[gmx-users] Re: gmx-users digest, Vol 1 #247 - 6 msgs

Lynne E. Bilston l.bilston at unsw.edu.au
Mon May 13 04:08:21 CEST 2002


Oddly, grompp -shuffle -sort actually slowed it down very marginally (dppc 
benchmark problem went from 1hr42min without shuffle/sort) to 1 hr 43 min, 
on two dual athlon cpus) The single dual cpu m/c was 1 hr 36 mins for the 
same benchmark.

I haven't tried the short message option on lam yet (I have just used the 
rpms from the gmx download page.)

>Subject: Re: [gmx-users] scaling
>On Fri, 10 May 2002, Lynne E. Bilston wrote:
> >I'm running the dppc benchmark on my new systems, and have found that it
> >takes longer to run the benchmark if I run it over two dual cpu machines
> >than running it on a single dual cpu machine, although the logfiles report
> >76% scaling and 99% scaling respectively. I'm using dual athlons with 100
> >Mb ethernet, and RH7.2.
> >
> >I assumed this means that the communication between the two machines is the
> >bottleneck. (I'm using an old switch while I wait for the new one)
> >
> >However, in the logfile there are some comments about load balancing
> >reducing performance. Is this something to look at?
>Have you tried using:
>grompp -shuffle -sort
>furthermore you want to compile LAM with the option
>(see http://zorn.bmc.uu.se/~spoel/scaling/#tcp)
>Groeten, David.
>Dr. David van der Spoel,        Biomedical center, Dept. of Biochemistry
>Husargatan 3, Box 576,          75123 Uppsala, Sweden
>phone:  46 18 471 4205          fax: 46 18 511 755
>spoel at xray.bmc.uu.se    spoel at gromacs.org   http://zorn.bmc.uu.se/~spoel

Lynne E. Bilston, PhD
Senior Scientist, Prince of Wales Medical Research Institute, and
Conjoint Associate Professor, Faculty of Medicine, University of New South 
Barker St, Randwick, NSW 2031 Australia
Tel: +61-2-9382-7924	Fax: +61-2-9382-2643

More information about the gromacs.org_gmx-users mailing list