Remove ifdef for linux targets - NHWC Transformer in Conv op#28564
Closed
JonathanC-ARM wants to merge 1 commit into
Closed
Remove ifdef for linux targets - NHWC Transformer in Conv op#28564JonathanC-ARM wants to merge 1 commit into
JonathanC-ARM wants to merge 1 commit into
Conversation
Signed-off-by: Jonathan Clohessy <Jonathan.Clohessy@arm.com>
Contributor
Author
|
Closing PR, fix is already included in #28565 |
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 change removes the linux part of the ifdef's in conv.cc and conv.h, so the existing NHWC Transformed packed-filter cache is compiled on macOS.
Before this, macOS used the NHWC Conv fast path, but the packed-filter cache code was compiled out. That meant eligible Conv weights could be packed repeatedly during inference. With the guard removed, the existing lazy cache path runs: the first eligible inference packs the filter, and subsequent runs reuse that packed filter.