# Faster BLAKE3 implementation \(\#25574\) · gitcafe/zig

[View on GitCafe](https://git.cafe/gitcafe/zig/commit/6669885aa2a33228baa29daba3b14985158d866f)

Repository: [gitcafe/zig](https://git.cafe/gitcafe/zig)

Visibility: public

Requested revision: 6669885aa2a33228baa29daba3b14985158d866f

Requested commit: 6669885aa2a33228baa29daba3b14985158d866f

Commit: 6669885aa2a33228baa29daba3b14985158d866f

Tree: 857aa08a89d005ae9944808ebf1fc8b93db1594d

Author: Frank Denis

Committer: GitHub

## Message

```
Faster BLAKE3 implementation (#25574)

This is a rewrite of the BLAKE3 implementation, with vectorization.

On Apple Silicon, the new implementation is about twice as fast as the previous one.

With AVX2, it is more than 4 times faster.

With AVX512, it is more than 7.5x faster than the previous implementation (from 678 MB/s to 5086 MB/s).

```

## Parents

- [70c21fdbab064ca060e5f111010836845ca35930](https://git.cafe/gitcafe/zig/commit/70c21fdbab064ca060e5f111010836845ca35930?format=markdown)

[Source at this commit](https://git.cafe/gitcafe/zig/tree/6669885aa2a33228baa29daba3b14985158d866f?format=markdown)
