Skip to content
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.

Sign up for GitHub

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

Jump to bottom

Support for ARM SVE and better performance for NEON #281

Merged
merged 13 commits into from
Jun 17, 2024
Merged

Support for ARM SVE and better performance for NEON #281

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
13 commits
Select commit Hold shift + click to select a range
7caecde
Support for ARM SVE and better performance for NEON
fwessels May 31, 2024
fcb2dea
Code refactoring to support code generation for both amd64 as well as…
fwessels Jun 4, 2024
bc4a985
Delete unused file
fwessels Jun 4, 2024
db2296f
Fix test build error
fwessels Jun 5, 2024
0804623
Add !noasm directive to platform specific test files
fwessels Jun 5, 2024
d68faf8
Fix formatting for generated code
fwessels Jun 5, 2024
e65e786
Don't use local vars for function pointers
fwessels Jun 5, 2024
8b6d68a
Refactor canGFNI into architecture specific versions and minor changes
fwessels Jun 5, 2024
a4242ed
Update constant for nopshufb case
fwessels Jun 6, 2024
c0f2a86
Sync up go generate code in _gen
fwessels Jun 6, 2024
d22fb73
Add code to generate the SVE and NEON routines for ARM
fwessels Jun 11, 2024
4ab53e5
Fix go formatting error and update README
fwessels Jun 11, 2024
205abfe
Revert back *8 scaled loads for AVX2 code and fix before conversion t…
fwessels Jun 17, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,10 @@ Using Go modules is recommended.

# Changes

## 2024

* Auto-generation of SVE and NEON routines for ARM based on AVX2 code. This results in a speedup of 2x for SVE (as measured using Graviton 3 on AWS) and a speedup of 1.5x as compared to the existing NEON-accelerated code.

## 2022

* [GFNI](https://github.com/klauspost/reedsolomon/pull/224) support for amd64, for up to 3x faster processing.
Expand Down
Loading
Loading