* Fix agent node id + randomize offset id
- fixes the node_id value
- randomizes a constant offset for the id.handle values
- switch to using node ids in rocprofiler-sdk-tool library
- update tests related to agents
* Logical node id
- sequential node id values from 0 to (N-1) where N is the number of agents
* Handle hsa_queue_destroy after finalization
- fixes issue where hsa_queue_destroy(...) is invoked after rocprofiler-sdk has finalized
- hsa::get_queue_controller() returns pointer
- if queue controller is a null pointer, skip invoking QueueController::destroy_queue
* Update HIP/HSA/marker update_table logging
* Update rocprofv3 tests
- remove HSA_TOOLS_LIB env variable
- remove setting ROCPROFILER_LOG_LEVEL env variable
- add timeouts to tests which are missing them
* Disable thread sanitizer deadlock detection
* Update CI workflow
- rename vega20-ubuntu job to core-ci
- enable navi32 in core-ci and sanitizers
* Update run-ci.py
- set gcovr html medium and high threshold
* Update lib/rocprofiler-sdk/hsa/queue_controller.cpp
- remove this capture from enable/disable serialization
* Update lib/rocprofiler-sdk/hsa/{hsa_barrier,profile_serializer}.*
- hsa_barrier::set_barrier accepts const-ref to queue map
- profile_serializer::enable and profile_serializer::disable accept const-ref to queue map
* Logging for HIP/HSA/marker/profile_serializer
* Logging for HIP/HSA/marker/queue_controller
* Improve test_retired_correlation_ids asserts
* Fix tests/counter-collection/validate.py
- scale expected SQ_WAVES counter value based on warp size of GPU
* Tweak github comment for code coverage
* Remove gcovr html high/medium threshold args
* Fix tests/counter-collection/validate.py
- round before casting to int in test_counter_values
* operator bool for profile_serializer
- only wait on CV if profile_serializer is used
* Logging updates (profile_serializer + code_object)
* Update counter-collection validate.py
* QueueController does not wait on CV if finalizing/finalized
* Update CI workflow
- remove navi32 from core job
* Improve HIP/HSA/marker tracing get_functor/functor
- remove lambda wrapper around functor
* Update lib/rocprofiler-sdk/hsa/queue_controller.cpp
- do not acquire cvmutex lock during finalization
* Update lib/rocprofiler-sdk/hsa/hsa_barrier.*
- move ctor and dtor to implementation
- skip signal store screlease and destroy if already finalized
* Update CI workflow
- remove navi32 runners
* bwelton fixes for hangs
* CMake improvements + simplified demangle
- remove amd-comgr from common target (and thus removed from roctx DT_NEEDED)
---------
Co-authored-by: Benjamin Welton <bewelton@amd.com>
* Improve error checks related to context create/start/stop/is_valid
* Bump version to 0.2.1
* Track number of kernels associated with correlation id
- add atomic kernel counter variable to context::correlation_id
* Update lib/rocprofiler-sdk/hsa/queue.cpp
- apply the +/- kernel count
* Fix tracing context domain logic for operations
- logic error: domain enabled (all operations all implicitly enabled) + domain enabled for subset of operations resulted in only explicitly enabled operations being treated as enabled
- domain_context: split single bitset for operations in all domains into array of bitsets for each domain
* Update lib/common/mpl.hpp
- assert_false for static_asserts in if constexpr expressions
* Update lib/rocprofiler-sdk/tests/contexts.cpp
- Tests for validating logic regarding domain and operations for callback and buffer tracing
* Use small_vector for API iterate_args
- replace dim3 value arguments with rocprofiler_dim3_t
