Skip to content

Commit

Permalink
Support for ARM SVE and better performance for NEON (#281)
Browse files Browse the repository at this point in the history
* Support for ARM SVE and better performance for NEON
* Code refactoring to support code generation for both amd64 as well as arm64
  • Loading branch information
fwessels authored Jun 17, 2024
1 parent d4574a5 commit 7202dfc
Show file tree
Hide file tree
Showing 20 changed files with 28,506 additions and 175 deletions.
4 changes: 4 additions & 0 deletions README.md
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

0 comments on commit 7202dfc

Please sign in to comment.