GPU HW Counters via rocprofiler (#84)

* 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

[ROCm/rocprofiler-systems commit: 4208b5654c]
This commit is contained in:
Jonathan R. Madsen
2022-07-17 21:52:09 -05:00
کامیت شده توسط GitHub
والد aa7f2f63af
کامیت 7d1989f5a4
51فایلهای تغییر یافته به همراه3973 افزوده شده و 390 حذف شده
@@ -23,10 +23,7 @@ else()
AND LIBOMP_LIBRARY
AND COMMAND omnitrace_custom_compilation)
target_compile_options(openmp-common PUBLIC -W -Wall -fopenmp=libomp)
target_compile_options(openmp-cg PRIVATE -W -Wall -fopenmp=libomp)
target_link_libraries(openmp-cg PRIVATE ${LIBOMP_LIBRARY})
target_compile_options(openmp-lu PRIVATE -W -Wall -fopenmp=libomp)
target_link_libraries(openmp-lu PRIVATE ${LIBOMP_LIBRARY})
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)
@@ -36,6 +33,9 @@ else()
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