- dim3 has a non-trivial destructor
- common::mpl::unqualified_type
- common::stringified_argument_array_t<N> alias
- assert_public_data_type_properties()
- common::container::small_vector<T>::at function
- stringize returns small_vector<stringified_argument>
- stack allocated vector
- remove has_pc_sampling condition (HSA, HIP)
- this will be handled in queue interception
* Misc tweaks
* 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
* Update registration client search
- Search ROCP_TOOL_LIBRARIES before dlopen search
- Fatal error if ROCP_TOOL_LIBRARIES entry does not contain rocprofiler_configure symbol
- Use RTLD_DEFAULT and RTLD_NEXT to (potentially) find first two instances of rocprofiler_configure
- if no rocprofiler_configure found via RTLD_NEXT, do not do extensive search via link map
* _GNU_SOURCE instead of GNU_SOURCE
* Clang-tidy fix
* Fix HIP compiler iterate args
- `include/rocprofiler-sdk/hip/api_args.h`
- replace struct fields named "f" with "func"
- replace hip stream fields named "hStream" with "stream"
- `lib/rocprofiler-sdk/callback_tracing.cpp`
- iterate_args for HIP compiler table
- `lib/rocprofiler-sdk/registration.cpp`
- fix warning about roctx num_tables
- `lib/rocprofiler-sdk/hip/hip.def.cpp`
- replace struct fields named "f" with "func"
- replace hip stream fields named "hStream" with "stream"
- `lib/rocprofiler-sdk/{hip,hsa,marker}/utils.hpp`
- improve `stringize_impl`
- `lib/rocprofiler-sdk/hsa/code_object.cpp`
- remove stale commented out code
- `lib/rocprofiler-sdk/hsa/queue_controller.*`
- destory_queue -> destroy_queue
- `tests/tools/json-tool.cpp`
- improve parallelism in tool_tracing_callback
- serialize the marker api args
- only invoke rocprofiler_iterate_callback_tracing_kind_operation_args in exit phase
- `samples/counter_collection/CMakeLists.txt`
- reduce timeout on tests to 120 seconds
* Update lib/rocprofiler-sdk/hsa/utils.hpp
- disable dereference of double pointer in stringize_impl
* Update lib/common
- indirection_level in mpl.hpp
- stringize_arg.hpp
* Rework rocprofiler_iterate_callback_tracing_kind_operation_args
- provide more information in rocprofiler_callback_tracing_operation_args_cb_t
- support specifying the dereference level to account for output paramters
* C compatibility for public headers
- add tests/tools/c-tool.c
- builds a tool (which does nothing) with C language
- ensures that tool can be compiled in C
- add tests/c-tool/CMakeLists.txt
- ensures that tool library build from C is a valid tool
- rocprofiler_counter_info_v0_t is_derived is int instead of bool
- C does not have bool unless <stdbool.h> is included
- add `include/rocprofiler-sdk/hsa/api_trace_version.h
- handles providing HSA_*_TABLE_(MAJOR|STEP)_VERSION values if compiled from C
- cmake define in version.h.in for ROCPROFILER_HSA_*_TABLE_(MAJOR|STEP)_VERSION
- HSA table versions compiled with
- use rocprofiler_(hsa|hip|marker)_api_no_args struct to handle incompatibility b/t empty structs in C vs. C++ (size of 0 vs. size of 1)
- extern "C" in include/rocprofiler-sdk/{hsa,hip,marker}/api_args.h
- fixed spelling error: derrived -> derived
- scope YY_NO_INPUT compile definition to lib/rocprofiler-sdk/counters/parser/*
* Revert CDash dashboard
- .github/workflows/continuous_integration.yml
- apt-get update before apt-get install
- remove libgtest-dev
- actions-comment-pull-request: v2.4.3 -> v2.5.0
- .github/workflows/formatting.yml
- create-pull-request: v5 -> v6
- cmake/rocprofiler_options.cmake
- remove unused ROCPROFILER_DEBUG_TRACE and ROCPROFILER_LD_AQLPROFILE options
