Attempt to fix nested vectorization gemm performance on new build bot #7959
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
|
Looks like this did indeed fix the performance regression on the new buildbot for that specific test: https://buildbot.halide-lang.org/master/#/builders/81/builds/178 However it seems other things are broken now |
|
ugh, looks like my Mac maintenance yesterday broke Python on max-x86-3, that should be easy to fix, but the armbots just pull the source and then fail with no explanation? wtf? |
|
looks like the armbot just needed a reboot, working on the other one now |
|
Is this ready to land? |
|
Yes, failures appear to be unrelated |
steven-johnson
approved these changes
Nov 29, 2023
steven-johnson
deleted the
abadams/fix_nested_vectorization_gemm_perf
branch
ardier
pushed a commit
to ardier/Halide-mutation
that referenced
this pull request
Mar 3, 2024
…halide#7959) * Better (simpler) schedules for nested vectorization gemm * Remove early return * Empty-Commit --------- Co-authored-by: Steven Johnson <srj@google.com>
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Outdated suggestions cannot be applied.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.
This new schedule is about the same speed as the old one on an M1, but generates much less code, spills less, and avoids the use of tbl instructions in favor of zips.