[gmx-users] gigabit scaling, DPPC benchmark
Jason de Joannis
jdejoan at emory.edu
Tue Jun 7 20:23:45 CEST 2005
> Date: Tue, 7 Jun 2005 17:32:47 +0200 (CEST)
> From: David van der Spoel <spoel at xray.bmc.uu.se>
> Subject: Re: [gmx-users] gigabit scaling, DPPC benchmark
> To: Discussion list for GROMACS users <gmx-users at gromacs.org>
> <Pine.LNX.4.44.0506071732001.17422-100000 at rembrandt.bmc.uu.se>
> Content-Type: TEXT/PLAIN; charset=US-ASCII
> On Tue, 7 Jun 2005, Jason de Joannis wrote:
> >> > Then why does the Xeon2800/1000Gbit system on gromacs.org scale so well?
> >> > I didn't see any special comments about its network.
> >> Where do you find that? You don't mean the old scaling benchmarks on 800
> >> MHz PIII machines?
> >Not exactly. I am talking about the last line of the 3.0 scaling
> >benchmarks. For example, the 4 processor job runs at 637 ps/day which
> >is 124% scaling. By contrast my machine which is quite similar as far
> >as I can tell, gets only 517 ps/day or 81% scaling. Are those benchmarks
> >for quad-nodes? Mine are dual-nodes.
> Aha, I wasn't aware of these benchmarks.
> These are most likely dual nodes.
> Did you use -shuffle -sort?
yes I did.
More information about the gromacs.org_gmx-users