Follow @Openwall on Twitter for new release announcements and other news
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Mon, 16 Jul 2012 18:23:36 +0800
From: myrice <>
Subject: Re: xsha512-cuda & xsha512-opencl testing

On Mon, Jul 16, 2012 at 5:40 PM, Solar Designer <> wrote:
> myrice -
>> 10K_1
>> guesses: 0  time: 0:00:04:00 0.00%  c/s: 122552M
> 12M passwords/second, probably limited by transfers of hashes from GPU
> to CPU, right?

I guess so.

>> 1M_1
>> guesses: 0  time: 0:00:03:58 0.00%  c/s: 2788G
> 2.7M passwords/second, probably limited by large hash table lookups on
> the host.  Is this magnum-jumbo (without bitmaps) or bleeding (with
> bitmaps)?  I'd expect better speed with bitmaps.  Either way, you need
> to implement an equivalent of them on the GPU side.  Not necessarily for
> this hash type (where having so many hashes/salt is not typical), but
> for saltless hashes mostly (where having millions of hashes and no salts
> is common).

I believe I used bleeding-jumbo from now(or I will have my loaded hash code :( )

BTW, what is exactly bitmaps you said for my format? Can you give me
more details? I think bitmaps are compressed hash table. How does JtR
lookups the hash table?


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.