[aievec] to-llvm flow for i8xi8, i16xi16, bf16xbf16 elementwise multiplication #1139
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
jsetoain
reviewed
Mar 20, 2024
jamestcl-amd
changed the title
jsetoain
reviewed
Apr 3, 2024
Comment on lines
635
to
636
| std::stringstream ss; | ||
| ss << "llvm.aie." << getVectorTypeString(resultType) << ".undef"; |
There was a problem hiding this comment.
This also needs to be replaced with an XLLVM intrinsic. In another patch, but this definitely needs clean-up.
There was a problem hiding this comment.
Will clean up this in the next PR.
david-vc
reviewed
Apr 3, 2024
| } | ||
|
|
||
| LogicalResult | ||
| matchAndRewrite(aievec::MulElemOp op, OpAdaptor adaptor, |
There was a problem hiding this comment.
@jamestcl-amd , @jsetoain : This function is not doing any checking on the number of vector lanes or alternatively the total number of bits of the operands or result. Looking at
mlir-aie/lib/Dialect/AIEVec/IR/AIEVecOps.cpp
Line 903 in 11822b0
|
New updates before merging this PR:
|
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Outdated suggestions cannot be applied.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 PR includes the e2e tests for i8xi8, i16xi16, bf16xbf16 elementwise multiplication going through the to-llvm flow.
Changes:
FoldAIECastOpspattern inAIEVecToLLVMpass. This pattern folds all theaievec.castops that are introduced in the vector->aievec pass. Taking this shortcut, we do not need to conditionally introduceaievec.castops in the vector->aievec conversion patterns.aievec.castop, and remove theFoldAIECastOpspattern originally introduced in theAIEVecOptimizationspass.