Add arm64 NEON path (~1.7x)#27
Merged
Merged
Conversation
Tested with QEMU. My test script:
```
echo Building ARM64 test binary...
set GOOS=linux
set GOARCH=arm64
go test -c -o xxh3_arm64.test
if %ERRORLEVEL% neq 0 (
echo Build failed!
SET GOOS=windows
SET GOARCH=amd64
exit /b %ERRORLEVEL%
)
SET GOOS=windows
SET GOARCH=amd64
echo Running tests in ARM64 container...
docker run --rm --platform linux/arm64 -e GOGC=20 -e GOMEMLIMIT=2GiB -v "%cd%:/work" -w /work arm64v8/alpine ./xxh3_arm64.test %*
```
Adding CI for `ubuntu-24.04-arm` which should test on real HW. Updates various CI aspects as well.
AI assisted code, fwiw.
Contributor
Author
|
Thanks to @leitzler for benchmarking on "Apple M1 Ultra": |
|
Results from M4 |
Owner
|
this seems awesome as usual. i just got back from a vacation so i'll take a look sometime soon. |
Owner
|
i realized the last tag was almost 4 years ago before the 128 bit hasher and a bunch of improvements, so i arbitrarily tagged v1.1.0 and pushed it 😄 thanks! |
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
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Tested with QEMU. My test script:
QEMU is dirt slow with NEON it seems.
Adding CI for
ubuntu-24.04-armwhich should test on real HW. Updates various CI aspects as well.Went for NEON since SVE supposedly gives little advantage and NEON is available across the platform.
Didn't go for the
scalar+NEONhybrid approach ofxxhash.h, since I'd rather not make it too complex.Has not been benchmarked on real hardware. Maybe someone with a Mac can give it a spin?
AI assisted code, fwiw.