Follow @Openwall on Twitter for new release announcements and other news
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Tue, 07 Aug 2012 23:40:47 +0200
From: Samuele Giovanni Tonon <samu@...uxasylum.net>
To: john-dev@...ts.openwall.com
Subject: Re: Result of hard core password generation on 7970

On 08/07/12 17:46, myrice wrote:
> Solar
>
> On Mon, Aug 6, 2012 at 3:46 PM, myrice<qqlddg@...il.com>  wrote:
>> Solar
>>
>> On Fri, Aug 3, 2012 at 12:42 AM, Solar Designer<solar@...nwall.com>  wrote:
>>> Are you using the bitmap even with just 1 hash loaded?  In the real
>>> implementation, I guess you'll need to do direct comparisons when the
>>> number of loaded hashes (for the current salt if applicable) is below a
>>> threshold (like just 1 or 2).
>>
>> Here is the result of using local memory for hashes<  2048 and direct
>> compare using register for hashes is 1 or 2:
>> I set global work size to 2048*8 with all test cases:
>>
>> raw-md5-opencl with PG (Local memory)
>>
>> 1
>> guesses: 0  time: 0:00:01:28 0.00%  c/s: 826315K
>>
>> 1000
>> guesses: 0  time: 0:00:01:45 0.00%  c/s: 828407M
>>
>> 1000000
>> guesses: 0  time: 0:00:00:52 0.00%  c/s: 437215G
>>
>> The code is here:
>> https://github.com/qqldd/myrice-JtR/blob/PG-test
>>
>> The file I changed:
>> https://github.com/qqldd/myrice-JtR/blob/PG-test/src/opencl_rawmd5_fmt.c
>> https://github.com/qqldd/myrice-JtR/blob/PG-test/src/opencl/md5_kernel.cl
>
> Previous, in my code, the password generation have unnecessary read
> global keys every iteration. I move these code out of two for
> iterations. Also, I change global work size to 2048*32 which
> contributes to better performance. Here is the result:
>
> 1
> guesses: 0  time: 0:00:01:26 0.00%  c/s: 1956M
>
> 1000
> guesses: 0  time: 0:00:01:27 0.00%  c/s: 1807G = 1807M
>
> 1M
> guesses: 0  time: 0:00:01:25 0.00%  c/s: 922618G = 922.6M
>
> Thanks
> myrice

hoping it can help, this are some results on 10 minutes run on the
6970 on the last code i found on your pg-test branch

./john -i:all7 -format=raw-md5-opencl -pot=/tmp/x11 /tmp/test2
OpenCL platform 0: AMD Accelerated Parallel Processing, 2 device(s).
Using device 0: Cayman
Compilation log:
Warning: md5 kernel has register spilling. Lower performance is expected.

Local work size (LWS) 128, Global work size (GWS) 65536
Loaded 1 password hash (Raw MD5 [OpenCL])
end self test
guesses: 0  time: 0:00:00:14 0.00%  c/s: 552271K  trying: ab17377 - 
guesses: 0  time: 0:00:00:21 0.00%  c/s: 569804K  trying: deslow0 - 
guesses: 0  time: 0:00:04:51 0.00%  c/s: 554802K  trying: roclm62 - 
guesses: 0  time: 0:00:05:23 0.00%  c/s: 555691K  trying: sw18@...Z - 
guesses: 0  time: 0:00:07:48 0.00%  c/s: 555025K  trying: gwirocK - 
guesses: 0  time: 0:00:08:07 0.00%  c/s: 555673K  trying: davaing - 
guesses: 0  time: 0:00:10:02 0.00%  c/s: 554718K  trying: taz@101 -

[...]
Loaded 1000 password hashes with no different salts (Raw MD5 [OpenCL])
end self test
guesses: 0  time: 0:00:00:28 0.00%  c/s: 532547M  trying: pll9786 -
guesses: 0  time: 0:00:03:35 0.00%  c/s: 536859M  trying: dumiegh -
guesses: 0  time: 0:00:05:50 0.00%  c/s: 534914M  trying: ddoni26 -
guesses: 0  time: 0:00:07:09 0.00%  c/s: 535536M  trying: phb2362 -
guesses: 0  time: 0:00:10:00 0.00%  c/s: 535703M  trying: 044rndt -

[...]
Loaded 1000000 password hashes with no different salts (Raw MD5 [OpenCL])
end self test
guesses: 0  time: 0:00:00:01 0.00%  c/s: 552271G  trying: 0148817 - 
guesses: 0  time: 0:00:00:08 0.00%  c/s: 483237G  trying: ap26486 - 
guesses: 0  time: 0:00:00:44 0.00%  c/s: 476962G  trying: shiades - 
guesses: 0  time: 0:00:01:47 0.00%  c/s: 480012G  trying: mbowl13 - 
guesses: 0  time: 0:00:04:15 0.00%  c/s: 480801G  trying: bb29979 - 
guesses: 0  time: 0:00:07:53 0.00%  c/s: 479881G  trying: clo15en - 
guesses: 0  time: 0:00:11:02 0.00%  c/s: 480526G  trying: lbresck - 
guesses: 0  time: 0:00:11:04 0.00%  c/s: 479910G  trying: gracy04 -


cheers
Samuele

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.