[gmx-users] Gromacs GPU system question

Szilárd Páll szilard.pall at cbr.su.se
Mon Jun 24 16:42:26 CEST 2013

I strongly suggest that you consider the single-chip GTX cards instead
of a dual-chip one; from the point of view of price/performance you'll
probably get the most from a 680 or 780.

You could ask why, so here are the reasons:
- The current parallelization scheme requires domain-decomposition to
use more than one GPU and the overhead of domain-decomposition is
quite high, so you typically get only 1.5-1.7x when going from one to
two domains (=GPUs, but you'll see that same with running CPUs only as
- GROMACS uses the GPU as a coprocessor and needs to transfer
coordinates to the GPU and forces back; if your PCI-E is shared by two
GPUs which will inherently try to transfer at the same time, you'll
the overhead of transferring will get rather high (15% or more).


On Sat, Jun 22, 2013 at 5:31 PM, Mare Libero <mareliber27 at yahoo.com> wrote:
> Hello,
> I am assembling a GPU workstation to run MD simulations, and I was wondering if anyone has any recommendation regarding the GPU/CPU combination.
> From what I can see, the GTX690 could be the best bang for my buck in terms of number of cores, memory, clock rate. But being a dual GPU card, I was wondering if  there is any latency issue that could make its performances less favorable with respect to a GTX Titan.
> Also, which motherboard, CPU is recommendable for this system.
> Thank you in advance for you help,
> Al
> --
> gmx-users mailing list    gmx-users at gromacs.org
> http://lists.gromacs.org/mailman/listinfo/gmx-users
> * Please search the archive at http://www.gromacs.org/Support/Mailing_Lists/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/Support/Mailing_Lists

More information about the gromacs.org_gmx-users mailing list