[gmx-users] Scaling on IBM/SP2 Power3

[David van der Spoel]

On Wed, 2002-11-06 at 12:26, Anton Feenstra wrote:
> > > I'd appreciate any comments and/or other suggestions!
> > You are omitting the most important information: is this with PME or
> > with a cut-off? With cut-off you should be able to reproduce the gmx
> > benchmarks, with PME it won't be as nice... Erik (and me) are working on
> > this though...
> 
> That is one of the reasons I have not (yet) switched to using PME... ;-}
> So, I'm using cut-offs which should give me better scaling than I have.
>
OK, but since your system is a lot smaller than the benchmark system
(120000 atoms) scaling will be worse as well. Check out the benchmark...


-- 
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://xray.bmc.uu.se/~spoel
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++