-
Notifications
You must be signed in to change notification settings - Fork 13
fearless_simd + BRAVO #64
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Merged
Merged
Conversation
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
…g to fearless_simd
…atch space; collapses performance
…tack scratch space; collapses performance" This reverts commit 6ad19af.
…default() instead
… maybe LLVM eliminated it already?
Codecov Report❌ Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #64 +/- ##
==========================================
- Coverage 99.88% 99.79% -0.10%
==========================================
Files 12 13 +1
Lines 2711 2867 +156
==========================================
+ Hits 2708 2861 +153
- Misses 3 6 +3 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
Closed
This was referenced Jan 24, 2026
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Outdated suggestions cannot be applied.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.
I've cleaned up the PoC and made it adapt to the native vector width.
This is a significant performance improvement across the board, barring the smallest sizes on Aarch64 which worked well enough with fully unrolled paths specialized for a single small size.
This is also a way forward for writing code that's "generic" over the f32/f64 types and native vector widths. The machine code is the same as if these were Rust generics (full monomorphization) but it's implemented via declarative macros. We can reuse this approach for DiT kernels later, which are currently copy-pasted.
Stacked on top of #58
Supersedes #62