[gmx-users] GROMACS in parallel on a multicore PC?

[Carsten Kutzner]

Hi Vasilii,


Vasilii Artyukhov wrote:
> Hi everybody,
> 
> Sorry for a somewhat technical question, but I'd like to know which is
> the best way to run GROMACS on a SMP machine (in particular, a multicore
> PC). The (known) points of interest are:
> 
> - Does GROMACS support multithreaded execution & how efficient is it?
As far as I know this is planned, but not supported yet.

> 
> - Should I rather use some kind of MPI & which (LAM/Open/MPICH) is
> better & why?
Yes. This is the way to go. On an SMP box you will probably not see
large differences between the different MPI implementations, but why not
try a few? My own experience is that LAM tends to be the fastest, partly
due to the memory mangager it uses.

Carsten

> Surely, there's always the option to run two serial jobs instead with a
> greater efficiency, but having some means to boost the single job
> performance by something like 1.9x would be very useful...
> 
> Thanks in advance,
> 
> Vasilii
> 
> 
> ------------------------------------------------------------------------
> 
> _______________________________________________
> gmx-users mailing list    gmx-users at gromacs.org
> http://www.gromacs.org/mailman/listinfo/gmx-users
> Please search the archive at http://www.gromacs.org/search before posting!
> Please don't post (un)subscribe requests to the list. Use the 
> www interface or send it to gmx-users-request at gromacs.org.
> Can't post? Read http://www.gromacs.org/mailing_lists/users.php

-- 
Dr. Carsten Kutzner
Max Planck Institute for Biophysical Chemistry
Theoretical and Computational Biophysics Department
Am Fassberg 11
37077 Goettingen, Germany
Tel. +49-551-2012313, Fax: +49-551-2012302
http://www.mpibpc.mpg.de/research/dep/grubmueller/
http://www.gwdg.de/~ckutzne