john-users - RE: DES with OpenMP

Openwall wordlists collection for password cracking (20+ languages)

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date: Mon, 30 Jan 2012 13:44:35 +0000
From: Alex Sicamiotis <alekshs@...mail.com>
To: <john-users@...ts.openwall.com>
Subject: RE: DES with OpenMP


> > 
> > On Fri, Jan 20, 2012 at 09:35:26PM +0000, Alex Sicamiotis wrote:
> > > ...the OMP version is scoring +200k in many salts over the noOMP despite threads=1,
> > 
> > Yes.
> > 
> > > when it should be equal.
> > 
> > No, it should not.  It should be close, but not equal.  Normally, OpenMP
> > build running with 1 thread is slightly slower than non-OpenMP build,
> > but it can also be the other way around.  The code is different in many
> > ways.  Even the chunk size (number of passwords being hashed per
> > crypt_all() call) differs by a factor of 32 between these builds.
> > Normally, this hurts performance when you don't actually run multiple
> > threads, but in certain builds and on certain machines it can be the
> > other way around as you have seen.
> > 

I was looking now at the john.log, and for openMP 2 threads it was

0:00:00:00 - Candidate passwords will be buffered and tried in chunks of 8192

for openMP 1 thread it was

0:00:11:32 - Candidate passwords will be buffered and tried in chunks of 4096

and for non-openMP it was

0:00:11:38 - Candidate passwords will be buffered and tried in chunks of 128

...and I remembered what you said about this code difference. So.. supposing this can give, say +200k c/s which I'm seeing between the openmp and non-openmp, where do I tweak the code to test various values?