8a25b239bca21dbcd46fcc07974b505c8f5d972d
4 コミット
| 作成者 | SHA1 | メッセージ | 日付 | |
|---|---|---|---|---|
 Jonathan R. Madsen
|
21dd088c8e |
ROCTx Library Tracing (#390)
* Update include/rocprofiler-sdk/marker/*
- Update rocprofiler_marker_api_args_t for all API functions
- Add ROCPROFILER_MARKER_API_ID_roctxGetThreadId to rocprofiler_marker_api_id_t
* Update include/rocprofiler-sdk/marker/api_args.h
- fix include
* Update lib/common/mpl.hpp
- is_pair
- is_type_complete_v
* Update include/rocprofiler-sdk/marker/*
- fix rocprofiler_marker_api_retval_t
- add roctxGetThreadId to rocprofiler_marker_api_args_t
- fix type in enum: HsaDevice -> HsaAgent
- add table_api_id.h
* Update include/rocprofiler-sdk/marker.h
- include marker/table_api_id.h
* Update include/rocprofiler-sdk/buffer_tracing.h
- Buffer marker tracer records have begin and end timestamp
* Add lib/rocprofiler-sdk/marker
- tracing implementation for marker (roctx) library
* Update include/rocprofiler-sdk/{buffer_tracing,marker/table_api_id}.h
- rocprofiler_buffer_tracing_marker_record_t -> rocprofiler_buffer_tracing_marker_api_record_t
* Update lib/rocprofiler-sdk/buffer_tracing.cpp
- support for ROCPROFILER_BUFFER_TRACING_MARKER_API
* Update lib/rocprofiler-sdk/callback_tracing.cpp
- support for ROCPROFILER_CALLBACK_TRACING_MARKER_API
* Update lib/rocprofiler-sdk/intercept_table.cpp
- template instantiation for notify_runtime_api_registration
* Update lib/rocprofiler-sdk/registration.cpp
- enable roctx in rocprofiler_set_api_table
* Update lib/rocprofiler-sdk/marker/marker.cpp
- rocprofiler_buffer_tracing_marker_record_t -> rocprofiler_buffer_tracing_marker_api_record_t
* Update lib/rocprofiler/tests for roctx testing
- add roctx.cpp
- unit tests for roctx callback and buffer tracing
- support marker API in get_{buffer,callback}_tracing_names()
* Update lib/common/logging.cpp
- logging initialized message mentions env variable
* Update lib/common/mpl.hpp
- NOLINT for misc-definitions-in-headers
* Update lib/rocprofiler-sdk/tests/CMakeLists.txt
- include LD_LIBRARY_PATH in rocprofiler-lib-tests-shared tests
* Update lib/rocprofiler-sdk/registration.cpp
- client_library_vec_t is now vector of option<client_library>
- enables resetting the client_library after finalization
- removed acquiring registration lock when invoke_client_finalizers called via atexit
- this was causing some lock-order-inversion warnings (potential deadlock)
* Update lib/rocprofiler-sdk/agent.cpp
- model name for agent supports spaces
* Update tests/common/serialization.hpp
- add serialization support for marker tracing data structures
* Update tests/apps
- Add ROCTx markers into reproducible-runtime and transpose
* Update tests/tools/json-tools.cpp
- add marker tracing support
- remove strdup (no longer necessary)
* Update tests/kernel-tracing/validate.py
- validate marker API tracing data
* Update tests/async-copy-tracing/validate.py
- validate marker API tracing data
* Update cmake for load path resolution during testing
* Update tests/async-copy-tracing/CMakeLists.txt
- fix test LD_LIBRARY_PATH
* Update cmake/Templates/rocprofiler-sdk-roctx/config.cmake.in
- fix constructing rocprofiler-sdk-roctx::rocprofiler-sdk-roctx
|
||
|
Jonathan R. Madsen
|
a24b08c2db |
Update tests/apps/* to support multigpu in single process (#374)
- CPU threads will spread out across multiple devices |
||
|
Jonathan R. Madsen
|
cf5e4b4b1b |
Integration Testing (#211)
