News for hackers. Stuff that matters.
Re:Branchless UTF-8 Encoding by Laiho on Saturday January 18, 2025 @07:05AM (#42747758)

  fn validate_ascii(bytes: &[u8]) -> bool{
      bytes.iter().fold(true, |acc, b| acc & (\*b <= 127))
  }
This check will likely be the best for english text/code. You can check in varying size chunks depending on how common you think non-ascii will be. If its ascii you can move 128 bytes forward on avx2 in a couple of cycles.

There are no comments on this comment yet.