- samples/counter_collection/callback_client.cpp
- corr_id field renamed to correlation_id
- samples/counter_collection/client.cpp
- corr_id field renamed to correlation_id
- include/rocprofiler-sdk/fwd.h
- In rocprofiler_record_counter_t: rename corr_id field to correlation_id
- doxygen fixes
- lib/common/utility.*
- remove get_accurate_clock_id_impl
- timestamp_ns() defaults to CLOCK_BOOTTIME
- lib/rocprofiler-sdk/counters/core.cpp
- fix spelling mistake: extrenal -> external
- corr_id field renamed to correlation_id
- lib/rocprofiler-sdk-tool/tool.cpp
- fix destruction of static tool::output_file before finalization
- scripts/update-docs.sh
- define PROJECT_NAME
- tests/async-copy-tracing/validate.py
- init_time and fini_time checks
- hip_api_traces, marker_api_tracing
- tests/common/serialization.hpp
- fix save function for rocprofiler_record_counter_t following rename of corr_id to correlation_id
- tests/kernel-tracing/validate.py
- init_time and fini_time checks
- relax test_total_runtime range
- tests/rocprofv3/tracing/CMakeLists.txt
- remove -M from rocprofv3-test-systrace-execute
- exclude test_hsa_api_trace in rocprofv3-test-systrace-validate due to HIP API tracing
- tests/rocprofv3/tracing/validate.py
- update test_kernel_trace to accept mangled or demangled
- tests/tools/json-tool.cpp
- remove use of GLOG
- include init_time and fini_time
- write_json(...) function
* Add rocprofiler_query_counter_info function
Replaces rocprofiler_query_counter_name. Allows for
querying other types of info from counters (such as
description) and gives us some flexibility to add
return data in the near future (if we have to).
* source formatting (clang-format v11) (#453)
Co-authored-by: bwelton <bwelton@users.noreply.github.com>
* Updated version fetching
* source formatting (clang-format v11) (#509)
Co-authored-by: bwelton <bwelton@users.noreply.github.com>
* Merged
---------
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: bwelton <bwelton@users.noreply.github.com>
* Add support for AQL dimension changes
Adds support for returning dimensions from AQLProfile through rocprofiler
to tools. Includes a much larger expanded test suite that covers nearly
all files in counter collection.
Specific changes below:
samples/counter_collection/print_functional_counters: Modified to check
the validity of dimensions returned in comparison to the actual underlying
data obtained from a kernel execution.
rocprofiler-sdk/aql/helpers: adds function calls to support fetching
dimension information from AQLProfile.
rocprofiler-sdk/aql/packet_construct: modified to allow for events
to be exported to aid evaluate_ast in decoding the output buffer.
lib/rocprofiler-sdk/counters: Instance count now derived from dimension
sizes. rocprofiler_query_counter_dimensions now moved to a callback format
to improve usability.
rocprofiler-sdk/counters/core: Code migrations and exports of functions
for testing.
rocprofiler-sdk/counters/dimensions: Generates a dimension cache to be
used when querying dimension information for a counter id.
rocprofiler-sdk/counters/evaluate_ast: Modified to pass back correct
dimension information and to check/determine output dimensions for derived
counters.
rocprofiler-sdk/counters/id_decode: Modified to have a map between
dimension name -> dimension along with a conversion from the aql profile
id for a dimension (string) -> integer based id (happens only once during
init).
rocprofiler-sdk/hsa/queue: Modified to allow for making testing easier.
Specifically to allow Queue to now be mocked in unit tests for counter
collection.
