Openwall GNU/*/Linux - a small security-enhanced Linux distro for servers
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Sun, 18 Dec 2011 01:29:02 -0700
From: RB <aoz.syn@...il.com>
To: john-dev@...ts.openwall.com
Subject: Re: DES BS + OMP improvements, MPI direction

On Sat, Dec 17, 2011 at 15:46, Solar Designer <solar@...nwall.com> wrote:
> It'd be nice if you add some benchmark results to:
>
> http://openwall.info/wiki/john/benchmarks

I'll look at adding a few.

> Actually, 120M c/s would result in completion in 17 hours (for printable
> US-ASCII), so perhaps you're not actually getting that speed.

Specifically with benchmarking, I need to go back and make a little
more rigorous tests.  What I was doing was in the middle of a CTF and
I paid less attention to clean tests and more to whether I was getting
the results I needed.

> Are you suggesting that we'd apply MPI at the same low level where we
> currently apply OpenMP?  No, that doesn't sound like a good idea to me,
> except maybe for the slowest hash/cipher types only (BF, MSCash2, RAR,
> crypt when run against SHA-crypt), where it might be acceptable.

Yes, it is what I'm suggesting.  Obviously anything that completes in
less than the RTT of the MPI environment would need to be handled
differently (if at all), but the problem the MPI implementation has
historically had is that it splits work at too high a level.  Last I
checked it was splitting work based on individual work steps - each
thread took a given length x count and worked it by itself on that.
For very fast hashes (like LM) I'm sure that's more acceptable, but
for slower ones and with larger MPI implementations (hundreds to
thousands of threads), the network very quickly gets to the point that
every thread is working on an effectively impossible-to-solve step,
which really isn't the end-user's intent of parallelization.  For the
sake of argumentation (and pulling numbers out of thin air to make an
example), the typical user wants to see 7-character passwords at a
count of 95 completed before N-1 out of N of their processors move on
to harder steps.


RB

Powered by blists - more mailing lists

Your e-mail address:

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