cmake_minimum_required(VERSION 3.14)
# Check support for CUDA/HIP in Cmake
project(composable_kernel)
list(APPEND CMAKE_MODULE_PATH "${PROJECT_SOURCE_DIR}/cmake")
enable_testing()
find_package(ROCM REQUIRED PATHS /opt/rocm)
include(ROCMInstallTargets)
include(ROCMPackageConfigHelpers)
include(ROCMSetupVersion)
include(ROCMInstallSymlinks)
include(ROCMCreatePackage)
include(CheckCXXCompilerFlag)
rocm_setup_version(VERSION 1.0.0)
include(TargetFlags)
list(APPEND CMAKE_PREFIX_PATH ${CMAKE_INSTALL_PREFIX} ${CMAKE_INSTALL_PREFIX}/llvm ${CMAKE_INSTALL_PREFIX}/hip /opt/rocm /opt/rocm/llvm /opt/rocm/hip)
## C++
enable_language(CXX)
set(CMAKE_CXX_STANDARD 17)
set(CMAKE_CXX_STANDARD_REQUIRED ON)
set(CMAKE_CXX_EXTENSIONS OFF)
message("CMAKE_CXX_COMPILER_ID: ${CMAKE_CXX_COMPILER_ID}")
## OpenMP
if(CMAKE_CXX_COMPILER_ID MATCHES "Clang")
# workaround issue hipcc in rocm3.5 cannot find openmp
set(OpenMP_CXX "${CMAKE_CXX_COMPILER}")
set(OpenMP_CXX_FLAGS "-fopenmp=libomp -Wno-unused-command-line-argument")
set(OpenMP_CXX_LIB_NAMES "libomp" "libgomp" "libiomp5")
set(OpenMP_libomp_LIBRARY ${OpenMP_CXX_LIB_NAMES})
set(OpenMP_libgomp_LIBRARY ${OpenMP_CXX_LIB_NAMES})
set(OpenMP_libiomp5_LIBRARY ${OpenMP_CXX_LIB_NAMES})
else()
find_package(OpenMP REQUIRED)
endif()
message("OpenMP_CXX_LIB_NAMES: ${OpenMP_CXX_LIB_NAMES}")
message("OpenMP_gomp_LIBRARY: ${OpenMP_gomp_LIBRARY}")
message("OpenMP_pthread_LIBRARY: ${OpenMP_pthread_LIBRARY}")
message("OpenMP_CXX_FLAGS: ${OpenMP_CXX_FLAGS}")
link_libraries(${OpenMP_gomp_LIBRARY})
link_libraries(${OpenMP_pthread_LIBRARY})
## HIP
find_package(HIP REQUIRED)
