Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix vectorization pass for pooling max and update related files #448

Open
wants to merge 17 commits into
base: main
Choose a base branch
from

Conversation

FloatingcloudKnight
Copy link
Contributor

Fix vectorization pass for pooling max and update related files

Pooling-Nhwc-max-vec.mlir: examples/BuddyNext
PoolingNhwcMaxVectorization.cpp: midend/lib/Conversion/ConvVectorization
Pooling-Nhwc-Max-Vectorization.mlir: tests/Conversion

FloatingcloudKnight and others added 17 commits November 8, 2024 05:50
…ation pass and add relevant examples and tests.
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.
Pooling-Nhwc-max-vec.mlir: examples/BuddyNext
PoolingNhwcMaxVectorization.cpp: midend/lib/Conversion/ConvVectorization
Pooling-Nhwc-Max-Vectorization.mlir: tests/Conversion
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant