[gmx-users] scaling

[Lynne E. Bilston]

Hi all,

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?

Any suggestions for how to figure out what lam-mpi is doing during the 
parallel runs so i can confirm that it is my switch that's the problem? I 
don't get anything enlightening from the basic mpitask or mpimsg commands.

Thanks,

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