fix(runtime): enable explicit FFTS synchronization on a2a3sim - #2733
Open
Little-oil wants to merge 1 commit into
Open
Little-oil wants to merge 1 commit into
Little-oil wants to merge 1 commit into
Conversation
Advance the runtime gitlink from 39ce891d to 72a8e627, including nine upstream runtime commits and the explicit A2/A3 FFTS simulator fix. Generated sync_set/sync_wait kernels compile and execute with counted cross-core events shared by separately loaded AIC and AIV libraries. Keep PTOAS v0.60 and the runtime-owned PTO ISA pin at 5a4f74cb. No PyPTO Python or C++ source changes are required. Validate 19 runtime-selection, ISA-resolution, and pinned-runtime ABI checks with no skips. The patched runtime also passes dspark CSA, HCA, SWA, allgather, and indexer simulator goldens, plus CSA TP4 16x256 with all seven output/state checks at the original tolerances.
|
Warning Review limit reachedNext included review available in 27 minutes. View limit detailsLimit details: You’ve used all 2 included reviews currently available. You've used all free OSS reviews for now. Wait for the free limit to reset to keep reviewing this public repository. Review configuration: ⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Advanced Run ID: 📒 Files selected for processing (1)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Little-oil
pushed a commit
to Little-oil/pypto-lib
that referenced
this pull request
Sep 10, 2026
- Bypass query scoring and sorting when the ratio-4 cache fits Top-K, retaining causal visibility, cache updates and the long-cache path. - Read CSA gather payloads directly into typed consumers before epoch retirement, removing full packed buffers and separate unpack waves. - Temporarily pin simulator CI to the FFTS-capable PyPTO dependency from hw-native-sys/pypto#2733 and hw-native-sys/simpler#2186; remove the pin when PyPTO main includes the fix. TP4 CSA at 16x256 on a2a3: average minimum-rank median latency falls 1016.850 -> 880.275 us (13.43%). Average minimum-rank mean latency falls 1027.507 -> 923.736 us (10.10%). Use PYPTO_BENCH=1, swimlane0, 100 timed rounds and 5 warmups, with all samples retained across AB/BA runs.
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.
Advance the runtime gitlink from 39ce891d to 72a8e627 so explicit FFTS
sync_set/sync_waitkernels compile and execute on A2/A3 CPU simulation. This incorporates current runtime main and the counted-event simulator fix in hw-native-sys/simpler#2186. PTOAS stays at v0.60 and the runtime-owned PTO ISA pin stays at 5a4f74cb; PyPTO source is unchanged.The update includes nine upstream runtime commits plus the FFTS fix. Merge after simpler #2186; update the gitlink if the merged runtime commit receives a different SHA.
Validation:
This resolves the simulator dependency failure seen in hw-native-sys/pypto-lib#1195. Validation here uses CPU simulation; native performance was not remeasured.