Follow @Openwall on Twitter for new release announcements and other news
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Wed, 25 Jul 2012 18:05:08 +0800
From: myrice <>
Subject: Re: Result of hard core password generation on 7970


On Wed, Jul 25, 2012 at 3:36 AM, Lukas Odzioba <> wrote:
> 2012/7/24 myrice <>:
>> The struct of kernel is as follows
>> for i in [a-zA-Z]
>>   for j in [a-zA-Z]
>>      add [a-zA-Z][a-zA-Z] to key
>>      MD5_Hash
>>      for k in loaded_hashes
>>          compare computed hash with loaded_hashes[k]
>>      endfor k
>>   endfor j
>> endfor i
> I don't understand this code. Every kernel does the same job?
> 9 months ago I coded some trivial md5cracker here's how I generated
> candidates - it is trivial but without those weird loops.
> Maybe this will help you (or not).
> It is possible to generate n-th permutation pretty fast so each thread
> could calculate n-th password from this permutation.
> Lukas

As Solar said, this is for one thread in a kernel. I should make it clear by:

append [a-z][a-z] to key[global_id]
and computed hash[global_id]


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.