[gmx-users] cpu utilization
dtj at uberh4x0r.org
Fri Oct 17 19:37:00 CEST 2003
I have started running some benchmarks using the latest of all the
required software (with vanilla MPICH). Its a 16 node Dell dual 1.7 &
1.8Ghz xeons with gigE. When I am running Amber I get pretty much full
cpu utillization when I run two 16 cpu (16x1) jobs and slightly less
with a single 32 cpu (16x2) job. Running GROMACS, I can only get
utilization up close to 40% when I try larger jobs. The nodes have
plenty of memory and the systems are pretty quiet. Is this consistent
with what people are seeing?
Also, perhaps a bit of evidence, it has a real hard time cleaning up
after itself. The output indicating performance and stuff comes *way*
before the jobs eventually die and some never die. I had to write a
simple 'killgro' command to nuke everything for good. Any ideas?
More information about the gromacs.org_gmx-users