Date: Sun, 24 Nov 2013 17:35:19 +0100 From: magnum <john.magnum@...hmail.com> To: john-dev@...ts.openwall.com Subject: Re: md5crypt-opencl On 2013-11-24 12:47, Lukas Odzioba wrote: > Solar stated this on private list: > 2013/11/24 Solar Designer <solar@...nwall.com>: >> BTW, I guess one of the reasons hashcat/md5crypt/AMD is so good is that >> hashcat groups candidate passwords by length. When there are different >> length passwords being tested on a GPU at the same time, you're probably >> wasting some local memory on supporting excess lengths for the shorter >> ones of the passwords. You could try implementing something similar - >> e.g. per-length OpenCL kernel invocations out of one crypt_all(), or >> simply detection of and optimization for the special case when all >> passwords in a crypt_all() are same length (maybe you do this already?) While that is probably a good idea, our currently active test vectors are only of length 8 so IRL we're even worse than the benchmark :-( BTW isn't some of what we do in SSE-intrinsics.c appliable to a GPU? I think it is but I never really groked that SSE code. > So what's my current status, I have code that pass self-test > (saltlen=8,pass=8). c/s results are the following: > > 570: 1.1k c/s > 7970 1.6k c/s > Titan 2.2k c/s You mean x1000 in all of the above, no? I get 194k using a laptop GPU with latest bleeding. The HC+ figures: 3445k c/s on 7970 and 1044 c/s on GTX 580. magnum
Powered by blists - more mailing lists
Confused about mailing lists and their use? Read about mailing lists on Wikipedia and check out these guidelines on proper formatting of your messages.