- 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>
[ROCm/rocprofiler-systems commit: 4e5029221b]
- 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
[ROCm/rocprofiler-compute commit: a95a45d69a]
* 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.
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