Jonathan R. Madsen
7b6d3c70bd
* Moved tests/apps to tests/bin * Renamed cmake project in tests/bin * Update samples - Use ROCPROFILER_DEFAULT_FAIL_REGEX - tweaks to stdout messages * Update tests - Use ROCPROFILER_DEFAULT_FAIL_REGEX * Add tests/lib - libraries with HIP code * Update PTL submodule - remove atexit delete of thread_id_map * Update cmake/rocprofiler_options.cmake - Set ROCPROFILER_DEFAULT_FAIL_REGEX * Update common lib: env + logging - improved customization of logging settings - default to disabling logging to files - install failure handler for rocprofv3 - set_env support in environment.* * Add lib/rocprofiler-sdk/shared_library.cpp - shared library constructor * Update lib/rocprofiler-sdk-tool/tool.cpp - destructor thread safety - convert callback_name_info and buffered_name_info to pointers - install failure handler for logging * Add tests/bin/hip-in-libraries - hip-in-libraries is an exe which uses two shared libraries where each shared library contains HIP kernels - used for testing deadlocking within __hipRegisterFatBinary * Update bin/rocprofv3 - reorganized the env variables - use exec to launch command - set ROCPROFILER_LIBRARY_CTOR=1 * Add tests/rocprofv3/tracing-hip-in-libraries - uses hip-in-libraries exe for exe which uses shared libraries to launch HIP kernels * Update bin/rocprofv3 - fix counter collection (no exec) * Update lib/rocprofiler-sdk-tool/tool.cpp - replace "Kernel-Name" with "Kernel_Name" * Update lib/rocprofiler-sdk/registration.cpp Use RTLD_LOCAL instead of RTLD_GLOBAL for env libraries * Update tests/rocprofv3 - replace "Kernel-Name" with "Kernel_Name" * Update tests - vector-ops (bin) stream syncs + runs with 4 queues per device - improve counter-collection/input1 validation - rocprofv3/tracing-hip-in-libraries does not do sys-trace - improved validation script for tracing-hip-in-libraries - updated dispatch_callback in json-tool.cpp following reworking of prototypes for counter collection * Update samples/counter_collection - updated dispatch_callback(s) and record_callback(s) following reworking of prototypes * Update bin/rocprofv3 - reorganized help menu - added options for sub-HSA tables - added --hip-runtime-trace - changed --hip-trace to include --hip-compiler-trace * Update lib/rocprofiler-sdk-tool - improved kernel filtering - removed arch_vgpr, accum_vgpr, sgpr code (in rocprofiler-sdk) - fixed issue with counter-collection w/o tracing - added support for fine grained HSA API tracing - removed directly linking to HSA-runtime * Update lib/rocprofiler-sdk/agent.cpp - rocp_agents != hsa_agents is non-fatal when ROCPROFILER_BUILD_CI=OFF (CMake option) * GPR (vector and scalar) info in kernel symbol data - rocprofiler_callback_tracing_code_object_kernel_symbol_register_data_t contains general purpose register info * Header include order fix - Include repo headers first - Third party library headers next - standard library headers last * Update dispatch profiling public API - introduce rocprofiler_profile_counting_dispatch_data_t - change signature of rocprofiler_profile_counting_dispatch_callback_t and rocprofiler_profile_counting_record_callback_t - provide rocprofiler_user_data_t pointer in dispatch callback - provide rocprofiler_user_data_t value (from dispatch cb) in record callback * Update tests/bin/CMakeLists.txt - fix add_subdirectory(hip-in-libraries) order * Update VERSION - bump to 0.2.0 in prep for AFAR
62 wiersze
2.0 KiB
CMake
62 wiersze
2.0 KiB
CMake
#
|
|
#
|
|
#
|
|
cmake_minimum_required(VERSION 3.21.0 FATAL_ERROR)
|
|
|
|
if(NOT CMAKE_HIP_COMPILER)
|
|
find_program(
|
|
amdclangpp_EXECUTABLE
|
|
NAMES amdclang++
|
|
HINTS ${ROCM_PATH} ENV ROCM_PATH /opt/rocm
|
|
PATHS ${ROCM_PATH} ENV ROCM_PATH /opt/rocm
|
|
PATH_SUFFIXES bin llvm/bin NO_CACHE)
|
|
mark_as_advanced(amdclangpp_EXECUTABLE)
|
|
|
|
if(amdclangpp_EXECUTABLE)
|
|
set(CMAKE_HIP_COMPILER "${amdclangpp_EXECUTABLE}")
|
|
endif()
|
|
endif()
|
|
|
|
project(rocprofiler-tests-lib-transpose-shared-library LANGUAGES CXX HIP)
|
|
|
|
foreach(_TYPE DEBUG MINSIZEREL RELEASE RELWITHDEBINFO)
|
|
if("${CMAKE_HIP_FLAGS_${_TYPE}}" STREQUAL "")
|
|
set(CMAKE_HIP_FLAGS_${_TYPE} "${CMAKE_CXX_FLAGS_${_TYPE}}")
|
|
endif()
|
|
endforeach()
|
|
|
|
option(TRANSPOSE_USE_MPI "Enable MPI support in transpose-shared-library exe" OFF)
|
|
|
|
set(CMAKE_CXX_STANDARD 17)
|
|
set(CMAKE_CXX_EXTENSIONS OFF)
|
|
set(CMAKE_CXX_STANDARD_REQUIRED ON)
|
|
set(CMAKE_HIP_STANDARD 17)
|
|
set(CMAKE_HIP_EXTENSIONS OFF)
|
|
set(CMAKE_HIP_STANDARD_REQUIRED ON)
|
|
|
|
set_source_files_properties(transpose.cpp PROPERTIES LANGUAGE HIP)
|
|
add_library(transpose-shared-library SHARED)
|
|
target_sources(transpose-shared-library PRIVATE transpose.cpp)
|
|
target_compile_options(transpose-shared-library PRIVATE -W -Wall -Wextra -Wpedantic
|
|
-Wshadow -Werror)
|
|
target_include_directories(transpose-shared-library PUBLIC ${CMAKE_CURRENT_SOURCE_DIR})
|
|
set_target_properties(transpose-shared-library PROPERTIES OUTPUT_NAME transpose)
|
|
|
|
find_package(Threads REQUIRED)
|
|
target_link_libraries(transpose-shared-library PRIVATE Threads::Threads)
|
|
|
|
find_package(rocprofiler-sdk-roctx REQUIRED)
|
|
target_link_libraries(transpose-shared-library
|
|
PRIVATE rocprofiler-sdk-roctx::rocprofiler-sdk-roctx)
|
|
|
|
if(TRANSPOSE_USE_MPI)
|
|
find_package(MPI REQUIRED)
|
|
target_compile_definitions(transpose-shared-library PRIVATE USE_MPI)
|
|
target_link_libraries(transpose-shared-library PRIVATE MPI::MPI_C)
|
|
endif()
|
|
|
|
install(
|
|
TARGETS transpose-shared-library
|
|
DESTINATION lib
|
|
COMPONENT tests)
|