# Override HIP version in config.h, if necessary.
# The variables set by find_package() can't be overwritten,
# therefore let's use intermediate variables.
set(CK_HIP_VERSION_MAJOR "${HIP_VERSION_MAJOR}")
set(CK_HIP_VERSION_MINOR "${HIP_VERSION_MINOR}")
set(CK_HIP_VERSION_PATCH "${HIP_VERSION_PATCH}")
if( DEFINED CK_OVERRIDE_HIP_VERSION_MAJOR )
set(CK_HIP_VERSION_MAJOR "${CK_OVERRIDE_HIP_VERSION_MAJOR}")
message(STATUS "CK_HIP_VERSION_MAJOR overriden with ${CK_OVERRIDE_HIP_VERSION_MAJOR}")
endif()
if( DEFINED CK_OVERRIDE_HIP_VERSION_MINOR )
set(CK_HIP_VERSION_MINOR "${CK_OVERRIDE_HIP_VERSION_MINOR}")
message(STATUS "CK_HIP_VERSION_MINOR overriden with ${CK_OVERRIDE_HIP_VERSION_MINOR}")
endif()
if( DEFINED CK_OVERRIDE_HIP_VERSION_PATCH )
set(CK_HIP_VERSION_PATCH "${CK_OVERRIDE_HIP_VERSION_PATCH}")
message(STATUS "CK_HIP_VERSION_PATCH overriden with ${CK_OVERRIDE_HIP_VERSION_PATCH}")
endif()
message(STATUS "Build with HIP ${HIP_VERSION}")
rocm_create_package(
NAME composablekernel
DESCRIPTION "High Performance Composable Kernel for AMD GPUs"
MAINTAINER "MIOpen Kernels Dev Team
"
LDCONFIG
)
## half
set(HALF_INCLUDE_DIR "${PROJECT_SOURCE_DIR}/external/include/half")
message("HALF_INCLUDE_DIR: ${HALF_INCLUDE_DIR}")
## tidy
include(EnableCompilerWarnings)
set(CK_TIDY_ERRORS ERRORS * -readability-inconsistent-declaration-parameter-name)
if(CMAKE_CXX_COMPILER MATCHES ".*hcc" OR CMAKE_CXX_COMPILER MATCHES ".*clang\\+\\+")
set(CK_TIDY_CHECKS -modernize-use-override -readability-non-const-parameter)
# Enable tidy on hip
elseif(CK_BACKEND STREQUAL "HIP" OR CK_BACKEND STREQUAL "HIPNOGPU")
set(CK_TIDY_ERRORS ALL)
endif()
include(ClangTidy)
enable_clang_tidy(
CHECKS
*
-abseil-*
-android-cloexec-fopen
# Yea we shouldn't be using rand()
-cert-msc30-c
-bugprone-exception-escape
-bugprone-macro-parentheses
-cert-env33-c
-cert-msc32-c
-cert-msc50-cpp
-cert-msc51-cpp
-cert-dcl37-c
-cert-dcl51-cpp
-clang-analyzer-alpha.core.CastToStruct
-clang-analyzer-optin.performance.Padding
-clang-diagnostic-deprecated-declarations
-clang-diagnostic-extern-c-compat
-clang-diagnostic-unused-command-line-argument
-cppcoreguidelines-avoid-c-arrays
-cppcoreguidelines-avoid-magic-numbers
-cppcoreguidelines-explicit-virtual-functions
-cppcoreguidelines-init-variables
-cppcoreguidelines-macro-usage
-cppcoreguidelines-non-private-member-variables-in-classes
-cppcoreguidelines-pro-bounds-array-to-pointer-decay
-cppcoreguidelines-pro-bounds-constant-array-index
-cppcoreguidelines-pro-bounds-pointer-arithmetic
-cppcoreguidelines-pro-type-member-init
-cppcoreguidelines-pro-type-reinterpret-cast
-cppcoreguidelines-pro-type-union-access
-cppcoreguidelines-pro-type-vararg
-cppcoreguidelines-special-member-functions
-fuchsia-*
-google-explicit-constructor
-google-readability-braces-around-statements
-google-readability-todo
-google-runtime-int
-google-runtime-references
-hicpp-vararg
-hicpp-braces-around-statements
-hicpp-explicit-conversions
-hicpp-named-parameter
-hicpp-no-array-decay
# We really shouldn't use bitwise operators with signed integers, but
# opencl leaves us no choice
-hicpp-avoid-c-arrays
-hicpp-signed-bitwise
-hicpp-special-member-functions
-hicpp-uppercase-literal-suffix
-hicpp-use-auto
