Follow @Openwall on Twitter for new release announcements and other news
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Sat, 27 Jul 2013 22:12:48 +0200
From: magnum <john.magnum@...hmail.com>
To: john-dev@...ts.openwall.com
Subject: Re: phpass-opencl experiments

On 27 Jul, 2013, at 17:20 , Solar Designer <solar@...nwall.com> wrote:
> On Sat, Jul 27, 2013 at 10:13:43AM +0200, Lukas Odzioba wrote:
>> Just to let you know.
>> I played for a while with phpass-opencl code here are my remarks.
> 
> Thanks!
> 
>> After I changed KPC to 2048*1024
> 
> So we need auto-tuning.
> 
>> After applying attached patch:
> 
> So we need to commit it.
> 
>> Speed of my old code with hash comparision on gpu side with hash
>> "embedded" in salt, is 2125K on amd (nv - not tested).
> 
> Why didn't you commit this?  Is it because it wouldn't handle multiple
> hashes sharing a salt value (this is how I read your description above)?

Lukas currently can't commit (as soon as he wants to, that will change) but I second the question, changed to "should we commit this or not?".

magnum

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.