[gmx-users] Benchmarks

[Nathan Moore]

I've been testing my compilation of GROMACS to the published benchmarks on
the GROMACS website.  according to the data on the web, Villin finishes on
an 1.25 Ghz G4 machine with a time of 2048 seconds.

My powerbook finishes Villin (0.0002 ns timestep, 5000 steps) in roughly
700 seconds,

              NODE (s)   Real (s)      (%)
       Time:    701.240    715.000     98.1
                       11:41
               (Mnbf/s)   (MFlops) (ps/NODE hour) (NODE hour/ns)
Performance:      6.758    211.844     51.338     19.479
Finished mdrun on node 0 Tue Jun  7 11:56:05 2005

Am I to believe that my 867 MHz is 10-20x faster than an Apple G5
compiling Xlc?

Do I understand correctly that the columns on the serial benchmark page
are execution times where a lower number is better?  I used the files
available on the benchmarks portion of gromacs.org and attach my log file
from the run to this email.

regards,

nt moore
-------------- next part --------------
A non-text attachment was scrubbed...
Name: villin.log
Type: application/octet-stream
Size: 12261 bytes
Desc: not available
URL: <http://maillist.sys.kth.se/pipermail/gromacs.org_gmx-users/attachments/20050607/1eba5d4c/attachment.obj>