Files
rocm-systems/cmake/Formatting.cmake
T
Jonathan R. Madsen 518c83e0f9 Dynamic expansion of thread data (#294)
* Tests for exceeding OMNITRACE_MAX_THREADS

- tests which exceeds OMNITRACE_MAX_THREADS value for thread creation

* CMake Formatting.cmake update

- include source files in /tests/source directory

* Add unknown-hash= to OMNITRACE_ABORT_FAIL_REGEX

- fail if a timemory hash is not resolved to a name

* Tests for exceeding OMNITRACE_MAX_THREADS

- update

* omnitrace-sample update

- remove env disabling of critical-trace and process-sampling

* core library update

- make_unique in concepts.hpp
- add OMNITRACE_USE_ROCM_SMI to "process_sampling" category
- remove forced disabling of critical-trace in sampling mode
- parentheses for OMNITRACE_PREFER
- use tim::get_hash_id instead of tim::get_combined_hash_id

* core library update (containers)

- added aligned_static_vector.hpp
  - similar to static_vector.hpp but attempts to align to cache line size
- alignment template parameter for stable_vector
- added missing aliases in static_vector
  - consistent with aligned_static_vector aliases

* thread_info update

- track the peak number of threads created
- thread_info::get_peak_num_threads() returns the peak number of threads

* thread_data update

- generic thread_data inherits from base_thread_data
- thread_data reworked to support dynamic expansion
- base_thread_data updated to invoke private_instance() function
- thread_data<optional<T>> uses stable_vector aligned to cache line width
- thread_data<identity<T>> uses stable_vector aligned to cache line width
- thread_data for optional and identity provide private private_instance function + friend to base_thread_data
- component_bundle_cache<T> is now thread_data<component_bundle_cache_impl<T>>

* causal update

- thread_data<T>::instances -> thread_data<T>::instance(construct_on_thread{ ... })
- loop over max_supported_threads (constexpr) -> loop over thread_info::get_peak_num_threads()
- tim::get_combined_hash_id -> tim::get_hash_id
- update progress_bundle usage to new thread_data API

* backtrace/backtrace_metrics component update

- backtrace_metrics update
  - update to new thead_data API
  - add thread CPU time row in perfetto
  - fix potential bug when rusage categories are disabled
  - fix bug in operator-= not subtracting cpu time of rhs
- backtrace update
  - skip all child call-stack below 'tim::openmp::' if sampling_keep_internal = false

* pthread_gotcha component update

- pthread_gotcha::shutdown() invokes pthread_create_gotcha::shutdown()

* pthread_create_gotcha component update

- minor tweak to {start,stop}_bundle functions: pass in thread id
- update to new thread_data API
- track native handles of internal threads
- implement system with pthread_kill to stop dangling bundles

* rocprofiler/roctracer component update

- update to new thread_data API
- loop over max_supported_threads (constexpr) -> loop over thread_info::get_peak_num_threads()

* critical trace (library) update

- update to new thread_data API
- tim::get_combined_hash_id -> tim::get_hash_id

* coverage update

- update to new thread_data API

* tasking update

- update to new thread_data API
- loop over max_supported_threads (constexpr) -> loop over thread_info::get_peak_num_threads()

* roctracer update

- update to new thread_data API
- loop over max_supported_threads (constexpr) -> loop over thread_info::get_peak_num_threads()

* rocm_smi update

- update to new thread_data API

* runtime.cpp update

- update to new thread_data API

* sampling.cpp update

- update to new thread_data API
- loop over max_supported_threads (constexpr) -> loop over thread_info::get_peak_num_threads()

* ompt.cpp update

- invoke pthread_gotcha::shutdown before invoking OMPT finalize function
  - this prevents signals from being delivered to OpenMP threads

* tracing.hpp and tracing.cpp update

- replace get_timemory_hash_{ids,aliases} functions with copy_timemory_hash_ids function
- update to new thread_data API
- loop over max_supported_threads (constexpr) -> loop over thread_info::get_peak_num_threads()
- tim::get_combined_hash_id -> tim::get_hash_id
- improvements to + error checking in thread_init function

