Bump water LLVM to 478e45fb94e541dfd3a53a23bbc8ed98337b8a77 #446
Conversation
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
Contributor
There was a problem hiding this comment.
Pull Request Overview
This PR bumps the water LLVM dependency to commit 478e45fb94e541dfd3a53a23bbc8ed98337b8a77 and updates the codebase to accommodate API changes in the new LLVM version.
Key Changes:
- Updated successor interface signatures from
RegionBranchPointtoRegionSuccessorparameters - Migrated
amdgpu.mfmasyntax from separate attribute format to compact dimension format (e.g.,32x32x16) - Updated test expectations to account for new
arith.andiconstant folding optimizations that eliminate redundant operations
Reviewed Changes
Copilot reviewed 5 out of 5 changed files in this pull request and generated no comments.
Show a summary per file
| File | Description |
|---|---|
| water/llvm-sha.txt | Updates LLVM commit SHA to 478e45fb94e541dfd3a53a23bbc8ed98337b8a77 |
| water/lib/Dialect/Wave/IR/WaveOps.cpp | Updates successor interface method signatures for IterateOp and YieldOp to use RegionSuccessor instead of RegionBranchPoint |
| water/test/Transforms/lowered_gemm_pipelined.mlir | Updates amdgpu.mfma test expectations to use new compact dimension syntax (32x32x16) |
| water/test/Dialect/Wave/lower-wave-to-mlir.mlir | Updates all amdgpu.mfma CHECK patterns across multiple MMA kinds to use new dimension syntax |
| water/test/Transforms/assert-in-bounds.mlir | Updates test expectations to reflect arith.andi constant folding that eliminates redundant AND operations with true |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Closed
ftynse
force-pushed
the
users/ftynse/bump-water-llvm
branch
from
e81fe0d to
bff0792
Compare
- increase version requirement for nanobind to reflect MLIR requirements for stubgen - work around the bug in MLIR installation not including the generated stubs by pre-generating them - update successor interfaces - update amdgpu.mfma syntax - account for arith.andi folder that prevents the operation from being created in the first place Signed-off-by: Alex Zinenko <[email protected]>
ftynse
force-pushed
the
users/ftynse/bump-water-llvm
branch
from
bff0792 to
9587a3d
Compare
Contributor
There was a problem hiding this comment.
Pull Request Overview
Copilot reviewed 7 out of 7 changed files in this pull request and generated no new comments.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Contributor
Author
tyb0807
approved these changes
Nov 18, 2025
martin-luecke
approved these changes
Nov 18, 2025
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.
for stubgen
stubs by pre-generating them
created in the first place