-hicpp-use-equals-default
-hicpp-use-override
-llvm-header-guard
-llvm-include-order
#-llvmlibc-*
-llvmlibc-restrict-system-libc-headers
-llvmlibc-callee-namespace
-llvmlibc-implementation-in-namespace
-llvm-else-after-return
-llvm-qualified-auto
-misc-misplaced-const
-misc-non-private-member-variables-in-classes
-misc-no-recursion
-modernize-avoid-bind
-modernize-avoid-c-arrays
-modernize-pass-by-value
-modernize-use-auto
-modernize-use-default-member-init
-modernize-use-equals-default
-modernize-use-trailing-return-type
-modernize-use-transparent-functors
-performance-unnecessary-value-param
-readability-braces-around-statements
-readability-else-after-return
# we are not ready to use it, but very useful
-readability-function-cognitive-complexity
-readability-isolate-declaration
-readability-magic-numbers
-readability-named-parameter
-readability-uppercase-literal-suffix
-readability-convert-member-functions-to-static
-readability-qualified-auto
-readability-redundant-string-init
# too many narrowing conversions in our code
-bugprone-narrowing-conversions
-cppcoreguidelines-narrowing-conversions
-altera-struct-pack-align
-cppcoreguidelines-prefer-member-initializer
${CK_TIDY_CHECKS}
${CK_TIDY_ERRORS}
HEADER_FILTER
"\.hpp$"
EXTRA_ARGS
-DCK_USE_CLANG_TIDY
)
include(CppCheck)
enable_cppcheck(
CHECKS
warning
style
performance
portability
SUPPRESS
ConfigurationNotChecked
constStatement
duplicateCondition
noExplicitConstructor
passedByValue
preprocessorErrorDirective
shadowVariable
unusedFunction
unusedPrivateFunction
unusedStructMember
unmatchedSuppression
FORCE
SOURCES
library/src
INCLUDE
${CMAKE_CURRENT_SOURCE_DIR}/include
${CMAKE_CURRENT_BINARY_DIR}/include
${CMAKE_CURRENT_SOURCE_DIR}/library/include
DEFINE
CPPCHECK=1
__linux__=1
)
set(CMAKE_LIBRARY_OUTPUT_DIRECTORY ${CMAKE_CURRENT_BINARY_DIR}/lib)
set(CMAKE_ARCHIVE_OUTPUT_DIRECTORY ${CMAKE_CURRENT_BINARY_DIR}/lib)
set(CMAKE_RUNTIME_OUTPUT_DIRECTORY ${CMAKE_CURRENT_BINARY_DIR}/bin)
include_directories(BEFORE
${PROJECT_SOURCE_DIR}/include
${PROJECT_BINARY_DIR}/include
${PROJECT_SOURCE_DIR}/library/include
)
SET(BUILD_DEV ON CACHE BOOL "BUILD_DEV")
if(BUILD_DEV)
add_compile_options(-Werror)
add_compile_options(-Weverything)
endif()
message("CMAKE_CXX_FLAGS: ${CMAKE_CXX_FLAGS}")
add_custom_target(check COMMAND ${CMAKE_CTEST_COMMAND} --output-on-failure -C ${CMAKE_CFG_INTDIR})
add_subdirectory(library)
add_subdirectory(example)
add_subdirectory(test)
add_subdirectory(profiler)
#Create an interface target for the include only files and call it "composablekernels"
include(CMakePackageConfigHelpers)
set(version 1.0.0)
write_basic_package_version_file(
"${CMAKE_CURRENT_BINARY_DIR}/composable_kernelConfigVersion.cmake"
VERSION "${version}"
COMPATIBILITY AnyNewerVersion
)
configure_package_config_file(${CMAKE_CURRENT_SOURCE_DIR}/Config.cmake.in
"${CMAKE_CURRENT_BINARY_DIR}/composable_kernelConfig.cmake"
INSTALL_DESTINATION ${CMAKE_INSTALL_LIBDIR}/cmake/composable_kernel
NO_CHECK_REQUIRED_COMPONENTS_MACRO
)
install(FILES
"${CMAKE_CURRENT_BINARY_DIR}/composable_kernelConfig.cmake"
"${CMAKE_CURRENT_BINARY_DIR}/composable_kernelConfigVersion.cmake"
DESTINATION ${CMAKE_INSTALL_LIBDIR}/cmake/composable_kernel
)