[Codegen] Fix uninitialized tensorCoreType causing flaky vector_to_gpu tests.#23701
Merged
[Codegen] Fix uninitialized tensorCoreType causing flaky vector_to_gpu tests.#23701
Conversation
…u tests. Both LLVMGPUVectorToGPUPass and LLVMGPUTensorCoreVectorizationPass had an uninitialized GPUTensorCoreType member. When constructed via the inherited TableGen base class constructor (pipeline string invocation), the member was never set — reading it was undefined behavior. When stack garbage happened to equal MMA_SYNC (1), the passes took a wrong code path (e.g. running populateFoldMemRefAliasOpPatterns which folded subviews back into transfer_reads), producing IR that didn't match CHECK lines. Initialize both to WMMA, matching the existing explicit constructor default. Co-Authored-By: Claude <noreply@anthropic.com>
benvanik
requested review from
Groverkss,
Max191,
krzysz00,
kuhar,
nirvedhmeshram and
qedawkins
as code owners
benvanik
added
bug 🐞
kuhar
approved these changes
Mar 9, 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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Both LLVMGPUVectorToGPUPass and LLVMGPUTensorCoreVectorizationPass had an uninitialized GPUTensorCoreType member. When constructed via the inherited TableGen base class constructor (pipeline string invocation), the member was never set — reading it was undefined behavior. When stack garbage happened to equal MMA_SYNC (1), the passes took a wrong code path (e.g. running populateFoldMemRefAliasOpPatterns which folded subviews back into transfer_reads), producing IR that didn't match CHECK lines.
Initialize both to WMMA, matching the existing explicit constructor default.