mirror of
https://gitlab.com/libeigen/eigen.git
synced 2026-04-10 11:34:33 +08:00
Update cmake configuration from master
This commit is contained in:
C. Antonio Sanchez
@@ -112,84 +112,9 @@ ei_add_test(special_packetmath "-DEIGEN_FAST_MATH=1")
|
||||
if(EIGEN_TEST_CXX11)
|
||||
if(EIGEN_TEST_SYCL)
|
||||
set(EIGEN_SYCL ON)
|
||||
# Forward CMake options as preprocessor definitions
|
||||
if(EIGEN_SYCL_USE_DEFAULT_SELECTOR)
|
||||
add_definitions(-DEIGEN_SYCL_USE_DEFAULT_SELECTOR=${EIGEN_SYCL_USE_DEFAULT_SELECTOR})
|
||||
endif()
|
||||
if(EIGEN_SYCL_NO_LOCAL_MEM)
|
||||
add_definitions(-DEIGEN_SYCL_NO_LOCAL_MEM=${EIGEN_SYCL_NO_LOCAL_MEM})
|
||||
endif()
|
||||
if(EIGEN_SYCL_LOCAL_MEM)
|
||||
add_definitions(-DEIGEN_SYCL_LOCAL_MEM=${EIGEN_SYCL_LOCAL_MEM})
|
||||
endif()
|
||||
if(EIGEN_SYCL_MAX_GLOBAL_RANGE)
|
||||
add_definitions(-DEIGEN_SYCL_MAX_GLOBAL_RANGE=${EIGEN_SYCL_MAX_GLOBAL_RANGE})
|
||||
endif()
|
||||
if(EIGEN_SYCL_LOCAL_THREAD_DIM0)
|
||||
add_definitions(-DEIGEN_SYCL_LOCAL_THREAD_DIM0=${EIGEN_SYCL_LOCAL_THREAD_DIM0})
|
||||
endif()
|
||||
if(EIGEN_SYCL_LOCAL_THREAD_DIM1)
|
||||
add_definitions(-DEIGEN_SYCL_LOCAL_THREAD_DIM1=${EIGEN_SYCL_LOCAL_THREAD_DIM1})
|
||||
endif()
|
||||
if(EIGEN_SYCL_REG_M)
|
||||
add_definitions(-DEIGEN_SYCL_REG_M=${EIGEN_SYCL_REG_M})
|
||||
endif()
|
||||
if(EIGEN_SYCL_REG_N)
|
||||
add_definitions(-DEIGEN_SYCL_REG_N=${EIGEN_SYCL_REG_N})
|
||||
endif()
|
||||
if(EIGEN_SYCL_USE_PROGRAM_CLASS)
|
||||
add_definitions(-DEIGEN_SYCL_USE_PROGRAM_CLASS=${EIGEN_SYCL_USE_PROGRAM_CLASS})
|
||||
endif()
|
||||
if(EIGEN_SYCL_ASYNC_EXECUTION)
|
||||
add_definitions(-DEIGEN_SYCL_ASYNC_EXECUTION=${EIGEN_SYCL_ASYNC_EXECUTION})
|
||||
endif()
|
||||
if(EIGEN_SYCL_DISABLE_SKINNY)
|
||||
add_definitions(-DEIGEN_SYCL_DISABLE_SKINNY=${EIGEN_SYCL_DISABLE_SKINNY})
|
||||
endif()
|
||||
if(EIGEN_SYCL_DISABLE_DOUBLE_BUFFER)
|
||||
add_definitions(-DEIGEN_SYCL_DISABLE_DOUBLE_BUFFER=${EIGEN_SYCL_DISABLE_DOUBLE_BUFFER})
|
||||
endif()
|
||||
if(EIGEN_SYCL_DISABLE_RANK1)
|
||||
add_definitions(-DEIGEN_SYCL_DISABLE_RANK1=${EIGEN_SYCL_DISABLE_RANK1})
|
||||
endif()
|
||||
if(EIGEN_SYCL_DISABLE_SCALAR)
|
||||
add_definitions(-DEIGEN_SYCL_DISABLE_SCALAR=${EIGEN_SYCL_DISABLE_SCALAR})
|
||||
endif()
|
||||
if(EIGEN_SYCL_DISABLE_GEMV)
|
||||
add_definitions(-DEIGEN_SYCL_DISABLE_GEMV=${EIGEN_SYCL_DISABLE_GEMV})
|
||||
endif()
|
||||
if(EIGEN_SYCL_DISABLE_ARM_GPU_CACHE_OPTIMISATION)
|
||||
add_definitions(-DEIGEN_SYCL_DISABLE_ARM_GPU_CACHE_OPTIMISATION=${EIGEN_SYCL_DISABLE_ARM_GPU_CACHE_OPTIMISATION})
|
||||
endif()
|
||||
|
||||
if(EIGEN_SYCL_TRISYCL)
