[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CABob6ipL+4K0Ac03bvBW+ZyP_7ha=raNNwMbz9e0g=PKbNEFAA@mail.gmail.com>
Date: Tue, 26 Jun 2012 03:50:50 +0200
From: Lukas Odzioba <lukas.odzioba@...il.com>
To: john-dev@...ts.openwall.com
Subject: Re: phpass OpenCL and CUDA
2012/6/26 Solar Designer <solar@...nwall.com>:
> On Tue, Jun 26, 2012 at 03:32:27AM +0200, Lukas Odzioba wrote:
>> 2012/6/26 Solar Designer <solar@...nwall.com>:
>> > 1. There's a function called "cuda_md5" - rename it.
>> >
>> > 2. Make use of rotate() and bitselect().
>> I'll send fix for that in a moment. My target is to make vectorized
>> code work properly so even if code is dirty it should not stay there
>> for long.
>
> Sure. Yet the non-vectorized code is to stay for jumbo-6, right?
Yes.
>> > Are we releasing with these lower speeds?
>> Yes, there were no any major changes. Lower speeds are because test
>> vector change.
>> Previously we're testing just one password, now 15 passwords with
>> increasing length.
>
> I think the increasing lengths are only in the CUDA code, right?
> Thus, the lower OpenCL speed is solely from the reverted code, right?
Yes.
> Do you happen to know what password lengths the published hashcat speeds
> are for?
I do not know, but I'll check that later. I am assuming you're curious
more about AMD speeds?
Lukas
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.
