On Wed, Mar 4, 2015 at 2:20 PM, Andi Kleen <a...@firstfloor.org> wrote: > Hi Honza, > > Regarding modern hash functions, as far as I understand the trend > is to just stop doing anything fancy and just use the CRC instructions > in modern CPUs
I wonder if we can use intrinsics for CRC in place of the existing iterative_hash_hashval_t (and thus the 'mix' macro)? Similar to how we optimize libcpp? Seems like #define mix(a,b,c) \ c = _mm_crc32_u32 (b, c) would do? And for iterative_hash_host_wide_int use _mm_crc32_u64? (libcpp seems to use GCC target builtins, not intrinsics though, see init_vectorized_lexer) Thanks, Richard. > (unless you need a somewhat cryto hash to guard against > DoS attacks). spooky doesn't do that though, it's just a highly > optimized classical hash. It's much more stream lined than the somewhat > weird iterative hash construction that standard gcc uses, and I suspect > has better avalance effect. Also it'll do much less work per bit > (at the cost of larger code) > >> Said all that I would be very curious if actual stronger hading would help. >> I saw some miscompares for stuff that should be covered by hash. I will try >> to get some stats soon. > > I sent you the spooky patches in separate mail. I did a quick test run > and they don't seem to regress anything. > > -Andi