* Add external/cereal submodule - used for integration testing * Update lib/common/container/small_vector.hpp - documentation notes * Update tests/apps - update transpose app (fix build) - add reproducible-runtime app * Update include/rocprofiler/fwd.h - rocprofiler_service_callback_phase_t -> rocprofiler_callback_phase_t * Update PTL submodule - fix for task group: submitting tasks from different thread * Update lib/rocprofiler/hsa/queue.cpp - CHECK_NOTNULL(_buffer) * Update lib/rocprofiler/hsa/hsa.cpp - use buffer::get_buffer instead of manually looking for buffer * Update lib/rocprofiler/internal_threading.cpp - use buffer::get_buffer instead of manually looking for buffer * Update lib/rocprofiler/buffer.cpp - offset the buffer id - properly handle rocprofiler_create_buffer reusing rocprofiler_buffer_id_t on a different context * Update tests - kernel tracing library for integration testing * Add cereal submodule * Update lib/rocprofiler/registration.* - OnUnload - Support ROCP_TOOL_LIBRARIES for python usage - improve finalize function - remove calling hsa_shut_down in finalize function * Update lib/rocprofiler/buffer.* - allocate_buffer sets the buffer id value - expose (internally) is_valid_buffer_id - update test * Update tests/kernel-tracing - installation - better organization of JSON groups - improved messaging * Update lib/rocprofiler/registration.cpp - add workaround for hsa-runtime supporting rocprofiler-register * Update tests/kernel-tracing/kernel-tracing.cpp - fix memory leaks * cereal support for minimal JSON - update cereal submodule to rocprofiler branch - change REPO_BRANCH in rocprofiler_checkout_git_submodule for cereal - update tests/kernel-tracing/kernel-tracing.cpp - use minimal json - slight tweak putting giving contexts name in storing name + context pointer pair in map * Update tests/kernel-tracing/kernel-tracing.cpp - support runtime selection of contexts via KERNEL_TRACING_CONTEXTS environment variable * Update tests - tests/CMakeLists.txt - find_package(Python3 REQUIRED) - tests/kernel-tracing - pytest validation * Update CI workflow - install pytest - add checks for test labels * Update scripts/run-ci.py - change --coverage options - replace 'unittests' with 'tests' - replace test label regex '-L unittests' with '-L tests' * Update requirements.txt - this is now an empty file since none of the packages are required for this repo |
||
|
Jonathan R. Madsen
|
3082288a25 |
Code object, kernel dispatch, and memory copy tracing (#177)
* Update samples/api_buffered_tracing
- external correlation id
- support ROCPROFILER_BUFFER_TRACING_KERNEL_DISPATCH
* Update lib/rocprofiler/context.cpp
- update alternative get_active_contexts paradigm
* Update lib/rocprofiler/external_correlation.cpp
- inherit correlation id from main thread
* Update lib/rocprofiler/hsa/queue.*
- typedef changes
- rocprofiler_packet union
- modify Queue::queue_info_session_t
- use rocprofiler_packet
- add thread id
- add kernel id
- add correlation id
- out of line definitions
- AsyncSignalHandler function update
- handle kernel dispatch tracing
- Move CreateBarrierPacket and AddVendorSpecificPacket to lambdas
- handle contexts
* Update lib/rocprofiler/hsa/hsa.cpp
- remove unnecessary log function
- use new get_active_contexts paradigm
- use new correlation id updates
* Update AgentCache and kernel dispatch record
- include const rocprofiler_agent_t* in rocprofiler_buffer_tracing_kernel_dispatch_record_t
- AgentCache::get_rocp_agent returns const pointer
* Replace ROCPROFILER_SERVICE_ with ROCPROFILER_
* source formatting
* Code Object Tracing
- include/rocprofiler/callback_tracing.h
- remove rocprofiler_callback_tracing_code_object_unload_data_t
- remove rocprofiler_callback_tracing_code_object_kernel_symbol_register_data_t
- include/rocprofiler/fwd.h
- remove ROCPROFILER_CALLBACK_TRACING_CODE_OBJECT_UNLOAD
- remove ROCPROFILER_CALLBACK_TRACING_CODE_OBJECT_DEVICE_KERNEL_SYMBOL_UNREGISTER
- lib/common/utility.hpp
- assert_public_api_struct_properties()
- init_public_api_struct(...)