|
||||
# triSYCL now requires c++17.
|
||||
set(CMAKE_CXX_STANDARD 17)
|
||||
else()
|
||||
if(MSVC)
|
||||
# Set the host and device compilers C++ standard to C++14. On Windows setting this to C++11
|
||||
# can cause issues with the ComputeCpp device compiler parsing Visual Studio Headers.
|
||||
set(CMAKE_CXX_STANDARD 14)
|
||||
list(APPEND COMPUTECPP_USER_FLAGS -DWIN32)
|
||||
else()
|
||||
set(CMAKE_CXX_STANDARD 11)
|
||||
list(APPEND COMPUTECPP_USER_FLAGS -Wall)
|
||||
endif()
|
||||
# The following flags are not supported by Clang and can cause warnings
|
||||
# if used with -Werror so they are removed here.
|
||||
if(COMPUTECPP_USE_COMPILER_DRIVER)
|
||||
set(CMAKE_CXX_COMPILER ${ComputeCpp_DEVICE_COMPILER_EXECUTABLE})
|
||||
string(REPLACE "-Wlogical-op" "" CMAKE_CXX_FLAGS ${CMAKE_CXX_FLAGS})
|
||||
string(REPLACE "-Wno-psabi" "" CMAKE_CXX_FLAGS ${CMAKE_CXX_FLAGS})
|
||||
string(REPLACE "-ansi" "" CMAKE_CXX_FLAGS ${CMAKE_CXX_FLAGS})
|
||||
endif()
|
||||
list(APPEND COMPUTECPP_USER_FLAGS
|
||||
-DEIGEN_NO_ASSERTION_CHECKING=1
|
||||
-no-serial-memop
|
||||
-Xclang
|
||||
-cl-mad-enable)
|
||||
endif()
|
||||
include(SyclConfigureTesting)
|
||||
|
||||
|
||||
ei_add_test(cxx11_tensor_sycl ${STD_CXX_FLAG})
|
||||
ei_add_test(cxx11_tensor_image_op_sycl ${STD_CXX_FLAG})
|
||||
ei_add_test(cxx11_tensor_math_sycl ${STD_CXX_FLAG})
|
||||
@@ -281,11 +206,11 @@ if(EIGEN_TEST_CXX11)
|
||||
ei_add_test(cxx11_tensor_thread_pool "-pthread" "${CMAKE_THREAD_LIBS_INIT}")
|
||||
ei_add_test(cxx11_tensor_trace)
|
||||
ei_add_test(cxx11_tensor_volume_patch)
|
||||
# ei_add_test(cxx11_tensor_symmetry)
|
||||
if("${CMAKE_SIZEOF_VOID_P}" EQUAL "8" AND NOT CMAKE_CXX_COMPILER_ID STREQUAL "MSVC")
|
||||
# This test requires __uint128_t which is only available on 64bit systems
|
||||
ei_add_test(cxx11_tensor_uint128)
|
||||
endif()
|
||||
# ei_add_test(cxx11_tensor_symmetry)
|
||||
if("${CMAKE_SIZEOF_VOID_P}" EQUAL "8" AND NOT CMAKE_CXX_COMPILER_ID STREQUAL "MSVC")
|
||||
# This test requires __uint128_t which is only available on 64bit systems
|
||||
ei_add_test(cxx11_tensor_uint128)
|
||||
endif()
|
||||
|
||||
endif()
|
||||
|
||||
@@ -311,6 +236,16 @@ if(CUDA_FOUND AND EIGEN_TEST_CUDA)
|
||||
else()
|
||||
set(CUDA_PROPAGATE_HOST_FLAGS OFF)
|
||||
set(NVCC_ARCH_FLAGS)
