10 Commits

Author SHA1 Message Date
Benjamin Welton 1517a398bf [rocprofiler-sdk] Buffer finalization fixes and HSA ABI 0x09 support (#2318)
* [rocprofiler-sdk] Fix buffer flush ordering and sanitizer CI improvements

Buffer Pool Design
------------------
Replace the fixed array-based double buffer with a dynamic pool design to
fix race conditions that caused "internal correlation id was retired
prematurely" errors.

The original design had a race where flush callbacks could be delivered
out-of-order: when buffer 0 fills and begins flushing, writes go to
buffer 1. If buffer 1 fills before buffer 0's flush completes, the
buffer index wraps back to 0 (which may still be flushing). Independent
flush tasks submitted to the thread pool can complete out of order.

The new pool design:
- Uses a std::deque of buffer instances that grows as needed
- Allocates buffers from the pool when the current buffer needs to flush
- Serializes flushes with a mutex to ensure FIFO callback ordering
- Returns buffers to the pool after flush completion
- Eliminates the race between buffer selection and write operations

New Unit Tests
--------------
- buffer_correlation_ordering.cpp: Tests that API records are always
  delivered before their corresponding retirement records
- buffer_ordering_stress.cpp: Stress tests buffer flush ordering under
  high contention with multiple threads rapidly filling buffers

HSA Tool Hooks
--------------
Added hsa_tool_hooks.cpp/hpp to register an HSA OnUnload callback that
waits for pending flush tasks before tool finalization, preventing
"retired prematurely" errors during HSA shutdown.

Sanitizer Improvements
----------------------
- LSAN: Set fast_unwind_on_malloc=1 to prevent deadlock in libgcc unwinder
- LSAN: Added suppressions for external tools (liblzma, liblsan, seq, strdup)
- TSAN: Added suppression for false positive on C++11 thread-safe static
  initialization in create_write_functor
- ASAN/UBSAN: Added patterns for known issues in HSA runtime, HIP, perfetto
- Disabled attachment tests for sanitizers due to library preloading issues

Other Fixes
-----------
- Thread-trace agent test: Use heap-allocated callback state
- Correlation ID: Refactored reference counting and finalization ordering

* [rocprofiler-sdk] Revert buffer pool design changes

Revert buffer.cpp and buffer.hpp to the original double-buffer
design from develop branch. The pool-based redesign introduced
concerns about:
- Signal safety (mutex vs atomic_flag)
- API changes (flush() return type)
- Complexity of the new design

This revert removes:
- Dynamic buffer pool with std::deque
- std::mutex/condition_variable synchronization
- buffer_correlation_ordering.cpp test
- buffer_ordering_stress.cpp test

The underlying buffer flush ordering issue will need to be
addressed with a different approach that preserves the original
API and synchronization characteristics.

* [rocprofiler-sdk] Consistent fini_status checks to prevent correlation ID creation during finalization

- Revert TOCTOU CAS loop change in sub_ref_count() - not needed with consistent checks
- Add fini_status check in correlation_tracing_service::construct() with ROCP_CI_LOG warning
- Add nullptr checks at all construct() call sites (queue.cpp, async_copy.cpp, memory_allocation.cpp)
- Change all 'get_fini_status() > 0' to '!= 0' for consistent behavior:
  - hsa/queue.cpp (lines 105, 210)
  - hsa/async_copy.cpp (line 344)
  - hsa/hsa_barrier.cpp (line 43)
  - buffer.cpp (lines 107, 138, 185)

This ensures no correlation IDs are created once finalization starts (fini_status != 0),
preventing races between finalization and ongoing tracing operations.

* [rocprofiler-sdk] Replace arrival-order checks with timestamp-based temporal validation

Buffer records are not guaranteed to arrive in any specific order. Tests and
samples should use timestamps for temporal ordering validation instead.

Changes:
- samples/external_correlation_id_request: Replace 'retired prematurely' arrival
  order check with timestamp-based validation that retirement timestamp >=
  max(end_timestamps) for records with the same correlation ID
- tests/external_correlation.cpp: Remove EXPECT_GT(corr_id, last_corr_id) check
- tests/registration.cpp: Remove EXPECT_GT(corr_id, last_corr_id) check
- tests/roctx.cpp: Remove EXPECT_GT(corr_id, last_corr_id) check

Correlation IDs are not guaranteed to be monotonically increasing when records
are sorted by timestamp. Temporal ordering should be validated using the
timestamp fields in each record.

* [rocprofiler-sdk] Revert external/CMakeLists.txt SYSTEM keyword removal

Restore the SYSTEM keyword to target_include_directories for
rocprofiler-sdk-fmt to match develop branch.

* [rccl] Remove orphaned rocSHMEM gitlink

Remove orphaned submodule reference that was introduced during a merge
but never had a corresponding .gitmodules entry, causing CI failures
with "fatal: no submodule mapping found in .gitmodules".

* [rocprofiler-sdk] Add HSA ABI version 0x09 support

Add ABI checks for HSA_AMD_EXT_API_TABLE_STEP_VERSION 0x09 which
introduces hsa_amd_counted_queue_acquire and hsa_amd_counted_queue_release
functions (added in rocr-runtime SWDEV-561708).

* [rocprofiler-sdk] Handle finalized status gracefully in buffer flush operations

This commit consolidates fixes for handling the finalization status during
buffer flush operations across the SDK.

Changes:
- Tool and samples: Handle ROCPROFILER_STATUS_ERROR_FINALIZED gracefully
  when flushing buffers, as this indicates buffers were already flushed
  during finalization (not an error condition)
- HSA handlers (queue.cpp, async_copy.cpp, hsa_barrier.cpp): Use > 0 check
  for fini_status to allow operations during finalization process
- buffer.cpp: Revert fini_status checks to use > 0 for consistency
- correlation_id.cpp: Add fini_status > 0 check with ROCP_TRACE logging
  to prevent correlation ID creation after finalization starts

Files modified:
- source/lib/rocprofiler-sdk-tool/tool.cpp
- tests/tools/json-tool.cpp
- source/lib/rocprofiler-sdk/tests/registration.cpp
- source/lib/rocprofiler-sdk/tests/roctx.cpp
- samples/api_buffered_tracing/client.cpp
- samples/counter_collection/buffered_client.cpp
- samples/counter_collection/device_counting_async_client.cpp
- samples/external_correlation_id_request/client.cpp
- samples/pc_sampling/client.cpp
- source/lib/rocprofiler-sdk/buffer.cpp
- source/lib/rocprofiler-sdk/context/correlation_id.cpp
- source/lib/rocprofiler-sdk/hsa/queue.cpp
- source/lib/rocprofiler-sdk/hsa/async_copy.cpp
- source/lib/rocprofiler-sdk/hsa/hsa_barrier.cpp

* [rocprofiler-sdk] Remove hsa_tool_hooks and simplify buffer flush handling

Remove the hsa_tool_hooks infrastructure and simplify buffer flush calls
in samples and tools. The ERROR_FINALIZED handling was overly complex
and the hsa_tool_hooks OnUnload synchronization is no longer needed.

Changes:
- Remove hsa_tool_hooks.cpp/hpp and related registration.cpp code
- Simplify buffer flush calls in samples to use direct ROCPROFILER_CALL
- Simplify buffer flush in tool.cpp and json-tool.cpp
- Remove ERROR_FINALIZED special handling from test files

Co-Authored-By: Claude <noreply@anthropic.com>

* [rocprofiler-sdk] Fix output_stream move semantics to null source pointers

The default move constructor and move assignment operator for
output_stream did not null out the source's pointers after the move.
This caused double-close when the moved-from temporary was destroyed,
leading to use-after-free crashes (SIGSEGV in std::ostream::sentry).

Co-Authored-By: Claude <noreply@anthropic.com>

* [rocprofiler-sdk] Improve Perfetto trace writer and sanitizer configuration

- generatePerfetto.cpp: Move output_stream into shared_state to prevent
  use-after-free race conditions during Perfetto callback execution
- run-ci.py: Simplify and consolidate sanitizer environment variable
  configuration for better maintainability

Co-Authored-By: Claude <noreply@anthropic.com>

* [rocprofiler-sdk] Revert run-ci.py changes that broke sanitizer suppressions

The previous changes removed MEMCHECK_SANITIZER_OPTIONS which is required
for CTest to properly pass suppression files to the sanitizers during
memcheck runs.

Co-Authored-By: Claude <noreply@anthropic.com>

* Revert "[rccl] Remove orphaned rocSHMEM gitlink"

This reverts commit 1ad21003941355658fff8114fa27768f11a948f7.

* [rocprofiler-sdk] Revert registration.cpp changes

Revert changes to registration.cpp to match develop branch.

Co-Authored-By: Claude <noreply@anthropic.com>

* [rocprofiler-sdk] Remove suppression file content printing from run-ci.py

Co-Authored-By: Claude <noreply@anthropic.com>

* Fix output_stream move ctor/assignment operator

* Fix erroneous revert of registration.cpp

* Fix handling of fini status in correlation ID construction

* [rocprofiler-sdk] Fix OMPT segfault during finalization

Add nullptr checks in OMPT tracing code to handle the case where
correlation_tracing_service::construct() returns nullptr during
finalization. This fixes segfaults in openmp-target-sample and
tests.integration.execute.openmp-tools.

