Jonathan R. Madsen
395f01b689
* Move include/rocprofiler-sdk/cxx/details/delimit.hpp to tokenize.hpp
* Update docs/how-to/using-rocprofv3.rst
- fix code block indents
- reorder rocprofv3 options, limit them to important options
- add docs for `--runtime-trace`
* Update rocprofv3.py
- parser argument groups
- new `--runtime-trace` option
- new `--summary` option
- new `--summary-per-domain` option
- new `--summary-groups` option
- new `--summary-output-file` option
- new `--summary-units` option
* Update lib/rocprofiler-sdk/hsa/async_copy.cpp
- fix async copy operation names: add "MEMORY_COPY_" prefix
* lib/rocprofiler-sdk-tool: update statistics.{hpp,cpp}
- statistics<>::get_percent function
- stats_entry_t struct
- stats_formatter struct
- percentage struct
- std::to_string(::rocprofiler::tool::percentage)
* lib/rocprofiler-sdk-tool: update domain_type.{hpp,cpp}
- reorder domain_type enum values
* lib/rocprofiler-sdk-tool: update generateCSV.{hpp,cpp}
- separate writing CSV from accumulating statistics
- a lot of functionality was moved to statistics.{hpp,cpp}
* lib/rocprofiler-sdk-tool: update output_file.{hpp,cpp}
- output_stream_t struct
- get_output_stream(...) returns output_stream_t instance
* lib/rocprofiler-sdk-tool: update generateJSON.cpp
- update get_output_stream usage to output_stream_t
* lib/rocprofiler-sdk-tool: update generateOTF2.cpp
- header include order tweak
* lib/rocprofiler-sdk-tool: update buffered_output.hpp
- stats_data_t was renamed to stats_entry_t
* lib/rocprofiler-sdk-tool: update generatePerfetto.cpp
- header include tweak
* lib/rocprofiler-sdk-tool: update tmp_file_buffer.hpp
- emit warning message if write_ring_buffer fails after offloading instead of aborting
- prefer placement new instead of assignment in write_ring_buffer
* lib/rocprofiler-sdk-tool: add generateStats.{hpp,cpp}
- functions for accumulating statistics
* Update tests/rocprofv3/tracing-hip-in-libraries/CMakeLists.txt
- accommodate tweak to CSV output file name for HIP and HSA traces
* lib/rocprofiler-sdk-tool: update config.{hpp,cpp}
- new config variables
- stats_summary
- stats_summary_per_domain
- summary_output
- stats_summary_unit_value
- stats_summary_unit
- stats_summary_file
- stats_summary_groups
- support output keys for hostname: %hostname% / %h
* lib/rocprofiler-sdk-tool: update tool.cpp
- support summary output
* Documentation fixes
* Test for summary output
* Update tests/bin/transpose to use more ROCTx
- also support building with the roctracer ROCTx
* Remove roctxMark from OTF2 + fix kernel-rename tests
- following more ROCTx calls in transpose, kernel-rename validation had to be updated
* JSON metadata + JSON summary
- add serialization support for config
- add serialization support for statistics
- additions to json spec
- rocprofiler-sdk-tool/metadata/config
- rocprofiler-sdk-tool/metadata/command
- rocprofiler-sdk-tool/summary
- config output_keys support for NVIDIA %q{<ENV-VAR>} syntax
- config output_keys support keys within keys
* rocprofv3 --summary-groups warning if no domain matches
- emit warning if a regex in for summary groups did not match any domain names
* Compile fix for lib/rocprofiler-sdk-tool/tool.cpp
- get_config().scratch_memory_trace
- pass contributions to write_json
* Update rocprofv3.py to preload rocprofiler-sdk-roctx
