Follow @Openwall on Twitter for new release announcements and other news
[<prev] [next>] [day] [month] [year] [list]
Date: Thu, 29 Sep 2016 20:00:05 +0100
From: Darren Wise <>
To: john-users-group <>
Subject: Re: Clustering using OpenCL & MPI

I have asked something along these lines in the past, and yes you are right in thinking that you can compute OpenCL using CUDA but I'm sure I was told (a while back) that if I wanted to compute mixing both CUDA and CPU cores as a while this itself would not be possible but there is nothing stopping you fire up a process that uses the CPU cores on one process and the GPU cores on another.
Further more when launching CPU instances you would use say 4 if it was a quad core processor, but with the CUDA or OpenCL type one whole chip or chard would just be one instance..
That's IF I understood correctly what I was told and I would wait a little while for better clarification on the matter..

> Kind regards,
> Darren Wise Esq, 
> B.Sc, HND, GNVQ, City & Guilds.
> Managing Director (MD)
> Art Director (AD)
> Chief Architect/Analyst (CA/A)
> Chief Technical Officer (CTO)

-------- Original message --------
From: Oliver Weichhold <> 
Date: 29/09/2016  19:42  (GMT+00:00) 
Subject: [john-users] Clustering using OpenCL & MPI 


I'm fairly new to JtR and one thing I couldn't quite figure out reading the various Wiki articles is if it is possible to cluster Linux instances running JtR utilizing OpenCL while coordinating through MPI?


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.