Conversation
|
Azure Pipelines: There may be pipelines that require an authorized user to comment /azp run to run. |
Contributor
Author
|
Jianhui Dai (@daijh) Jie Chen (@jchen10), Jianhui, PTAL, thanks. |
Contributor
|
Is this one duplicated with #32185? |
Contributor
Author
|
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
The im2col-matmul Conv kernel used to bail out when the Conv node had a fused
activation. This PR applies the activation in the im2col-matmul shader, right
after the bias is added, so fused Conv can use this path too.
Motivation and Context
Fused Conv is common in vision models, and excluding it meant those models never
got the faster kernel. Measured on PTL, this gives ~15% improvement on
detr-resnet-50-fp16.onnxandresnet50-v1-f16-demo.onnx.