The correlation ID construction now returns nullptr when fini_status > 0,
but the OMPT callbacks were not checking for this, causing crashes when
dereferencing the null pointer during OpenMP runtime shutdown.

Changes:
- event_common(): Return nullptr early if correlation ID is null
- event(): Check for nullptr before calling sub_ref_count()
- ompt_task_create_callback(): Return early if correlation ID is null
- ompt_task_schedule_callback(): Return early if correlation ID is null

* [rocprofiler-sdk] Fix HSA API tracing segfault during finalization

Add nullptr check in hsa_api_impl::functor after correlation ID
construction. During finalization, correlation_service::construct()
returns nullptr, and without this check the code would dereference
the null pointer when accessing corr_id->internal.

This fixes the SEGV at address 0x000000000008 (null + 8 byte offset)
that occurs when HSA async event threads call hsa_signal_destroy
during runtime shutdown after finalization has started.

---------

Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
2026-01-27 13:27:54 -05:00
Jonathan R. Madsen a2288eb50b [rocprofiler-sdk] Install unit tests and helper functions for integration tests (#921)
* [rocprofiler-sdk] Install unit tests and helper functions for integration tests

* Fix rocprofiler-sdk-tests-target export

* Fix handling of cmake policy CMP0174

* Remove -vv from new pytest.ini files

* add unit tests and integration tests.

* add path to ci workflow.

* misc. fixes.

* pc sampling tests.

* bug fixes.

* pc sampling tests fix.

* misc.

* Update CMakeLists.txt

* Update rocprofiler_config_install_tests.cmake, correct license name

* fix units tests install issues.

* fix counters_def file path.

* fix bug, arg shifting.

* vendor pytest-cmake.

* cmake config fix. missing endfunction()

* disable tests, 1.rocprofv3-trace-hip-libs. 2.kernel-tracing. 3.external_correlation 4.rocpd.

* disable buffered-tracing test and remove pytest-cmake from requirements.txt.

* disable hip-graph-tracing test.

* fix building standalone tests to load rocprofiler-sdk cmake package first and then find rocprofiler_sdk_pytest module.

* addressed comments: 1.add local bin path to code cov workflow. 2.add to cmake prefix path local bin. 3.use ROCPROFILER_MEMCHECK_PRELOAD_ENV_VALUE 4.misc. fix

* enabled back tests api_buffered, external_correlation_id, hip-graph, kernel-tracing, rocpd, tracing-hip-in-libraries. and misc fixes(formating, extra fixtures for agent-index tests.)

* cpack to use llvm bin for .hsaco debug symbols.

* psdb tests fixes.

* EOL.

* misc. fixes and Disable api_buffered_tracing, external_correlation_id, hip-graph-tracing, kernel-tracing, rocpd, summary, tracing-hip-libraries, tracing-plus-counter-collection.

* fix incorrect cmakelists file.

* strip smallkernel.bin

* format.

* revert disabled tests commit.

* misc. fix in counter tests.

* misc.

* search codeobj unit test assets in curr bin and install bin.

* refactor newly added rocpd tests.

* modify tests for newly added hip-host-tracing.

* add LD LIB path to units, psdb is failing due to libs not being found.

---------

Co-authored-by: Venkateshwar Reddy Kandula <venkateshwar.kandula1306@gmail.com>
Co-authored-by: Venkateshwar Reddy Kandula <Venkateshwarreddy.Kandula@amd.com>
Co-authored-by: JeniferC99 <150404595+JeniferC99@users.noreply.github.com>
2025-11-21 08:06:56 -06:00
Indic, Vladimir fe6cfc9cc8 PCS test: cast agent name to str (#546)
* PCS test: cast agent name to str

[ROCm/rocprofiler-sdk commit: 2d8936362e]
2025-07-29 12:11:15 -07:00
Madsen, Jonathan fb51f0e5d4 [CI] Disable other unstable tests (#491)
Disable other unstable tests

- validation test_validate_counter_collection_pmc1 for conversion script
- increase timeout for tests/rocprofv3/pc-sampling execution phase

[ROCm/rocprofiler-sdk commit: f0fe04b95e]
2025-06-30 15:53:30 -05:00
Madsen, Jonathan 839c07c4aa [CI] Testing stability (#486)
* [CI] Testing Stability

- CMake option ROCPROFILER_DISABLE_UNSTABLE_CTESTS
  - used for tests which periodically fail around 1 out of every 10 runs
  - set to ON while instability remains, this needs to set to OFF in ROCm 7.1 or, ideally, ROCm 7.0.1
- Use FIXTURES_SETUP and FIXTURES_REQUIRED for some tests
- replace "threw an exception" with "${ROCPROFILER_DEFAULT_FAIL_REGEX}" for misc FAIL_REGULAR_EXPRESSIONS

