[midend/lib/Conversion/ConvVectorization] add conv2dnhwcfhwc vectorization pass and add relevant examples and tests. #428
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
…ation pass and add relevant examples and tests.
…ation pass and examples.
…ation pass and examples.
…ation pass and examples.
…ation pass and examples.
…ation pass and examples.
…ation pass and examples about attributes.
conv2d-nhwc-fhwc.mlir, conv2d-nhwc-fhwc-opt.mlir: adjust the code structure; conv2d-nhwc-fhwc-vec.mlir: handwritten mlir file; makefile update Related commands. midend/lib/Conversion/ConvVectorizationn/: Conv2dNhwcFhwcVectorization.cpp to implement vectorisation. Under the path tests/Conversion/: conv2d-nhwc-fhwc-max-vectorisation.mlir: a test file. Before vectorisation optimization: 0.000247002, after vectorisation optimization: 0.000134945 (vectorisation size 2), speedup ratio 0.454.
conv2d-nhwc-fhwc-vec.mlir: examples/BuddyConvlution Conv2dNhwcFhwcVectorization.cpp: midend/lib/Conversion/ConvVectorization conv2d-nhwc-fhwc-vectorization.mlir: tests/Conversion
FloatingcloudKnight
force-pushed
the
conv2dnhwcfhwc
branch
from
fee59fd to
5cb3fbb
Compare
…ht/buddy-mlir into conv2dnhwcfhwc
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Outdated suggestions cannot be applied.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.
Add conv2dnhwcfhwc vectorization pass and add relevant examples and tests.
examples/BuddyConvolution/:
linalg-pooling-nhwc-max.mlir: Linalg Dialect handwritten mlir;
conv2d-nhwc-fhwc-vec.mlir: Vector Dialect handwritten mlir file;
makefile update related commands.
midend/lib/Conversion/ConvVectorizationn/: PoolingNhwcMaxVectorization.cpp implements vectorisation.
tests/Conversion/:
pooling-nhwc-max-vectorisation.mlir: a test file.
Before vectorisation optimization: 1.71661e-05, after vectorization optimization: 1.09673e-05 (vectorization size is 32), speedup ratio is 0.454. The amount of data in the example is small and the optimization effect is not obvious.