Arm backend: Add fused i8 warp+downsample example - #21972
Merged
oscarandersson8218 merged 1 commit intoAug 20, 2026
Conversation
Adds example where int8 warp+downsample is fused into one custom shader. This pattern is present in rife model and such a fusion can reduce memory bandwidth significantly as it avoids processing pixels that are not used by downsampling. Signed-off-by: Oscar Andersson <oscar.andersson@arm.com> Change-Id: I0bec6fb6d3fe879900d744cb92f6c4aab16238ff
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/21972
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 Cancelled Job, 1 Unrelated FailureAs of commit 14f33be with merge base 92079a2 ( CANCELLED JOB - The following job was cancelled. Please retry:
BROKEN TRUNK - The following job failed but were present on the merge base:👉 Rebase onto the `viable/strict` branch to avoid these failures
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
Collaborator
|
nit: Maybe also update examples/arm/QAT_example/README.md |
zingo
approved these changes
Aug 20, 2026
zingo
left a comment
Collaborator
There was a problem hiding this comment.
I assume the bin files are used/needed and in this stage not generated?
Collaborator
Author
They are needed just like the ones in https://github.com/pytorch/executorch/tree/main/backends/arm/vgf/shaders.
I'll add this in a follow up if that's ok. |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds example where int8 warp+downsample is fused into one custom shader. This pattern is present in rife model and such a fusion can reduce memory bandwidth significantly as it avoids processing pixels that are not used by downsampling.
cc @digantdesai @freddan80 @per @zingo @mansnils @Sebastian-Larsson @robell @rascani