Allow events to be grouped by HIP stream ID (#274)

- Corelate memory_copy and kernel_dispatch events with their HIP stream_id and add stream_id as an annotation in Perfetto.
- By default, group memory_copy and kernel_dispatch events in Perfetto output by their stream_id.
- Add option, with the configuration setting ROCPROFSYS_ROCM_GROUP_BY_QUEUE, to group by HSA queue instead.

---------

Signed-off-by: David Galiffi <David.Galiffi@amd.com>
Co-authored-by: David Galiffi <David.Galiffi@amd.com>

[ROCm/rocprofiler-systems commit: 4b4a846b58]
This commit is contained in:
ajanicijamd
2025-07-23 21:28:26 -04:00
committed by GitHub
parent 0b57805e20
commit e2fc692ee0
11 changed files with 416 additions and 120 deletions
@@ -32,7 +32,7 @@ rocprof-sys-sample: `source/bin/rocprof-sys-sample <https://github.com/ROCm/rocp
* Adds ``librocprof-sys-dl.so`` to ``LD_PRELOAD``
* Is launched by using ``execvpe`` with ``<command> <command-args>`` and a modified environment
rocprof-sys-casual: `source/bin/rocprof-sys-causal <https://github.com/ROCm/rocprofiler-systems/tree/amd-mainline/source/bin/rocprof-sys-causal>`_
rocprof-sys-causal: `source/bin/rocprof-sys-causal <https://github.com/ROCm/rocprofiler-systems/tree/amd-mainline/source/bin/rocprof-sys-causal>`_
---------------------------------------------------------------------------------------------------------------------------------------------------
When there is exactly one causal profiling configuration variant (which enables debugging),