Openwall GNU/*/Linux - a small security-enhanced Linux distro for servers
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Wed, 6 May 2015 13:09:22 +0300
From: Solar Designer <solar@...nwall.com>
To: john-dev@...ts.openwall.com
Subject: Re: [GSoC] JtR SIMD support enhancements

On Wed, May 06, 2015 at 10:56:00AM +0800, Lei Zhang wrote:
> On May 5, 2015, at 8:48 PM, Solar Designer <solar@...nwall.com> wrote:
> > Thank you!  I think we'll want you to try VTune on other formats as
> > well, and to see lower-level bottlenecks as well (cache misses, etc.)
> > (But for phpass you'd proceed with that later - need to deal with the
> > immediate bottleneck first.)
> 
> Do you mean profiling a normal x86 build or a MIC build? Actually it's a bit of pain to profile MIC programs. The older version of VTune has very limited support for MIC, while the latest version is incompatible with an older MPSS installation. Our lab's server has a rather old MPSS, and currently I don't have the permission to upgrade it, so I have to live with the older VTune.

I meant profiling a MIC build, but please feel free to use VTune on
x86(-64) builds as well.

> I'm not sure where OMP_SCALE is defined for phpass. I guess it's in dynamic_types.h, and that's the result after tuning it:
> 
> OMP_SCALE	Result
> -----------------------------------
> 1			18249 c/s real, 75.9 c/s virtual
> 4			18917 c/s real, 79.1 c/s virtual
> 16			18629 c/s real, 77.5 c/s virtual
> 64			18541 c/s real, 77.8 c/s virtual
> 256			18541 c/s real, 77.7 c/s virtual
> 
> It appears tuning OMP_SCALE makes not much difference here. BTW, setting OMP_SCALE to 2048 or higher would cause the failure of memory allocation. From this experiment, I'm uncertain about if OMP_SCALE has a significant impact on synchronization overhead.

That's weird.  Either that OMP_SCALE in dynamic_types.h isn't affecting
phpass as we want it to, or the bottleneck is different.

phpass really ought to benchmark to within 1/2 of the performance of
md5crypt.  We should make it so.

Alexander

Powered by blists - more mailing lists

Your e-mail address:

Powered by Openwall GNU/*/Linux - Powered by OpenVZ