* Merge with changes for serialization
* Added suggestions
* source formatting (clang-format v11) (#457)
Co-authored-by: bwelton <bwelton@users.noreply.github.com>
* Minor fix
* Test change
---------
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: bwelton <bwelton@users.noreply.github.com>
* Update lib/rocprofiler-sdk/hsa/queue.cpp
- switch using the kernel_pkt.kernel_dispatch.completion_signal instead of interrupt signal for getting the dispatch time
* Update tests/kernel-tracing/validate.py
- add verification of total runtime collected in test_timestamps
- the sum of the runtime of all the kernels in reproducible-runtime should be ~1 sec +/- 10%
* Remove include/rocprofiler-sdk/rocprofiler_plugin.h
* Update CI workflow
- update actions/cache@v3 -> v4
- actions/cache/save@v3 -> v4
- thollander/actions-comment-pull-request@v2 -> v2.4.3
* Update pytest.ini
- change default options to one that is more verbose
* Update tests/kernel-tracing/CMakeLists.txt
- skip test_total_runtime when Address or Thread Sanitizer enabled
- overhead skews the results
* Update tests/kernel-tracing/validate.py
- separate test_total_runtime test
* Update cmake/rocprofiler_config_packaging.cmake
- rocprofiler_set_package_depends which ensure CPACK_DEBIAN_PACKAGE_DEPENDS, CPACK_RPM_PACKAGE_REQUIRES, and component variants are properly formatted
* Update continuous_integration.yml
- Set ROCPROFILER_DEP_ROCMCORE to ON (test multiple dependencies)
- Set ROCPROFILER_BUILD_DOCS to ON (test building/packaging docs)
* Update docs/CMakeLists.txt
- remove '--' after cmake -E env
* Update include/rocprofiler-sdk
- buffer_tracing.h
- fix doxygen for rocprofiler_buffer_tracing_hip_api_record_t
- update doxygen for rocprofiler_buffer_tracing_marker_api_record_t
- remove unused marker_id field
- fwd.h
- Split ROCPROFILER_CALLBACK_TRACING_MARKER_API into ROCPROFILER_CALLBACK_TRACING_MARKER_{CORE,CONTROL,NAME}_API
- Split ROCPROFILER_BUFFER_TRACING_MARKER_API into ROCPROFILER_BUFFER_TRACING_MARKER_{CORE,CONTROL,NAME}_API
- split rocprofiler_runtime_library_t into rocprofiler_runtime_library_t and rocprofiler_intercept_table_t
- after split of ROCTx into 3 tables, specifying rocprofiler_at_internal_thread_create became confusing
* Update include/rocprofiler-sdk-roctx/api_trace.h
- Split into three tables: core, control, and name
- core: what it sounds like
- control: functions for controling the profiler
- name: functions for giving resources names
* Update lib/rocprofiler-sdk-roctx/roctx.cpp
- modifications following split into multiple tables
* Update lib/rocprofiler-sdk/marker/*
- modifications following split of ROCTx API into multiple intercept tables
* Update lib/rocprofiler-sdk/tests
- common.hpp
- add enums to get_callback_tracing_names() and get_buffer_tracing_names()
- intercept_table.cpp
- update test to use rocprofiler_intercept_table_t (and enums) instead of rocproifler_runtime_library_t
- update OR combos tested
- roctx.cpp
- updates following split of ROCTx API table into multiple tables
- use simplified specification of control API
* Update lib/rocprofiler-sdk
- buffer_tracing.cpp
- Updates for ROCPROFILER_BUFFER_TRACING_MARKER_{CORE,CONTROL,NAME}_API enum values
- callback_tracing.cpp
- Updates for ROCPROFILER_CALLBACK_TRACING_MARKER_{CORE,CONTROL,NAME}_API enum values
- intercept_table.hpp
- notify_runtime_api_registration -> notify_intercept_table_registration
- intercept_table.cpp
- updates for new rocprofiler_intercept_table_t enum and new ROCTx tables
- registration.cpp
- updates for new rocprofiler_intercept_table_t enum and new ROCTx tables
- updates for notify_runtime_api_registration -> notify_intercept_table_registration
* Update lib/rocprofiler-sdk-tool
- helper.cpp
- Updates for new enums in get_callback_id_names() and get_buffer_id_names()
- tool.cpp
- migrate to new enums for split ROCTx tables
- use simplified split for control table vs. core+name tables
* Update samples/{api_callback_tracing,intercept_table}
- intercept_table/client.cpp
- rocprofiler_runtime_library_t -> rocprofiler_intercept_table_t
