Openwall GNU/*/Linux - a small security-enhanced Linux distro for servers
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Sun, 1 Apr 2012 08:31:07 +0530
From: SAYANTAN DATTA <std2048@...il.com>
To: john-dev@...ts.openwall.com
Subject: Re: JtR: GPU for slow hashes

On Sat, Mar 31, 2012 at 3:51 PM, Solar Designer <solar@...nwall.com> wrote:

> Hi Sayantan,
>
> On Sat, Mar 31, 2012 at 03:42:03PM +0530, SAYANTAN DATTA wrote:
> > I'm pleased to inform you that I have finished the implementation of
> PBKDF2
> > step on GPU  (openCL).
>
> Great.  What performance did you achieve?
>
> >    I'm attaching the unoptimized version host and device codes here.
>
> Please turn this into a JtR "format" that we can benchmark and test via
> JtR itself.  Also, please add copyright and license statements:
>
> http://openwall.info/wiki/john/licensing
>
> BTW, I was pleased to find that myrice's code (in his git repo) already
> has such statements. :-)
>
> Thanks,
>
> Alexander
>

Hi Alexander,
I have few question here regarding JtR format.

1.As the PBKDF2 step uses a 16 byte hexadecimal string as password ,what
should be the properties flag for this type of pass?Here's an example of my
test structure.
static struct fmt_tests tests[] = {
     {"c9ffa11fa850ca3e69bf2e9332528fd8","3ac02a65d6d4c6893f001ce1b4f8543b"
,{"123456789123"}},
          {NULL}
          };
The third field is the username in plaintext.Which will be internally
converted to salt.

2.How do you perform the benches?Do you use the crypt_all() method for
benching?


Regards,

Sayantan

[ CONTENT OF TYPE text/html SKIPPED ]

Powered by blists - more mailing lists

Your e-mail address:

Powered by Openwall GNU/*/Linux - Powered by OpenVZ