Re: NAMD 2.7b2 versy slow on multiple nodes

From: Laurent Chaloin (Laurent.Chaloin_at_cpbs.cnrs.fr)
Date: Wed May 26 2010 - 07:43:56 CDT

Thanks a lot for the link. Your benchmark is very well detailed and I
agree with you concerning MPI, Charmrun is the winner.
However, after having reproduced the build of charm and compiled Namd
again with g++ and smp, I still have the same problem that indicates
that it could be a hardware problem. Where did you find the +giga
+max_dgram_size options, I did not see it anywhere and what do they mean?

Thanks, Laurent

>
> Have a look at
>
> http://norma.mbg.duth.gr/index.php?id=about:benchmarks:namdv27b1
>
> for a summary of our experiences (noting that ours is a toy cluster).
>
>
> Nicholas
>
>
>

-- 
_______________________________________________
Dr. CHALOIN Laurent
Equipe de biophysique et bioinformatique Centre d'études d'agents Pathogènes et Biotechnologies pour la Santé
CNRS - UMR 5236 - Université Montpellier 1 et 2
Institut de Biologie, 4 bd Henri IV - CS 69033
34965 Montpellier - cedex 2
Tel: 04 67 60 02 31
Fax: 04 67 60 44 20

This archive was generated by hypermail 2.1.6 : Wed Feb 29 2012 - 15:54:10 CST