Openwall GNU/*/Linux - a small security-enhanced Linux distro for servers
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Thu, 28 Mar 2013 08:47:53 +0100
From: magnum <john.magnum@...hmail.com>
To: john-dev@...ts.openwall.com
Subject: Re: MPI-openCL build; fast hashes are faster!!

On 28 Mar, 2013, at 5:20 , Sayantan Datta <std2048@...il.com> wrote:
> 6 threads:
> OpenCL error (CL_MAP_FAILURE) in file (opencl_rawmd4_fmt.c) at line (87) - (Error mapping page-locked memory saved_plain)
> 
> Any explanation on why this error is occuring? As far as I know each MPI thread creates it own private pool of memory ,so threads shouldn't be interfering with each other's pinned memories.   

What's the output of ulimit -l? It should be "unlimited". Otherwise you may run out of it, although I think you are supposed to get unpinned memory if that is the case.

Verify that "mpirun -np 1 ulimit -l" is also unlimited.

You could try skipping auto-tune using LWS & GWS environment variables:

$ mpiexec -np 6 -x LWS 64 -x GWS 2097152 ./john -t -pla=1 -dev=0 -fo=raw-md4-opencl

Try lower figure for GWS as well.

magnum

Powered by blists - more mailing lists

Your e-mail address:

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