* library.cpp update

- move copying timemory hash id/aliases to tracing.cpp
- update to new thread_data API
- loop over max_supported_threads (constexpr) -> loop over thread_info::get_peak_num_threads()

* Update BuildSettings.cmake

- add -Wno-interference-size to suppress warning about use of std::hardware_destructive_interference

* Update fork example

- improve scheme for waiting on child processes via waitpid instead of wait
- support running main routine multiple times
- push/pop regions in child process

* Update lib/common/defines.h.in

- allow use to specify misc values via -D <name>=<value>
  - OMNITRACE_CACHELINE_SIZE
  - OMNITRACE_CACHELINE_SIZE_MIN
  - OMNITRACE_ROCM_MAX_COUNTERS
- remove unused defines
  - OMNITRACE_ROCM_LOOK_AHEAD
  - OMNITRACE_MAX_ROCM_QUEUES

* Update rocprofiler.hpp

- OMNITRACE_MAX_ROCM_COUNTERS -> OMNITRACE_ROCM_MAX_COUNTERS

* Update aligned_static_vector

- set cacheline_align_v from max of OMNITRACE_CACHELINE_SIZE and OMNITRACE_CACHELINE_SIZE_MIN

* Update tracing.cpp

- acquire locks for updating main hash ids/aliases
- only propagate ids/aliases when finalizing