- api_callback_tracing/client.cpp
- Updates for new enums in get_callback_id_names()
- use simplified split for control table vs. core+name tables
- migrate to new enums for split ROCTx tables
* Update tests
- rocprofv3/tracing/validate.py
- handle new marker domain names
- tools/json-tool.cpp
- Updates for new enums in get_callback_id_names() and get_buffer_id_names()
- use simplified split for control table vs. core+name tables
- migrate to new enums for split ROCTx tables
* Update tests/rocprofv3/tracing/CMakeLists.txt
- fix FAIL_REGULAR_EXPRESSION for rocprofv3-test-trace-execute
* Update lib/rocprofiler-sdk-tool/{output_file,tool}.*
- logging in output_file dtor
- support stdout/stderr
* Update lib/common/container/record_header_buffer.hpp
- reduce probability of is_empty() returning true while emplace is happening
* Update lib/rocprofiler-sdk-tool/tool.cpp
- logging for buffered_tracing_callback
- counter collection uses CSV encoder
* Update bin/rocprofv3
- remove -i flag from help menu
* Update include/rocprofiler-sdk/fwd.h
- add ROCPROFILER_STATUS_ERROR_FINALIZED error code
* Update lib/rocprofiler-sdk/rocprofiler.cpp
- status string for ROCPROFILER_STATUS_ERROR_FINALIZED
* Update lib/rocprofiler-sdk/buffer.cpp
- return error code if buffer flush invoked after finalized
- fatal error if task group destroyed
- error message if task runs after finalized
- improve join of task group
* Update lib/rocprofiler-sdk/counters/tests/evaluate_ast_tests.cpp
- Update lambdas to return reference due to strange -Warray-bounds and -Wstringop-overflow warnings with g++ (Ubuntu 13.1.0-8ubuntu1~20.04.2) 13.1.0
* Swap container to compute-rocm-dkms-component-staging-profiler
compute-rocm-dkms-component-staging-profiler contains the staging
branches for aqlprofile and others that are needed by the CI to function.
* python formatting (black) (#414)
Co-authored-by: jrmadsen <jrmadsen@users.noreply.github.com>
---------
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: jrmadsen <jrmadsen@users.noreply.github.com>
* Update include/rocprofiler-sdk/{counters,profile_config}.h
- use rocprofiler_agent_id_t instead of rocprofiler_agent_t
* Update samples
- use rocprofiler-sdk::rocprofiler-sdk instead of rocprofiler::rocprofiler in cmake
- api_callback_tracing sample roctxProfiler{Pause,Resume}
- api_callback_tracing sample uses ROCTx
- updates to use rocprofiler_agent_id_t
* Update run-ci.py
- exclude rocprofiler-sdk-tool from samples (no sample uses that code)
* Update lib/rocprofiler-sdk-tool/tool.cpp
- Update rocprofiler_iterate_agent_supported_counters to use agent ID
* Update lib/rocprofiler-sdk/counters/core.*
- profile_config has pointer to agent instead of copy
* Update lib/rocprofiler-sdk/agent.*
- provide get_agent(...) func via rocp agent id
* Update lib/rocprofiler-sdk/{buffer,callback}_tracing.cpp
- return ROCPROFILER_STATUS_ERROR_NOT_IMPLEMENTED for enums missing implementation
* Update lib/rocprofiler-sdk/counters.cpp
- update to use rocprofiler_agent_id_t instead of rocprofiler_agent_t
* Update lib/rocprofiler-sdk/profile_config.cpp
- update to use rocprofiler_agent_id_t instead of rocprofiler_agent_t
* Update source/docs
- requirements.txt + install reqs in cmake
* Bump version to 0.1.0
* Update samples/api_callback_tracing/CMakeLists.txt
- LD_LIBRARY_PATH for test
* Update test/rocprofv3/tracing/CMakeLists.txt
- reorder validation files so memory copy comes first
* Update lib/rocprofiler-sdk-tool/tool.cpp
- logging for flushing buffers
- variables for buffer_size and buffer_watermark
- increase the watermark to a full buffer
- use dedicated threads for each buffer
* Update lib/rocprofiler-sdk-tool/CMakeLists.txt
- test sets ROCPROF_LOG_LEVEL and ROCPROFILER_LOG_LEVEL to info
* Remove lib/rocprofiler-sdk-tool/trace_buffer.hpp
* Update lib/rocprofiler-sdk-tool/CMakeLists.txt
- drop log level to warning when leak sanitizer is enabled (produces small memory leak)
Gopesh Bhardwaj
Benjamin Welton
Jonathan R. Madsen
Vladimir Indic
Ammar ELWazir
SrirakshaNag