SWP for block-wise fp8 fastacc #1
Open
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
Summary: Test Plan: Reviewers: Subscribers: Tasks: Tags:
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Outdated suggestions cannot be applied.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.
Trying to manually create a better pipelined schedule:
prior-to-swp.ttgir --> ttgir right before SWP optimization
manual-decomp-and-swp.ttgir --> manually decomposed and pipelined version based on the final ttgir
manual-decomp-prior-to-swp.ttgir --> manually decomposed version based on the ttgir right before SWP optimization
computation-pipeline.ttgir --> run improved computation pipelining and other passes on manual-decomp-prior-to-swp.ttgir
manual-fix-on-top-of-comp-swp.ttgir --> with manual fixup based on computation-pipeline.ttgir
base.ptx --> ptx for the base case
manual-decomp-and-swp.ptx --> ptx for manual-decomp-and-swp.ttgir
manual-fix-on-top-of-comp-swp.ptx --> ptx for manual-fix-on-top-of-comp-swp.ttgir