[DNR][ConSan] Restrict tensor-core completion visibility - #11190
Draft
jeffniu-openai wants to merge 1 commit into
Draft
[DNR][ConSan] Restrict tensor-core completion visibility#11190jeffniu-openai wants to merge 1 commit into
jeffniu-openai wants to merge 1 commit into
Conversation
jeffniu-openai
force-pushed
the
jeffniu/consan-tensor-core-completion
branch
from
August 6, 2026 03:04
893fdd5 to
90c92a3
Compare
jeffniu-openai
changed the base branch from
jeffniu/consan-async-shared-store
to
main
August 6, 2026 03:04
lezcano
reviewed
Aug 6, 2026
Comment on lines
+1188
to
+1189
| cta = ttgl.inline_asm_elementwise("mov.u32 $0, %cluster_ctarank;", "=r", [], dtype=ttgl.int32, is_pure=True, | ||
| pack=1) |
Contributor
There was a problem hiding this comment.
we should document somewhere that this type of code is not officially supported in gluon, so that codex stops finding these "bugs"
Collaborator
Author
There was a problem hiding this comment.
this is a real bug. the reproducer just happens to be written this way
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 description written by Codex
Restrict tensor-core completion to qualifying tensor-core effects, while preserving prerequisite writes for tensor-core-read buffers. This prevents remote mbarriers from publishing unrelated distributed-shared-memory writes.
Validated with the complete ConSan suite (414 passed, 70 skipped), NVIDIA/AMD sanitizer lit tests, and targeted Gluon regressions.