mirror of
https://github.com/NVIDIA/cuda-samples.git
synced 2025-07-01 20:20:29 +08:00
60 lines
2.1 KiB
CMake
60 lines
2.1 KiB
CMake
cmake_minimum_required(VERSION 3.20)
|
|
|
|
list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_SOURCE_DIR}/../../../cmake/Modules")
|
|
|
|
project(vectorAddDrv LANGUAGES C CXX CUDA)
|
|
|
|
find_package(CUDAToolkit REQUIRED)
|
|
|
|
set(CMAKE_POSITION_INDEPENDENT_CODE ON)
|
|
|
|
set(CMAKE_CUDA_ARCHITECTURES 50 52 60 61 70 72 75 80 86 87 89 90 100 101 120)
|
|
set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -Wno-deprecated-gpu-targets")
|
|
if(ENABLE_CUDA_DEBUG)
|
|
set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -G") # enable cuda-gdb (may significantly affect performance on some targets)
|
|
else()
|
|
set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -lineinfo") # add line information to all builds for debug tools (exclusive to -G option)
|
|
endif()
|
|
|
|
# Include directories and libraries
|
|
include_directories(../../../Common)
|
|
|
|
# Source file
|
|
# Add target for vectorAddDrv
|
|
add_executable(vectorAddDrv vectorAddDrv.cpp)
|
|
|
|
target_compile_options(vectorAddDrv PRIVATE $<$<COMPILE_LANGUAGE:CUDA>:--extended-lambda>)
|
|
|
|
target_compile_features(vectorAddDrv PRIVATE cxx_std_17 cuda_std_17)
|
|
|
|
set_target_properties(vectorAddDrv PROPERTIES CUDA_SEPARABLE_COMPILATION ON)
|
|
target_include_directories(vectorAddDrv PRIVATE
|
|
${CUDAToolkit_INCLUDE_DIRS}
|
|
)
|
|
|
|
target_link_libraries(vectorAddDrv PUBLIC
|
|
CUDA::cuda_driver
|
|
)
|
|
|
|
set(CUDA_FATBIN_FILE "${CMAKE_CURRENT_BINARY_DIR}/vectorAdd_kernel64.fatbin")
|
|
set(CUDA_KERNEL_SOURCE "${CMAKE_CURRENT_SOURCE_DIR}/vectorAdd_kernel.cu")
|
|
|
|
# Construct GENCODE_FLAGS explicitly from CUDA architectures
|
|
set(GENCODE_FLAGS "")
|
|
foreach(arch ${CMAKE_CUDA_ARCHITECTURES})
|
|
list(APPEND GENCODE_FLAGS "-gencode=arch=compute_${arch},code=sm_${arch}")
|
|
endforeach()
|
|
|
|
add_custom_command(
|
|
OUTPUT ${CUDA_FATBIN_FILE}
|
|
COMMAND ${CMAKE_CUDA_COMPILER} ${INCLUDES} ${ALL_CCFLAGS} -Wno-deprecated-gpu-targets ${GENCODE_FLAGS} -o ${CUDA_FATBIN_FILE} -fatbin ${CUDA_KERNEL_SOURCE}
|
|
DEPENDS ${CUDA_KERNEL_SOURCE}
|
|
COMMENT "Building CUDA fatbin: ${CUDA_FATBIN_FILE}"
|
|
)
|
|
|
|
# Create a dummy target for fatbin generation
|
|
add_custom_target(generate_fatbin_vectorAdd ALL DEPENDS ${CUDA_FATBIN_FILE})
|
|
|
|
# Ensure matrixMulDrv depends on the fatbin
|
|
add_dependencies(vectorAddDrv generate_fatbin_vectorAdd)
|