[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CANJ2NMO3hPiLjHxMzGHEAircmnosrA-BZXoMeLUW2jMg27GY=A@mail.gmail.com>
Date: Sat, 7 Jul 2012 22:57:13 +0800
From: myrice <qqlddg@...il.com>
To: john-dev@...ts.openwall.com
Subject: Re: [PATCH] integrate psk-crack (from ike-scan) into john.
On Sat, Jul 7, 2012 at 9:26 PM, Lukas Odzioba <lukas.odzioba@...il.com> wrote:
> 2012/7/7 Dhiru Kholia <dhiru.kholia@...il.com>:
>> Hi,
>>
>> The attached patch (alpha quality) integrates psk-crack (from
>> ike-scan) into john. Please apply it to bleeding-jumbo and test.
>>
>> $ ../run/john -format:ike -t # AMD X3 720 BE CPU
>> Benchmarking: IKE PSK HMAC-MD5 / HMAC-SHA1 [32/64]... (3xOMP) DONE
>> Raw: 1222K c/s real, 415673 c/s virtual
>
> It is quite fast as I suspected. We may not have yet enough good
> john's architecture for efficient gpu implementation.
> Myrice what do you think?
>
The 400K c/s/core could be archived I think. The raw-sha256 format got
2000K/c/s/core
Dhiru expects GPU version got to 35M c/s. The raw-md5-opencl version
already got 40M c/s. But raw-sha256-cuda is slow. Lukas, what do you
get in raw-sha256 on GPU?
myrice
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.
