Follow @Openwall on Twitter for new release announcements and other news
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <B3D39F7F-C2AD-41A2-A8E1-D53AC7DDB812@erols.com>
Date: Tue, 14 Sep 2010 19:17:34 -0400
From: Erik Winkler <ewinkler@...ls.com>
To: john-users@...ts.openwall.com
Subject: Re: NTLM and OpenCL 1.0


On Sep 13, 2010, at 1:58 PM, Alain Espinosa wrote:

> This is a more "polish" version. In my tests there are a speedup of 6x
> (not all john, only transfer and crack). Erik may test this for a more
> real benchmark. John in cygwin continue to not work, i test the code
> in Windows with a simple program.

I tested the new version and here are the benchmarks:

OpenCL 64-bit 
./john -test=15 -format:NT
Benchmarking: NT MD4 [OpenCL 1.0]... 
OpenCL platform: <<< Apple >>>
OpenCL device: <<< GeForce 9400M >>>
DONE
Raw:	9127K c/s real, 21100K c/s virtual

64-bit
./john -test=15 -format:NT
Benchmarking: NT MD4 [128/128 X2 SSE2-16]... DONE
Raw:	24121K c/s real, 24137K c/s virtual


OpenCL SSE2
./john -test=15 -format:NT
Benchmarking: NT MD4 [OpenCL 1.0]... 
OpenCL platform: <<< Apple >>>
OpenCL device: <<< GeForce 9400M >>>
DONE
Raw:	9313K c/s real, 21906K c/s virtual

SSE2
./john -test=15 -format:NT
Benchmarking: NT MD4 [128/128 SSE2 + 32/32]... DONE
Raw:	14783K c/s real, 14793K c/s virtual


Big increase in benchmarks.  It should work really well on a high-end video card.

Erik


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.