[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <4255c2571003100803x71aca7f1j9418feef817f7689@mail.gmail.com>
Date: Wed, 10 Mar 2010 09:03:17 -0700
From: RB <aoz.syn@...il.com>
To: john-users@...ts.openwall.com
Subject: Re: Is JTR MPIrun can be optimized for more cores ?
On Wed, Mar 10, 2010 at 01:26, websiteaccess@...il.com
<websiteaccess@...il.com> wrote:
> Here it is a new test with Magnum's advice :
>
> ------------------------------------------------------
> 1 core, duration 40 mn : found 8676
> ------------------------------------------------------
> 2 cores, duration 20 mn : found 8207
> ------------------------------------------------------
> 4 cores, duration 10 mn : found 7886
> ------------------------------------------------------
> 8 cores, duration 5 mn : found 7189
> ------------------------------------------------------
This does serve to roughly illustrate the point, but is also a clear
indicator of the lack of communication between the individual
processes. There is a lot of room for improvement.
The most accurate test would be to do an incremental run of a
character set you know will complete on a single core in a reasonable
timeframe. Then, test the completion time (using 'time john ...' for
accuracy) of 2, 3, and 4-core runs.
Please be aware that the MPI patch by itself induces (as I recall)
10-15% overhead in a single-core run. All runs you are only going to
do on a single processor should never have the MPI patch applied.
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.
