From: Nicholas M Glykos (glykos_at_mbg.duth.gr)
Date: Mon Oct 26 2009 - 04:57:22 CDT
Hi Bernardo,
> NAMD scalability might be significantly different for two different systems.
> Right?
Right.
> If it is so, why would be important to run the benchmark apoa1 if you
> are going to be working with a different system? It is just to compare
> to the performance that other people get with NAMD?
For the same reason we run all types of benchmarks, namely to establish
(through comparison) that the given computing machine is properly tuned
and performing as expected for its class.
> Then if that is the case, for any system I would have to run some kind
> of benchmark to see how scalable is NAMD in that particular case. Right?
Absolutely right. Parallel scaling should be established for every new
system (mainly number of atoms) and simulation protocol, otherwise you may
end-up wasting computational resources.
I should add as a side note that -at least to my experience- there is no
single optimal way of tuning the operating system, such that it performs
best for all possible problem sizes and protocols. If you tune the OS
using the ApoA1 system, you shouldn't be surprised if it turns-out that it
is not optimal for, say, a peptide simulation. For large centralised
clusters, of course, you do not have a choice (which usually is a relief ;-)
My twocents,
Nicholas
--
Dr Nicholas M. Glykos, Department of Molecular Biology
and Genetics, Democritus University of Thrace, University Campus,
Dragana, 68100 Alexandroupolis, Greece, Tel/Fax (office) +302551030620,
Ext.77620, Tel (lab) +302551030615, http://utopia.duth.gr/~glykos/
This archive was generated by hypermail 2.1.6 : Wed Feb 29 2012 - 15:53:24 CST