|
||||
# Define an -arch=sm_<arch>, otherwise if GPU does not exactly match one of
|
||||
# those in the arch list for -gencode, the kernels will fail to run with
|
||||
# cudaErrorNoKernelImageForDevice
|
||||
# This can happen with newer cards (e.g. sm_75) and compiling with older
|
||||
# versions of nvcc (e.g. 9.2) that do not support their specific arch.
|
||||
list(LENGTH EIGEN_CUDA_COMPUTE_ARCH EIGEN_CUDA_COMPUTE_ARCH_SIZE)
|
||||
if(EIGEN_CUDA_COMPUTE_ARCH_SIZE)
|
||||
list(GET EIGEN_CUDA_COMPUTE_ARCH 0 EIGEN_CUDA_COMPUTE_DEFAULT)
|
||||
set(NVCC_ARCH_FLAGS " -arch=sm_${EIGEN_CUDA_COMPUTE_DEFAULT}")
|
||||
endif()
|
||||
foreach(ARCH IN LISTS EIGEN_CUDA_COMPUTE_ARCH)
|
||||
string(APPEND NVCC_ARCH_FLAGS " -gencode arch=compute_${ARCH},code=sm_${ARCH}")
|
||||
endforeach()
|
||||
@@ -347,63 +282,57 @@ if(CUDA_FOUND AND EIGEN_TEST_CUDA)
|
||||
ei_add_test(cxx11_tensor_random_gpu)
|
||||
endif()
|
||||
|
||||
|
||||
unset(EIGEN_ADD_TEST_FILENAME_EXTENSION)
|
||||
endif()
|
||||
|
||||
# Add HIP specific tests
|
||||
if (EIGEN_TEST_HIP)
|
||||
|
||||
set(HIP_PATH "/opt/rocm/hip" CACHE STRING "Path to the HIP installation.")
|
||||
|
||||
if (EXISTS ${HIP_PATH})
|
||||
set(ROCM_PATH "/opt/rocm" CACHE STRING "Path to the ROCm installation.")
|
||||
|
||||
if (EXISTS ${ROCM_PATH}/hip)
|
||||
set(HIP_PATH ${ROCM_PATH}/hip)
|
||||
list(APPEND CMAKE_MODULE_PATH ${HIP_PATH}/cmake)
|
||||
|
||||
find_package(HIP REQUIRED)
|
||||
if (HIP_FOUND)
|
||||
|
||||
execute_process(COMMAND ${HIP_PATH}/bin/hipconfig --platform OUTPUT_VARIABLE HIP_PLATFORM)
|
||||
|
||||
if ((${HIP_PLATFORM} STREQUAL "hcc") OR (${HIP_PLATFORM} STREQUAL "amd"))
|
||||
|
||||
include_directories(${CMAKE_CURRENT_BINARY_DIR})
|
||||
include_directories(${HIP_PATH}/include)
|
||||
|
||||
set(EIGEN_ADD_TEST_FILENAME_EXTENSION "cu")
|
||||
#
|
||||
# complex datatype is not yet supported by HIP
|
||||
# so leaving out those tests for now
|
||||
#
|
||||
# ei_add_test(cxx11_tensor_complex_gpu)
|
||||
# ei_add_test(cxx11_tensor_complex_cwise_ops_gpu)
|
||||
#
|
||||
ei_add_test(cxx11_tensor_reduction_gpu)
|
||||
ei_add_test(cxx11_tensor_argmax_gpu)
|
||||
ei_add_test(cxx11_tensor_cast_float16_gpu)
|
||||
ei_add_test(cxx11_tensor_scan_gpu)
|
||||
ei_add_test(cxx11_tensor_device)
|
||||
|
||||
ei_add_test(cxx11_tensor_gpu)
|
||||
ei_add_test(cxx11_tensor_contract_gpu)
