New fastest portable hash: wyhash
github.com
New fastest portable hash: wyhash
1–10 of 52 posts
Re: New fastest portable hash: wyhash
#2From what I see Farmhash is still faster on IA32/AMD64 architectures (although they need to leverage the AES instruction for that, granted).
Re: New fastest portable hash: wyhash
#3The small key performance is very nice. It would be good to have more written about this new hash function, and less misinformed rant about siphash.
Re: New fastest portable hash: wyhash
#4Here's a link to wyhash itself: https://github.com/wangyi-fudan/wyhash
Re: New fastest portable hash: wyhash
#5Here's a link to wyhash itself: https://github.com/wangyi-fudan/wyhash
Maybe the link could be updated to point to this instead?
Re: New fastest portable hash: wyhash
#6From what I see Farmhash is still faster on IA32/AMD64 architectures (although they need to leverage the AES instruction for that, granted).
Some non-portable hashes are still faster, sure. But for a general hash it's remarkably simple, good and fast.
Re: New fastest portable hash: wyhash
#7From what I see Farmhash is still faster on IA32/AMD64 architectures (although they need to leverage the AES instruction for that, granted).
Algorithms using AES intrinsics are generally fastest at all key sizes now. For small keys, the AquaHash[0] algorithm is extremely fast, and several algorithms (e.g. MeowHash[1] and the aforementioned AquaHash) are essentially at the hardware limits for large keys. Algorithms like wyhash are useful for things like embedded CPUs without AES support, but if you are targeting x86/ARM then AES is often a better choice.
[0] https://github.com/jandrewrogers/AquaHash [1] https://github.com/cmuratori/meow_hash
Re: New fastest portable hash: wyhash
#8The small key performance is very nice. It would be good to have more written about this new hash function, and less misinformed rant about siphash.
> misinformed rant
Only siphash fans would say that, and they are very misinformed about the false recommendations from their paper. Prove me wrong.
Re: New fastest portable hash: wyhash
#9The small key performance is very nice. It would be good to have more written about this new hash function, and less misinformed rant about siphash.
> misinformed rant Only siphash fans would say that, and they are very misinformed about the false recommendations from their paper. Prove me wrong.
No, that onus is on you. If you've got specific critique of siphash I'm sure people would like to read them. As it is, you're making somewhat vague denunciations without providing any substance to back them up.
Re: New fastest portable hash: wyhash
#10>The fast hash functions tested here are recommendable as fast for file digests and maybe bigger databases, but not for 32bit hash tables.
Do people really try to optimize file hashing this way?