Add partial-width tile shape tests for hint-exercising paths in CCL and X collectives#436
Merged
mawad-amd merged 2 commits intomuhaawad/hintsfrom Mar 7, 2026
Merged
Conversation
Co-authored-by: mawad-amd <112003944+mawad-amd@users.noreply.github.com>
Copilot
AI
changed the title
[WIP] Use hints in CCL and X implementations
Add partial-width tile shape tests for hint-exercising paths in CCL and X collectives
Mar 7, 2026
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 #432 added
hint=parameters toiris.store()calls across CCL (all_gather,all_reduce,all_to_all) andiris/x/all_reduce.py. The hint path was only tested forx.all_gather(PR #435). This PR extends coverage to the remaining ops.Changes
tests/x/test_all_reduce.py: Added two new shapes to the existing parametrize list:(128, 128, 64, 32)— BLOCK_N < N/world_size, exercises multi-block partial-width path(256, 128, 64, 16)— BLOCK_N=16, exercises 16-bit vectorization pathtests/ccl/test_all_gather.py: Upgraded(M, N)parametrize to(M, N, block_size_m, block_size_n)in bothtest_all_gatherandtest_all_gather_partitioned; block sizes forwarded viaConfig. Added the same two partial-width shapes.tests/ccl/test_all_reduce.py: Same restructure — block size params passed throughConfig(all_reduce_variant=..., block_size_m=..., block_size_n=...).tests/ccl/test_all_to_all.py: Same restructure — block sizes forwarded viaConfig.The two new shapes added to each file:
💬 We'd love your input! Share your thoughts on Copilot coding agent in our 2 minute survey.