Hacker News Reader

You know, everytime I see articles about CityHash/MurmurHash I always wonder why more people don't know about xxHash, which is 3 times faster than MurmurHash.

http://code.google.com/p/xxhash/

http://fastcompression.blogspot.fr/2012/04/selecting-checksu...

On a side note, same goes with LZ4 being twice as fast as Speedy (from the same author).

http://code.google.com/p/lz4/

View on HN

I did a quick skim of the source for xxHash and CityHash. They appear to rely heavily on 32- and 64-bit multiply operations, and are likely "fast" to the extent that these operations are vectorized. The benchmarks I noticed are all run on recent x86_64 processors with big vector units and caches.

It would be interesting to see how they stack up on other platforms like ARM with and without NEON, PPC with and without Altivec, and MIPS. Without that data, the algorithms look pretty tailored for SSE3, and so I'd hesitate to build them into any application or protocol that needs to be portable or implemented in embedded devices.

Reply on news.ycombinator.com