[gmx-users] Woodcrest results
vipin at cs.unm.edu
Tue Apr 10 19:27:27 CEST 2007
Considering that you are running 4 MPI processes on 4 cores/2 chips
system, don't you think the title of the page of the benchmarks is
misleading -- "Single processor benchmarks" ? Also, won't we get better
performance with running threads. I believe the 2 chips are connected
through a front side bus and has a globally coherent memory
shared among the 2 chips ?
On Tue, 10 Apr 2007, David van der Spoel wrote:
> vipin sachdeva wrote:
>> So on the single processor page, the results are mentioned for woodcrest,
>> which had 4 physical cores. I want to confirm that the results are by
>> running 4 threads rather than 1 thread?
>> Also the cache mentioned is 6 MB. Is that per 2 cores or for all the 4
>> cores ?
> Since it is a mac pro it is two cpus with two cores each. since it says 4
> cores, the simulations were run on 4 cores using MPI, not threads.
> 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://folding.bmc.uu.se
> gmx-users mailing list gmx-users at gromacs.org
> Please search the archive at http://www.gromacs.org/search before posting!
> Please don't post (un)subscribe requests to the list. Use the www interface
> or send it to gmx-users-request at gromacs.org.
> Can't post? Read http://www.gromacs.org/mailing_lists/users.php
More information about the gromacs.org_gmx-users