[Codegen] Remove memref optimizations from OptimizeTensorInsertExtractSlices #18732
+25
−23
Conversation
This file contains 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
Groverkss
requested review from
antiagainst,
MaheshRavishankar,
kuhar,
qedawkins and
hanhanW
as code owners
Groverkss
commented
Oct 9, 2024
Comment on lines
-243
to
+246
| linalg::hoistRedundantVectorTransfers(cast<func::FuncOp>(funcOp)); | ||
| IRRewriter rewriter(funcOp->getContext()); | ||
|
|
||
| funcOp.walk([&](scf::ForOp forOp) { moveLoopInvariantCode(forOp); }); | ||
| LDBG("after hoisting loop invariant code\n" << funcOp); |
There was a problem hiding this comment.
linalg::hoistRedundantVectorTransfers is a combination of LICM + memref optimizations. We only run LICM to keep the previous behavior for tensor code.
Groverkss
commented
Oct 9, 2024
Comment on lines
-105
to
+107
| // CHECK: vector.transfer_read {{.+}} vector<1x8xf16> | ||
| // CHECK: vector.transfer_read {{.+}} vector<8xf16> | ||
| // CHECK: vector.transfer_write | ||
| // CHECK: vector.transfer_read {{.+}} vector<1x8xf16> | ||
| // CHECK: vector.transfer_read {{.+}} vector<8xf16> |
There was a problem hiding this comment.
test changes caused by switching pass to optimize-vector-transfer, which also drops vector unit dims.
qedawkins
approved these changes
Oct 9, 2024
| @@ -549,7 +549,9 @@ void addGPUMatmulSimtPassPipeline(OpPassManager &funcPassManager, | |||
| // still rely on buffer level transformations for transfer ops hoisting and | |||
| // store to load forwarding. This relies on shacky alias analysis and we need | |||
| // to move this to tensor level once we have better abstractions. | |||
| funcPassManager.addPass(createOptimizeTensorInsertExtractSlicesPass()); | |||
| // TODO: We should be to start hoisting out accumulator load/store out | |||
| // after https://github.com/llvm/llvm-project/pull/111533. | |||
There was a problem hiding this comment.
reminder to drop before landing
There was a problem hiding this comment.
oh good catch, thanks!
hanhanW
approved these changes
Oct 9, 2024
There was a problem hiding this comment.
Okay, I have better understanding now. Thanks for the good writeup in llvm/llvm-project#111533 (comment)!
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.
This pass is meant to be run on tensor code, but has slowly accumulated unrelated optimizations. This patch makes this pass run only tensor optimizations.
No test additions because this pass only has tensor tests.
Depends on #18731