[gmx-users] Parallel Gromacs Benchmarking with Opteron Dual-Core & Gigabit Ethernet
lindahl at cbr.su.se
Mon Jul 23 14:41:03 CEST 2007
> I read at Gmx site that the DPPC system
> composed of 121,856 atoms. I saw the gmx topology files, it
> seems that Gmx makes data decomposition on input data to run in
> (in our simulation case using "-np 12" for execution
> on 3 nodes, the data space for every process is about 10156 atoms).
> I think that the DPPC system's size is not so big enough that someone
> can sense the scalability of parallel execution in the existence of
> Gigabit Eth. I mean to see the Cluster scalability in our
> we should setup a bigger simulation. Pls correct me, if I'm in
Well, you can always try different systems (genconf + edit topology),
but the fact that you see low user CPU usage likely means the nodes
are busy waiting for the communication (which probably counts as
Remember - compared to the benchmark numbers at www.gromacs.org, your
bandwidth is 1/4 and the latency 4 times higher, since you have four
cores sharing a single network connection.
Gromacs 4 should scale better on any hardware (significantly better
with PME), but you'll probably never see great scaling with only 4-
way shared gigabit ethernet. It's available in the head branch of
CVS for expert users/voluntary guinea-pigs, but entirely unsupported
until we release it.
More information about the gromacs.org_gmx-users