[ARROW-6385] [C++] Investigate xxh3

• Type: Task
• Status: Resolved
• Priority: Major
• Resolution: Fixed
• Fix Version/s: 0.15.0
• Component/s: Benchmarking, C++
• Labels: pull-request-available
• External issue URL: https://github.com/apache/arrow/issues/22758
• Assignee: Antoine Pitrou
• Reporter: Antoine Pitrou
• Created: 29/Aug/19 12:06
• Updated: 11/Jan/23 07:46
• Resolved: 05/Sep/19 15:31

Description

xxh3 is a new hash algorithm by Yann Collet that claims excellent speed on both small/tiny and large keys. It has accelerated paths for x86 SSE2, AVX and ARM NEON. It also has excellent hash quality.
https://fastcompression.blogspot.com/2019/03/presenting-xxh3.html

Perhaps this can replace our current complex strategy involving a custom tiny string hashing implementation, a HW CRC32-based path where available for large strings, and a murmurhash2 fallback.

Issue Links

• links to: GitHub Pull Request #5265