- appended to LD_PRELOAD when args.marker_trace is enabled
* Fix ReST link errors about subtitle underline being too short
* Patch tokenization of config::stats_summary_groups
- guard against array values of empty strings
* Tweak rocprofv3 summary test
- input-summary.yaml (used by rocprofv3-test-summary-inp-yaml-execute) only provides one summary group regex
* Disable LD_PRELOAD of librocprofiler-sdk-roctx.so
- this causes problems in the sanitizers, will be addressed in another PR
100 líneas
3.1 KiB
CMake
100 líneas
3.1 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-bin-transpose LANGUAGES CXX HIP)
|
|
|
|
foreach(_TYPE DEBUG MINSIZEREL RELEASE RELWITHDEBINFO)
|
|
if("${CMAKE_HIP_FLAGS_${_TYPE}}" STREQUAL "")
|
|
set(CMAKE_HIP_FLAGS_${_TYPE} "${CMAKE_CXX_FLAGS_${_TYPE}}")
|
|
endif()
|
|
endforeach()
|
|
|
|
option(TRANSPOSE_USE_MPI "Enable MPI support in transpose exe" OFF)
|
|
|
|
set(CMAKE_CXX_STANDARD 17)
|
|
set(CMAKE_CXX_EXTENSIONS OFF)
|
|
set(CMAKE_CXX_STANDARD_REQUIRED ON)
|
|
set(CMAKE_HIP_STANDARD 17)
|
|
set(CMAKE_HIP_EXTENSIONS OFF)
|
|
set(CMAKE_HIP_STANDARD_REQUIRED ON)
|
|
|
|
set_source_files_properties(transpose.cpp PROPERTIES LANGUAGE HIP)
|
|
|
|
function(transpose_build_target _NAME _COMPILE_DEFS _LINK_TARGETS)
|
|
add_executable(${_NAME})
|
|
target_sources(${_NAME} PRIVATE transpose.cpp)
|
|
target_compile_definitions(${_NAME} PRIVATE ${_COMPILE_DEFS})
|
|
target_compile_options(${_NAME} PRIVATE -W -Wall -Wextra -Wpedantic -Wshadow -Werror)
|
|
target_link_libraries(
|
|
${_NAME} PRIVATE Threads::Threads rocprofiler-sdk::tests-build-flags
|
|
${_LINK_TARGETS})
|
|
|
|
if(TRANSPOSE_USE_MPI)
|
|
find_package(MPI REQUIRED)
|
|
target_compile_definitions(${_NAME} PRIVATE USE_MPI=1)
|
|
target_link_libraries(${_NAME} PRIVATE MPI::MPI_C)
|
|
endif()
|
|
|
|
endfunction()
|
|
|
|
find_package(Threads REQUIRED)
|
|
find_package(rocprofiler-sdk-roctx REQUIRED)
|
|
|
|
transpose_build_target(transpose "" rocprofiler-sdk-roctx::rocprofiler-sdk-roctx)
|
|
|
|
#
|
|
# using old roctracer roctx
|
|
#
|
|
find_path(
|
|
roctracer_roctx_ROOT_DIR
|
|
NAMES include/roctracer/roctx.h
|
|
HINTS ${hip_DIR}
|
|
PATHS ${hip_DIR})
|
|
|
|
find_path(
|
|
roctracer_roctx_INCLUDE_DIR
|
|
NAMES roctracer/roctx.h
|
|
HINTS ${roctracer_roctx_ROOT_DIR} ${hip_DIR}
|
|
PATHS ${roctracer_roctx_ROOT_DIR} ${hip_DIR}
|
|
PATH_SUFFIXES include)
|
|
|
|
find_library(
|
|
roctracer_roctx_LIBRARY
|
|
NAMES roctx64
|
|
HINTS ${roctracer_roctx_ROOT_DIR} ${hip_DIR}
|
|
PATHS ${roctracer_roctx_ROOT_DIR} ${hip_DIR}
|
|
PATH_SUFFIXES lib lib64)
|
|
|
|
include(FindPackageHandleStandardArgs)
|
|
|
|
find_package_handle_standard_args(roctracer-roctx DEFAULT_MSG roctracer_roctx_ROOT_DIR
|
|
roctracer_roctx_INCLUDE_DIR roctracer_roctx_LIBRARY)
|
|
|
|
if(roctracer-roctx_FOUND)
|
|
add_library(roctracer-roctx INTERFACE IMPORTED)
|
|
add_library(roctracer-roctx::roctracer-roctx ALIAS roctracer-roctx)
|
|
target_include_directories(roctracer-roctx INTERFACE ${roctracer_roctx_INCLUDE_DIR})
|
|
target_link_libraries(roctracer-roctx INTERFACE ${roctracer_roctx_LIBRARY})
|
|
endif()
|
|
|
|
if(TARGET roctracer-roctx::roctracer-roctx)
|
|
transpose_build_target(transpose-roctracer-roctx "USE_ROCTRACER_ROCTX=1"
|
|
roctracer-roctx::roctracer-roctx)
|
|
endif()
|