* Update pthread_create_gotcha.cpp

- make sure hash for "start_thread" exists on main thread

* Update causal end to end tests

- if OMNITRACE_BUILD_NUMBER is 1, set OMNITRACE_VERBOSE=0
2023-10-16 18:04:47 -05:00

132 líneas
5.0 KiB
CMake

include_guard(DIRECTORY)
# ----------------------------------------------------------------------------------------#
#
# Clang Tidy
#
# ----------------------------------------------------------------------------------------#
# clang-tidy
macro(OMNITRACE_ACTIVATE_CLANG_TIDY)
if(OMNITRACE_USE_CLANG_TIDY)
find_program(CLANG_TIDY_COMMAND NAMES clang-tidy)
omnitrace_add_feature(CLANG_TIDY_COMMAND "Path to clang-tidy command")
if(NOT CLANG_TIDY_COMMAND)
timemory_message(
WARNING "OMNITRACE_USE_CLANG_TIDY is ON but clang-tidy is not found!")
set(OMNITRACE_USE_CLANG_TIDY OFF)
else()
set(CMAKE_CXX_CLANG_TIDY ${CLANG_TIDY_COMMAND})
# Create a preprocessor definition that depends on .clang-tidy content so the
# compile command will change when .clang-tidy changes. This ensures that a
# subsequent build re-runs clang-tidy on all sources even if they do not
# otherwise need to be recompiled. Nothing actually uses this definition. We
# add it to targets on which we run clang-tidy just to get the build
# dependency on the .clang-tidy file.
file(SHA1 ${CMAKE_CURRENT_LIST_DIR}/.clang-tidy clang_tidy_sha1)
set(CLANG_TIDY_DEFINITIONS "CLANG_TIDY_SHA1=${clang_tidy_sha1}")
unset(clang_tidy_sha1)
endif()
endif()
endmacro()
# ------------------------------------------------------------------------------#
#
# clang-format target
#
# ------------------------------------------------------------------------------#
find_program(OMNITRACE_CLANG_FORMAT_EXE NAMES clang-format-11 clang-format-mp-11
clang-format)
find_program(OMNITRACE_CMAKE_FORMAT_EXE NAMES cmake-format)
find_program(OMNITRACE_BLACK_FORMAT_EXE NAMES black)
add_custom_target(format-omnitrace)
if(NOT TARGET format)
add_custom_target(format)
endif()
foreach(_TYPE source python cmake)
if(NOT TARGET format-${_TYPE})
add_custom_target(format-${_TYPE})
endif()
endforeach()
if(OMNITRACE_CLANG_FORMAT_EXE
OR OMNITRACE_BLACK_FORMAT_EXE
OR OMNITRACE_CMAKE_FORMAT_EXE)
file(GLOB_RECURSE sources ${PROJECT_SOURCE_DIR}/source/*.cpp
${PROJECT_SOURCE_DIR}/source/*.c)
file(GLOB_RECURSE headers ${PROJECT_SOURCE_DIR}/source/*.hpp
${PROJECT_SOURCE_DIR}/source/*.hpp.in ${PROJECT_SOURCE_DIR}/source/*.h
${PROJECT_SOURCE_DIR}/source/*.h.in)
file(GLOB_RECURSE examples ${PROJECT_SOURCE_DIR}/examples/*.cpp
${PROJECT_SOURCE_DIR}/examples/*.c ${PROJECT_SOURCE_DIR}/examples/*.hpp
${PROJECT_SOURCE_DIR}/examples/*.h)
file(GLOB_RECURSE tests_source ${PROJECT_SOURCE_DIR}/tests/source/*.cpp
${PROJECT_SOURCE_DIR}/tests/source/*.hpp)
file(GLOB_RECURSE external ${PROJECT_SOURCE_DIR}/examples/lulesh/external/kokkos/*)
file(
GLOB_RECURSE
cmake_files
${PROJECT_SOURCE_DIR}/source/*CMakeLists.txt
${PROJECT_SOURCE_DIR}/examples/*CMakeLists.txt
${PROJECT_SOURCE_DIR}/tests/*CMakeLists.txt
${PROJECT_SOURCE_DIR}/source/*.cmake
${PROJECT_SOURCE_DIR}/examples/*.cmake
${PROJECT_SOURCE_DIR}/tests/*.cmake
${PROJECT_SOURCE_DIR}/cmake/*.cmake
${PROJECT_SOURCE_DIR}/source/*.cmake)
list(APPEND cmake_files ${PROJECT_SOURCE_DIR}/CMakeLists.txt)
if(external)
list(REMOVE_ITEM examples ${external})
list(REMOVE_ITEM cmake_files ${external})
endif()
if(OMNITRACE_CLANG_FORMAT_EXE)
add_custom_target(
format-omnitrace-source
${OMNITRACE_CLANG_FORMAT_EXE} -i ${sources} ${headers} ${examples}
${tests_source}
COMMENT "[omnitrace] Running C++ formatter ${OMNITRACE_CLANG_FORMAT_EXE}...")
endif()
if(OMNITRACE_BLACK_FORMAT_EXE)
add_custom_target(
format-omnitrace-python
${OMNITRACE_BLACK_FORMAT_EXE} -q ${PROJECT_SOURCE_DIR}
COMMENT
"[omnitrace] Running Python formatter ${OMNITRACE_BLACK_FORMAT_EXE}...")
if(NOT TARGET format-python)
add_custom_target(format-python)
endif()
endif()
if(OMNITRACE_CMAKE_FORMAT_EXE)
add_custom_target(
format-omnitrace-cmake
${OMNITRACE_CMAKE_FORMAT_EXE} -i ${cmake_files}
COMMENT "[omnitrace] Running CMake formatter ${OMNITRACE_CMAKE_FORMAT_EXE}..."
)
if(NOT TARGET format-cmake)
add_custom_target(format-cmake)
endif()
endif()
foreach(_TYPE source python cmake)
if(TARGET format-omnitrace-${_TYPE})
add_dependencies(format-omnitrace format-omnitrace-${_TYPE})
add_dependencies(format-${_TYPE} format-omnitrace-${_TYPE})
endif()
endforeach()
foreach(_TYPE source python)
if(TARGET format-omnitrace-${_TYPE})
add_dependencies(format format-omnitrace-${_TYPE})
endif()
endforeach()
else()
message(STATUS "clang-format could not be found. format build target not available.")
endif()