Jonathan R. Madsen
5eb8c2658c
* Add rocprofv3-multi-node.md to source/lib/rocprofiler-sdk-tool
* Initial source re-organization
- create "output" static library
* Update include/rocprofiler-sdk/cxx/serialization.hpp
- add GPR count fields to kernel symbol serialization
* Add source/scripts/generate-rocpd.py
- reads one or more JSON output files from rocprofv3 and writes rocpd SQLite3 database
- Note: preliminary implementation
* More reorganization b/t lib/rocprofiler-sdk-tool and lib/output
* Updates to generate-rocpd.py
- add SQL views
- option: --absolute-timestamps -> --normalize-timestamps
- option: --generic-markers
- misc fixes with regards to getting the views working
- support marker names
* Update generate-rocpd.py
- Add --marker-mode option
* Update generate-rocpd.py
- Improve debugging of bad bulk SQLite statements
* Update rocprofv3-multi-node.md
- cleanup of proposed SQL schema
* lib/output/format_path.{hpp,cpp}
- rename format to format_path (in config.hpp and config.cpp)
- move format_path functionality to format_path.{hpp,cpp}
* Rework lib/output/tmp_file_buffer.{hpp,cpp}
* Update output_key.cpp
- support %cwd%, %launch_date%
* Rework lib/output/buffered_output.hpp
* Support csv_output_file constructed via domain_type
* Update lib/output/domain_type.{hpp,cpp}
- get_domain_trace_file_name
- get_domain_stats_file_name
* Update lib/rocprofiler-sdk-tool/tool.cpp
- tweak headers
* Update lib/output/generate*.cpp
- remove include of helpers.hpp
- CSV uses domain_type for filenames
* Update samples/counter_collection/per_dev_serialization.cpp
- make wait_on volatile
* Remove tool_table from lib/output and lib/rocprofiler-sdk-tool
- Also split various structs into their own files
- lib/output/agent_info
- lib/output/metadata
- lib/output/kernel_symbol_info
- lib/output/counter_info
- Implemented rocprofiler::tool::metadata
* Optimize rocprofiler_tool_counter_collection_record_t
- reduce the size of the struct from 24784 bytes to 8376 bytes
* Introduced output_config
- split subset of config (from tools library) into output_config to be able to configure the output generating functions separately from the tool library
- this is a significant step towards the output generating functions not relying on static global memory
* Stream chunks of data into output instead of loading all info memory
* Remove duplicate group_segment_size in rocprofiler_kernel_dispatch_info_t serialization
* Adding Q&A to rocprofv3-multi-node.md
* Remove all remaining include lib/rocprofiler-sdk-tool from lib/output
- migrated a fair amount of code from lib/rocprofiler-sdk-tool/helper.hpp to lib/output
* Update Q&A of rocprofv3-multi-node.md
* Fix minor compilation errors + minor cleanup
* Update hsa/async_copy.cpp
- when ROCPROFILER_CI_STRICT_TIMESTAMPS > 0, reduce the active_signal sync wait time
* Update profiling_time.hpp
- fix log messages for when start/end time is less/greater than enqueue/current CPU time
* Fix generate_stats for tool_counter_record_t
* Dictionary optimization for generate-rocpd.py
---------
Co-authored-by: SrirakshaNag <104580803+SrirakshaNag@users.noreply.github.com>
60 lignes
1.7 KiB
CMake
60 lignes
1.7 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-sdk-samples-advanced-thread-trace 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()
|
|
|
|
find_package(rocprofiler-sdk REQUIRED)
|
|
find_package(
|
|
amd_comgr
|
|
REQUIRED
|
|
CONFIG
|
|
HINTS
|
|
${rocm_version_DIR}
|
|
${ROCM_PATH}
|
|
PATHS
|
|
${rocm_version_DIR}
|
|
${ROCM_PATH}
|
|
PATH_SUFFIXES
|
|
lib/cmake/amd_comgr)
|
|
|
|
set_source_files_properties(main.cpp PROPERTIES LANGUAGE HIP)
|
|
set_source_files_properties(main.cpp PROPERTIES COMPILE_FLAGS "-g")
|
|
|
|
add_executable(advanced-thread-trace)
|
|
target_sources(advanced-thread-trace PRIVATE main.cpp client.cpp)
|
|
target_link_libraries(
|
|
advanced-thread-trace
|
|
PRIVATE rocprofiler-sdk::rocprofiler-sdk amd_comgr
|
|
rocprofiler-sdk::samples-common-library rocprofiler-sdk::samples-build-flags)
|
|
|
|
rocprofiler_samples_get_preload_env(PRELOAD_ENV)
|
|
|
|
add_test(NAME advanced-thread-trace COMMAND $<TARGET_FILE:advanced-thread-trace>)
|
|
|
|
set_tests_properties(
|
|
advanced-thread-trace
|
|
PROPERTIES TIMEOUT 45 LABELS "samples" ENVIRONMENT "${PRELOAD_ENV}"
|
|
FAIL_REGULAR_EXPRESSION "threw an exception")
|