[gmx-users] Benchmarks

[David]

On Tue, 2005-06-07 at 13:46 -0500, Nathan Moore wrote:
> 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.
> 
No, the numbers are ps/day, in your case you want to multiply 51.3 by
24, to get roughly 1200 ps/day.



> regards,
> 
> nt moore
> _______________________________________________ gmx-users mailing list gmx-users at gromacs.org http://www.gromacs.org/mailman/listinfo/gmx-users Please don't post (un)subscribe requests to the list. Use the www interface or send it to gmx-users-request at gromacs.org.
-- 
David.
________________________________________________________________________
David van der Spoel, PhD, Assoc. Prof., Molecular Biophysics group,
Dept. of Cell and Molecular Biology, Uppsala University.
Husargatan 3, Box 596,          75124 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
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++