Open Source at Google: Introducing CityHash

Re:Open Source at Google: Introducing CityHash by nbpoole on Monday April 11, 2011 @05:47PM (#2434563)

I'm not seeing any benchmarks: since they tout speed as a major selling point, that surprises me.

Edit: For instance, the blog post mentions being inspirsed by MurmurHash, which touts its performance on its site along with benchmarks (http://sites.google.com/site/murmurhash/):

    OneAtATime - 354.163715 mb/sec
    FNV - 443.668038 mb/sec
    SuperFastHash - 985.335173 mb/sec
    lookup3 - 988.080652 mb/sec
    MurmurHash 1.0 - 1363.293480 mb/sec
    MurmurHash 2.0 - 2056.885653 mb/sec

In fact, it looks like the author of MurmurHash also developed a test suite for hash functions which includes performance testing: http://code.google.com/p/smhasher/wiki/SMHasher

[ Parent | on HN ]

Re:Open Source at Google: Introducing CityHash by elq on Monday April 11, 2011 @06:00PM (#2434604)

looking at the code, they've optimized for speed. And they also said -

> We decided to optimize for speed rather than simplicity and even included special cases for short inputs.

[ Parent | on HN ]

Re:Open Source at Google: Introducing CityHash by nbpoole on Monday April 11, 2011 @06:11PM (#2434648)

Right, I understand that. I'm just surprised that they aren't showing off benchmarks or statistics to quantify the performance gains they're seeing.

[ Parent | on HN ]

Re:Open Source at Google: Introducing CityHash by andrewcooke on Monday April 11, 2011 @06:51PM (#2434804)

and i'm not seeing any definition of what the hash is, or why it should be any good, apart from the code...

[ Parent | on HN ]