|
||||
ei_add_test(cxx11_tensor_of_float16_gpu)
|
||||
ei_add_test(cxx11_tensor_random_gpu)
|
||||
|
||||
unset(EIGEN_ADD_TEST_FILENAME_EXTENSION)
|
||||
|
||||
elseif ((${HIP_PLATFORM} STREQUAL "nvcc") OR (${HIP_PLATFORM} STREQUAL "nvidia"))
|
||||
message(FATAL_ERROR "HIP_PLATFORM = nvcc is not supported within Eigen")
|
||||
else ()
|
||||
message(FATAL_ERROR "Unknown HIP_PLATFORM = ${HIP_PLATFORM}")
|
||||
endif()
|
||||
|
||||
endif()
|
||||
|
||||
elseif (EXISTS ${ROCM_PATH}/lib/cmake/hip)
|
||||
set(HIP_PATH ${ROCM_PATH})
|
||||
list(APPEND CMAKE_MODULE_PATH ${HIP_PATH}/lib/cmake/hip)
|
||||
else ()
|
||||
|
||||
message(FATAL_ERROR "EIGEN_TEST_HIP is ON, but the specified HIP_PATH (${HIP_PATH}) does not exist")
|
||||
|
||||
message(FATAL_ERROR "EIGEN_TEST_HIP is ON, but could not find the ROCm installation under ${ROCM_PATH}")
|
||||
endif()
|
||||
|
||||
endif()
|
||||
find_package(HIP REQUIRED)
|
||||
if (HIP_FOUND)
|
||||
execute_process(COMMAND ${HIP_PATH}/bin/hipconfig --platform OUTPUT_VARIABLE HIP_PLATFORM)
|
||||
|
||||
if ((${HIP_PLATFORM} STREQUAL "hcc") OR (${HIP_PLATFORM} STREQUAL "amd"))
|
||||
include_directories(${CMAKE_CURRENT_BINARY_DIR})
|
||||
include_directories(${HIP_PATH}/include)
|
||||
|
||||
set(EIGEN_ADD_TEST_FILENAME_EXTENSION "cu")
|
||||
#
|
||||
# complex datatype is not yet supported by HIP
|
||||
# so leaving out those tests for now
|
||||
#
|
||||
# ei_add_test(cxx11_tensor_complex_gpu)
|
||||
# ei_add_test(cxx11_tensor_complex_cwise_ops_gpu)
|
||||
#
|
||||
ei_add_test(cxx11_tensor_reduction_gpu)
|
||||
ei_add_test(cxx11_tensor_argmax_gpu)
|
||||
ei_add_test(cxx11_tensor_cast_float16_gpu)
|
||||
ei_add_test(cxx11_tensor_scan_gpu)
|
||||
ei_add_test(cxx11_tensor_device)
|
||||
|
||||
ei_add_test(cxx11_tensor_gpu)
|
||||
ei_add_test(cxx11_tensor_contract_gpu)
|
||||
ei_add_test(cxx11_tensor_of_float16_gpu)
|
||||
ei_add_test(cxx11_tensor_random_gpu)
|
||||
|
||||
unset(EIGEN_ADD_TEST_FILENAME_EXTENSION)
|
||||
|
||||
elseif ((${HIP_PLATFORM} STREQUAL "nvcc") OR (${HIP_PLATFORM} STREQUAL "nvidia"))
|
||||
message(FATAL_ERROR "HIP_PLATFORM = nvcc is not supported within Eigen")
|
||||
else ()
|
||||
message(FATAL_ERROR "Unknown HIP_PLATFORM = ${HIP_PLATFORM}")
|
||||
endif()
|
||||
endif()
|
||||
endif()
|
||||
|
||||
Reference in New Issue
Block a user