- lib/rocprofiler/registration.cpp
- invoke hsa::code_object_init
- lib/rocprofiler/hsa/CMakeLists.txt
- compile code_object code
- lib/rocprofiler/hsa/code_object.{hpp,cpp}
- tracing code object load/unload
- lib/rocprofiler/hsa/queue.cpp
- get_kernel_id
* Update lib/rocprofiler/hsa/hsa.cpp
- fix should_wrap_functor logic (which was not handling callback_tracer + buffered_tracer properly)
* Update lib/rocprofiler/hsa/queue.cpp
- fix rocprofiler_buffer_tracing_kernel_dispatch_record_t construction
* Update samples/api_buffered_tracing/client.cpp
- print kernel names
* Move samples/apps to tests/apps
* Update lib/rocprofiler/hsa/code_object.cpp
- ensure unload callbacks when application is exiting
- support user data in between load/unload callbacks
* Update lib/rocprofiler/hsa/queue.{hpp,cpp}
- store contexts and external correlation ids in queue_info_session
- reduce signal_limiter to 96 to fix hangs
- fix support for kernel tracing and async memory copies
* Add lib/common/scope_destructor.hpp
- similar to static_cleanup_wrapper but different
* Update include/rocprofiler/buffer_tracing.h
- update rocprofiler_buffer_tracing_memory_copy_record_t
- remove operation: user can figure that out from correlation id
- add kernel id
- add rocprofiler agent id
* Update include/rocprofiler/callback_tracing.h
- fix data type of load_delta field in code object
- remove rocp_agent from kernel_symbol_register_data_t (known via code_object_id)
* Add samples/code_object_tracing
- sample demonstrating code object tracing
* Update samples
- minor tweak to print_call_stack
* Update lib/rocprofiler/hsa/code_object.cpp
- flip ordering of unload callbacks for code object unloading and kernel symbol deregistering
* clang-tidy fixes
* Update lib/rocprofiler/hsa/code_object.cpp
- fix heap-use-after-free issue with code object
* Update include/rocprofiler/external_correlation.h
- update documentation to include info about default value of external correlation value
* Use common::container::small_vector for contexts
- small_vector<const context*> is an ideal data structure for array of active contexts
* Update context handling for code object unload
- code object unload is only called for contexts which received the load callback
* Update samples
- improve ROCPROFILER_CALL macro to include status string
- api_buffered_tracing handles ROCPROFILER_STATUS_ERROR_BUFFER_BUSY
* Code object shutdown
- ensure code object callbacks are invoked prior to finalizing
* Update lib/common (memory allocators)
- added lib/common/memory folder with allocators
* Add lib/rocprofiler/allocator.*
- rocprofiler::allocator::static_data_allocator
- special allocator for static data which finalizes before any data gets destroyed
- rocprofiler::allocator::unique_static_ptr_t
- unique_ptr that uses static data deleter (ensure finalize is called)
* Update lib/rocprofiler/buffer.cpp
- flush checks fini status
- use unique_static_ptr_t
* Update lib/rocprofiler/internal_threading.*
- change meaning of thread_pool_t and task_group_t
- improve finalization to prevent data races and heap-use-after-free
* Update lib/rocprofiler/registration.cpp
- use static_data_allocator for client_library vector
* Update lib/rocprofiler/context/context.*
- use allocator::unique_static_ptr_t
* Update lib/rocprofiler/allocator.cpp
- avoid deadlock in deleter<static_data>::operator()
* Update lib/rocprofiler/registration.cpp
- avoid deadlock in rocprofiler::registration::finalize()
* Update lib/rocprofiler/hsa/code_object.cpp
- suppress duplicate reporting of code-object/kernel-symbol load/unload
* Update leak sanitizer suppressions
- __new_exitfn (via stdlib/cxa_atexit.c leaks
|