_STATIC_CUDA_RUNTIME) + set(CUDA_CUDART_LIBRARY_VAR CUDA_cudart_static_LIBRARY) +else() set(CUDA_CUDART_LIBRARY_VAR CUDA_CUDART_LIBRARY) endif() + if(NOT CUDA_VERSION VERSION_LESS "5.0") cuda_find_library_local_first(CUDA_cudadevrt_LIBRARY cudadevrt "\"cudadevrt\" library") mark_as_advanced(CUDA_cudadevrt_LIBRARY) @@ -917,6 +959,24 @@ if(NOT CUDA_VERSION VERSION_LESS "3.2") endif() if(CUDA_VERSION VERSION_GREATER "5.0") find_cuda_helper_libs(cublas_device) +endif() + +if(NOT CUDA_VERSION VERSION_LESS "9.0") + # In CUDA 9.0 NPP was nppi was removed + find_cuda_helper_libs(nppc) + find_cuda_helper_libs(nppial) + find_cuda_helper_libs(nppicc) + find_cuda_helper_libs(nppicom) + find_cuda_helper_libs(nppidei) + find_cuda_helper_libs(nppif) + find_cuda_helper_libs(nppig) + find_cuda_helper_libs(nppim) + find_cuda_helper_libs(nppist) + find_cuda_helper_libs(nppisu) + find_cuda_helper_libs(nppitc) + find_cuda_helper_libs(npps) + set(CUDA_npp_LIBRARY "${CUDA_nppc_LIBRARY};${CUDA_nppial_LIBRARY};${CUDA_nppicc_LIBRARY};${CUDA_nppicom_LIBRARY};${CUDA_nppidei_LIBRARY};${CUDA_nppif_LIBRARY};${CUDA_nppig_LIBRARY};${CUDA_nppim_LIBRARY};${CUDA_nppist_LIBRARY};${CUDA_nppisu_LIBRARY};${CUDA_nppitc_LIBRARY};${CUDA_npps_LIBRARY}") +elseif(CUDA_VERSION VERSION_GREATER "5.0") # In CUDA 5.5 NPP was splitted onto 3 separate libraries. find_cuda_helper_libs(nppc) find_cuda_helper_libs(nppi) @@ -1695,9 +1755,10 @@ function(CUDA_LINK_SEPARABLE_COMPILATION_OBJECTS output_file cuda_target options add_custom_command( OUTPUT ${output_file} DEPENDS ${object_files} - COMMAND ${CUDA_NVCC_EXECUTABLE} ${nvcc_flags} -dlink ${object_files} -o ${output_file} + COMMAND ${CUDA_NVCC_EXECUTABLE} ${nvcc_flags} -dlink ${object_files} ${CUDA_cublas_device_LIBRARY} -o ${output_file} ${flags} COMMENT "Building NVCC intermediate link file ${output_file_relative_path}" + COMMAND_EXPAND_LISTS ${_verbatim} ) else() @@ -1707,7 +1768,8 @@ function(CUDA_LINK_SEPARABLE_COMPILATION_OBJECTS output_file cuda_target options PRE_LINK COMMAND ${CMAKE_COMMAND} -E echo "Building NVCC intermediate link file ${output_file_relative_path}" COMMAND ${CMAKE_COMMAND} -E make_directory "${output_file_dir}" - COMMAND ${CUDA_NVCC_EXECUTABLE} ${nvcc_flags} ${flags} -dlink ${object_files} -o "${output_file}" + COMMAND ${CUDA_NVCC_EXECUTABLE} ${nvcc_flags} ${flags} -dlink ${object_files} ${CUDA_cublas_device_LIBRARY} -o "${output_file}" + COMMAND_EXPAND_LISTS ${_verbatim} ) endif() |