* Remove contents of all EXCLUDE_{TESTS,LABEL}_REGEX from CI workflow

* Disable patch git step in code-coverage run

* Tweak spin time of reproducible runtime

* Removed patch git step in code-coverage run

* Update ROCPROFILER_DEFAULT_FAIL_REGEX

* Mark test-counter-collection tests as unstable

- add fixtures setup/required

* Remove ATTACHED_FILES_ON_FAIL

- CDash doesn't store enable downloading these properly anyway

* Relax collection-period fuzzing window

* Disable unstable collection-period test

- too unstable

* formatting

* Disable unstable device_counting_service_test.async_counters

* Suppress perfetto internal data race errors

* Switch code-coverage CI jobs to mi300 runner

* Timeout increases

* rocprofv3-test-rocpd updates

- add fixtures
- switch executable
- redefine input/output paths

* Revert code-coverage job to mi300a runner

* Update rocprofv3-test-rocpd-execute-multiproc

- reduce problem size

* disable multiproc rocpd

* Split code-coverage into separate workflow

- network issues cause this job to fail frequently
- when in a separate workflow, it can be restarted easily

* Fixtures for rocprofv3-test-trace-hip-in-libraries

* Disable unstable device_counting_service_test.sync_counters

* Potential fix for code scanning alert no. 171: Workflow does not contain permissions

Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>

* Switch code-coverage to run on rocprof-azure

- mi300a EMU runner set is unstable (network issues)

* tests/rocprofv3/pc-sampling SKIP_REGULAR_EXPRESSION

* Update rocprofv3-test-list-avail-trace-execute

- reduce log level and increase timeout

* rocprofv3: Prevent recursive call to rocprofv3_error_signal_handler + log chaining

* rocprofv3: Use ROCP_ERROR + std::exit instead of ROCP_FATAL

- should help with SKIP_REGULAR_EXPRESSION

---------

Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>

[ROCm/rocprofiler-sdk commit: 640ca55ac0]
2025-06-30 15:07:37 -05:00
Indic, Vladimir e5097d6a36 [ROCm 7.0] [PC sampling] Disable PC sampling tests if the GFX arch doesn't support it (#436)
Disable PC sampling tests if the GFX arch doesn't support it

[ROCm/rocprofiler-sdk commit: a24f486732]
2025-06-06 18:47:47 +02:00
Indic, Vladimir 7dc9c6c391 [ROCm 7.0] [PC Sampling] [Tests] Using yaml input directory (#435)
Using yaml input directory

[ROCm/rocprofiler-sdk commit: 0dea7bc182]
2025-06-05 10:22:13 -07:00
Madsen, Jonathan 9f7703f918 Build system (libdw), correlation ID, and shebang fixes (#354)
* Fix compilation for output library

- link to targets for ATT (amd-comgr, dw, elf)

* Relax correlation ID retirement log failures

- only fail for correlation ID retirement underflow when building in CI mode

* Fix shebang for several files

- license was inserted before shebang in several places

* Update code coverage exclude folders for samples

* Tweak to agent tests

- test to make sure hsa agent is not the old value instead of testing that it is the new value

* Fix libdw include/link

---------

Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>

[ROCm/rocprofiler-sdk commit: 3580478426]
2025-04-27 20:16:18 -05:00
Trowbridge, Ian 5a5fe7f4bf Copyright Compliance (#333)
* Added copyright information to requested files

* Formatting

* Fix bad function name error

[ROCm/rocprofiler-sdk commit: 4fbcfd142c]
2025-04-14 13:07:32 -05:00
Indic, Vladimir 0ca07105a3 [SDK][rocprofv3] MI300 Stochastic PC sampling (#92)
* MI300 Stochastic PC sampling SDK API implementation

* ROCProfV3: Stochastic PC sampling Support (#94)

* ROCProfV3: MI300 Stochastic PC sampling initial draft

* ROCProfV3: Initial Stochastic PC sampling Tests (#95)

ROCProfV3: Initial Stochastic PC sampling tests

* Update rocprofiler_pc_sampling_record_stochastic_v0_t

- update doxygen docs for members
- replace rocprofiler_correlation_id_t with rocprofiler_async_correlation_id_t

* Relax the check in JSON tests

* drain PC sampling buffer during finalize_rocprofv3

* Increase timeout for "Test Install Build" step

- 10 minutes -> 20 minutes
- "Test Installed Packages" has 20 minutes so "Test Install Build" should also

---------

Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>

[ROCm/rocprofiler-sdk commit: 49ce79a5b5]
2025-03-21 14:40:45 -05:00