Follow @Openwall on Twitter for new release announcements and other news
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Wed, 25 Apr 2012 22:24:23 +0200
From: magnum <john.magnum@...hmail.com>
To: john-dev@...ts.openwall.com
Subject: Re: New RAR OpenCL kernel

On 04/25/2012 02:38 PM, SAYANTAN DATTA wrote:
> Hi magnum,
> 
> I tested your rar format on my 4890.Here's the result:
> 
> OpenCL platform 0: AMD Accelerated Parallel Processing, 2 device(s).
> Using device 0: ATI RV770
> Compilation log: LOOP UNROLL: pragma unroll (line 264)
>     Unrolled as requested!
> 
> Optimal local work size 256
> (to avoid this test on next run, put "rar_LWS = 256" in john.conf, section
> [Options:OpenCL])
> Optimal keys per crypt 256
> (to avoid this test on next run, put "rar_KPC = 256" in john.conf, section
> [Options:OpenCL])
> Local worksize (LWS) 256, Global worksize (KPC) 256
> Benchmarking: RAR3 (6 characters) [OpenCL]... DONE
> Raw:    64.2 c/s real, 64.2 c/s virtual
> 
>  Is it okay to have KPC 256? Seems a bit low..

Thanks! I suspect this is very low for that card, it should likely be
more than 10x faster. I really need to find out what I am doing that
nvidia's like, but AMD's do not. Good to hear it's working at all though.

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.