PR #46486: [xla:gpu] Add a flag to configure the level of details in runtime trace annotation - #3611
Merged
Merged
Conversation
copybara-service
Bot
force-pushed
the
test_957034022
branch
from
August 3, 2026 06:40
c710e1d to
a5be97f
Compare
…runtime trace annotation Imported from GitHub PR openxla/xla#46486 This change adds runtime-configurable GPU trace annotation detail, with level 1 XLA emits a lot more details (at the cost of some overhead + larger traces) that allow to better analyze e2e performance. - Add `--xla_gpu_trace_annotation_level`: - Level 0 emits compact instruction names and basic structured payloads. - Level 1 adds detailed HLO and collective metadata. - Keep NVTX names compact while emitting structured Basic, Detailed, and Collective payloads. - Emit full parseable XProf annotation names containing operation metadata, source location, shape, replica groups, collective flags, and frontend attributes. - Allow ScopedAnnotation to use separate generators for the annotation stack and profiler range stack. - Rename the runtime API from kernel to instruction terminology, retaining GetKernelAnnotation as a deprecated compatibility shim. Copybara import of the project: -- 6d2f18de8ea26d400b4438591dc336d48e553957 by Eugene Zhulenev <ezhulenev@openxla.org>: [xla:gpu] Add a flag to configure the level of details in runtime trace annotation Merging this change closes #46486 PiperOrigin-RevId: 958262733
copybara-service
Bot
force-pushed
the
test_957034022
branch
from
August 3, 2026 09:45
a5be97f to
8449c3e
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
PR #46486: [xla:gpu] Add a flag to configure the level of details in runtime trace annotation
Imported from GitHub PR openxla/xla#46486
This change adds runtime-configurable GPU trace annotation detail, with level 1 XLA emits a lot more details (at the cost of some overhead + larger traces) that allow to better analyze e2e performance.
--xla_gpu_trace_annotation_level:Copybara import of the project:
--
6d2f18de8ea26d400b4438591dc336d48e553957 by Eugene Zhulenev ezhulenev@openxla.org:
[xla:gpu] Add a flag to configure the level of details in runtime trace annotation
Merging this change closes #46486
FUTURE_COPYBARA_INTEGRATE_REVIEW=openxla/xla#46486 from ezhulenev:trace-annotation-level 6d2f18de8ea26d400b4438591dc336d48e553957