Jonathan R. Madsen
4208b5654c
* Initial support for GPU hardware counters
* Update find modules for roctracer and rocprofiler
- /opt/rocm/{rocprofiler,roctracer} path is deprecated so tweak search procedure
* Improve ConfigCPack for MPI
* Update rocprofiler
- rocm_metrics()
- minor cleanup
* Update rocm find modules
* declare rocm_metrics + call in omnitrace-avail
* relocate omnitrace-launch-compiler
* REALPATH and find_modules
* Examples cmake (may drop)
* omnitrace-avail
- hw_counter categories
- init rocm
* setenv updates for rocprofiler in library.cpp and dl.cpp
* get_rocm_events config
* gpu::hip_device_count()
* rocm_metrics returns hardware_counters::info
* - relocated library/components/roctracer_callbacks.* to library/roctracer.*
- relocated library/components/rocprofiler.* to library/rocprofiler.*
- cleaned up rocprofiler.hpp
- added perfetto output of rocprofiler
- added timemory output of rocprofiler
- renamed omni.roctracer thread to roctracer.hip
- added roctracer.hsa thread name
- updated timemory submodule to support std::variant
- updated timemory submodule to support = in config value
- updated timemory submodule to support standalone storage
- updated timemory submodule to support new hw counter apis
- updated timemory submodule to prevent label/description caching in data_tracker
* update omnitrace-avail info_type generation
* Update timemory submodule
* rocprofiler component
* cmake formatting
* omnitrace-avail handle no GPUs
- Add -c command-line option for --categories
- support verbosity
* hsa_rsrc_factory throws exceptions
- throw exceptions to avoid aborting on HSA_STATUS_ERROR_NOT_INITIALIZED when advantageous
- removed duplicate specialization of is_available for component::rocprofiler
* rocprofiler symbols for when disabled
* Fix warning in omnitrace-avail
- std::stringstream from initializer list would use explicit constructor
* Fix finalization after settings are deleted
* Reorganized rocprofiler source
* Updated formatting
* Miscellaneous tweaks
- added using statements from timemory
- tweaked the main and thread bundle names
- fixed timemory header includes
45 γραμμές
1.7 KiB
CMake
45 γραμμές
1.7 KiB
CMake
cmake_minimum_required(VERSION 3.16 FATAL_ERROR)
|
|
|
|
project(omnitrace-openmp LANGUAGES CXX)
|
|
|
|
file(GLOB common_source ${CMAKE_CURRENT_SOURCE_DIR}/common/*.cpp)
|
|
add_library(openmp-common OBJECT ${common_source})
|
|
target_include_directories(openmp-common PUBLIC ${CMAKE_CURRENT_SOURCE_DIR}/common)
|
|
|
|
add_executable(openmp-cg ${CMAKE_CURRENT_SOURCE_DIR}/CG/cg.cpp
|
|
$<TARGET_OBJECTS:openmp-common>)
|
|
add_executable(openmp-lu ${CMAKE_CURRENT_SOURCE_DIR}/LU/lu.cpp
|
|
$<TARGET_OBJECTS:openmp-common>)
|
|
|
|
if(CMAKE_CXX_COMPILER_ID MATCHES "Clang")
|
|
find_package(OpenMP REQUIRED)
|
|
target_link_libraries(openmp-common PUBLIC OpenMP::OpenMP_CXX)
|
|
else()
|
|
find_program(CLANGXX_EXECUTABLE NAMES clang++)
|
|
find_library(
|
|
LIBOMP_LIBRARY
|
|
NAMES omp omp5 ${CMAKE_SHARED_LIBRARY_PREFIX}omp${CMAKE_SHARED_LIBRARY_SUFFIX}.5)
|
|
if(CLANGXX_EXECUTABLE
|
|
AND LIBOMP_LIBRARY
|
|
AND COMMAND omnitrace_custom_compilation)
|
|
target_compile_options(openmp-common PUBLIC -W -Wall -fopenmp=libomp)
|
|
target_link_libraries(openmp-common PUBLIC ${LIBOMP_LIBRARY})
|
|
omnitrace_custom_compilation(COMPILER ${CLANGXX_EXECUTABLE} TARGET openmp-common)
|
|
omnitrace_custom_compilation(COMPILER ${CLANGXX_EXECUTABLE} TARGET openmp-cg)
|
|
omnitrace_custom_compilation(COMPILER ${CLANGXX_EXECUTABLE} TARGET openmp-lu)
|
|
else()
|
|
find_package(OpenMP REQUIRED)
|
|
target_link_libraries(openmp-common PUBLIC OpenMP::OpenMP_CXX)
|
|
endif()
|
|
endif()
|
|
|
|
target_link_libraries(openmp-cg PRIVATE openmp-common)
|
|
target_link_libraries(openmp-lu PRIVATE openmp-common)
|
|
|
|
if(OMNITRACE_INSTALL_EXAMPLES)
|
|
install(
|
|
TARGETS openmp-cg openmp-lu
|
|
DESTINATION bin
|
|
COMPONENT omnitrace-examples)
|
|
endif()
|