Date: Sun, 22 Apr 2012 02:23:14 +0200 From: magnum <john.magnum@...hmail.com> To: john-dev@...ts.openwall.com Subject: Re: New RAR OpenCL kernel On 04/22/2012 12:37 AM, Claudio André wrote: > Em 21-04-2012 13:47, magnum escreveu: >> Please test and report. I actually haven't tested it on any GPU yet. > ---- > > OpenCL platform 0: AMD Accelerated Parallel Processing, 2 device(s). > Using device 0: Juniper > > Calculating best keys per crypt for LWS 128, this will take a while > kpc 128 21 c/s 1978473 sha1/s 6.092 sec per crypt_all() This is similar to what I get on a mobile E2 "Loveland" GPU. Are the GPU's this slow, or do I have a major problem? This is about half the speed of one CPU core. I do get warnings about register spill on that one though. > Max is 128: > Calculating best keys per crypt for LWS 256, this will take a while > Error: CL_MEM_OBJECT_ALLOCATION_FAILURE I have committed a fix that adds a check for amount of local memory, similar to what you did in cryptsha512. It also contains lots of more optimisations. Thanks! 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.