jlmaccal at ucalgary.ca
Tue Jan 8 19:36:31 CET 2002
> On Mon, 7 Jan 2002, Justin MacCallum wrote:
> >Our hardware vendor has given us three gigabit ethernet (Intel PRO/1000T
> >Server) and a switch (Intel NetStructure 470T) for evaluation. We have
> >dual PIII 1Ghz nodes in our cluster. I tried two test systems. The first
> >one was a 64 lipid DOPC bilayer with ~11000 atoms. The second was a box
> >of water containing 81000 atoms. Both systems used a 0.9 rlist, 1.4 rdw
> >and 0.9 rcoulomb with PME, order=4, fourierspacing=0.12, optimize_fft=yes.
> >For both systems I ran two simulations, one on two processors and one on
> >four. For both systems, the two processor version performed slightly
> >better than the four processor one. In both cases, the network load in
> >the four processor versions was about 5%. Based on previous benchmarks on
> >fast ethernet nodes, I expect things to scale much better without PME.
> Did you use grompp -shuffle -sort
> It certainly shouldn't be this bad. For a more exact comparison you may
> want to have a look at the gromacs benchmarks which you can download from
> Groeten, David.
I didn't use the -shuffle or -sort options. I will rerun the tests using
those options. Its my understanding that as molecules diffuse, the
benifits of these options will decrease. In other words, spacial
decomposition isn't implemented yet. Is that correct?
More information about the gromacs.org_gmx-users