[VectorDistribution] Reuse intrinsic layout in chained gemm #18505
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
force-pushed
the
users/Groverkss/reuse-attention-intrinsic
branch
from
67a72fa
to
d8f7aad
Compare
Groverkss
requested review from
MaheshRavishankar,
qedawkins,
kuhar and
antiagainst
as code owners
kuhar
reviewed
Sep 19, 2024
compiler/src/iree/compiler/Codegen/Common/GPU/GPUNestedLayoutDistributionPatterns.cpp
Outdated
Show resolved
Hide resolved
compiler/src/iree/compiler/Codegen/Common/GPU/GPUNestedLayoutDistributionPatterns.cpp
Outdated
Show resolved
Hide resolved
compiler/src/iree/compiler/Codegen/LLVMGPU/LLVMGPUConfigureTensorLayouts.cpp
Show resolved
Hide resolved
compiler/src/iree/compiler/Codegen/LLVMGPU/test/ROCDL/pipeline_vector_distribute_gfx940.mlir
Outdated
Show resolved
Hide resolved
kuhar
approved these changes
Sep 20, 2024
MaheshRavishankar
approved these changes
Sep 20, 2024
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Outdated suggestions cannot be applied.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 patch teaches attention codegen pipeline to reuse the intrinsic layout of output of the first matmul as the lhs of the second matmul. This is possible for 16x16x16 and 32x32x8 MFMA intrinsic layouts.