* [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>
- Create a local copy for ROCm/rccl-tests for our examples.
- Update argument parsing to no longer use getopt_long.
- Workaround for Dyninst instrumentation.
---------
Co-authored-by: David Galiffi <David.Galiffi@amd.com>
This commit introduces a new SetTrapHandler API to the driver interface
- Implemented SetTrapHandler in KfdDriver to set trap handlers using
hsaKmtSetTrapHandler.
- Added a stub implementation of SetTrapHandler in XdnaDriver that returns
HSA_STATUS_ERROR.
- Updated the driver interface in driver.h to include the new SetTrapHandler
method.
- Modified GpuAgent to use driver().SetTrapHandler instead of directly calling
hsaKmtSetTrapHandler.
Signed-off-by: Honglei Huang <Honglei1.Huang@amd.com>
* Modified perfetto output for HIP stream display
* Moved stream_map file location and changed perfetto output names Private_Segment_Size and Group_Segment_Size to Scratch_Size and LDS_Block_Size respectively
* Used const_cast to remove const modifier on void*
* Reverted stream_map changes, now using tool_metadata map to track mapping between stream ptrs and stream IDs
* Removed buffer tracing args in perfetto, added tool_...hip buffer record struct that stores the HIP stream ID for display purposes
* Updated rocpd perfetto.cpp to reflect stream changes. Still need to add vgpr values and stream ID for HIP API
* Changes pass-by const reference to pass-by const value
hsa-rocr was missing in the dependency list of aqlprofile package
Updated dependency for ASAN and aqlprofile test package as well
Co-authored-by: raramakr_amdeng <raramakr@amd.com>
* Add custom rocprofiler-sdk counter definitions file for MI 100
* Update CHANGELOG to mention that accumulation counters will not be
collected when profiling on MI 100 using rocprofiler-sdk/rocprofv3
* Migrate accum_counters.yaml to code
Replace direct hsakmt API calls with calls through the driver abstraction layer
in queue management related functions. This includes:
- CreateQueue/DestroyQueue operations
- Queue update and GWS allocation
- CU masking configuration
Also update the corresponding error status types from HSAKMT_STATUS to
hsa_status_t and adjust error handling accordingly.
Signed-off-by: Honglei Huang <Honglei1.Huang@amd.com>
Replace direct libhsakmt calls with driver interface methods
in GpuAgent initialization:
- Replace hsaKmtGetNodeMemoryProperties with driver().GetMemoryProperties
- Replace hsaKmtGetNodeCacheProperties with driver().GetCacheProperties
Signed-off-by: Honglei Huang <Honglei1.Huang@amd.com>
The agent properties variable `agent_props` was declared but never used
in the `InitScratchSRD()` function. Which casued compile warning:
runtime/core/runtime/amd_aql_queue.cpp:1880:15: warning:
unused variable ‘agent_props’ [-Wunused-variable]
1880 | const auto& agent_props = agent_->properties();
No functional changes, purely a code cleanup commit.
Change when Roofline PDFs are generated- during general profiling and --roof-only profiling (skip only when --no-roof option is present)
---------
Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>
Madsen, Jonathan
Chris Freehill
Elwazir, Ammar
xuchen-amd
Galantsev, Dmitrii
jamessiddeley-amd
vedithal-amd
Pranjal Swarup
Honglei Huang
Bhardwaj, Gopesh
Fei Zheng
Kandula, Venkateshwar reddy
Trowbridge, Ian
Ramakrishnan, Ranjith
Kuricheti, Mythreya
Tony Gutierrez
Ma, Bing
anujshuk-amd
David Galiffi
Yiannis Papadopoulos
dependabot[bot]
Kian Cossettini
Kunal Malviya
Verma, Saurabh
cfallows-amd