[gmx-users] Poor GPU Performance with GROMACS 5.1.4

[Szilárd Páll]

On Thu, May 25, 2017 at 2:09 PM, Marcelo Depólo <marcelodepolo at gmail.com> wrote:
> Hi,
>
>
> I had the same struggle benchmarking a similar system last week. Just for
> curiosity, could you tell us the performance you get when sharing your GPU
> with multiple jobs?

BTW, interpreting some performance number is not not always
straightforward as it depends on both CPU/GPU hardware, type of
simulation and settings and it will vary somewhat GROMACS release (the
last release brought several related improvements).

As examples/references you can have a look at these results:
Slide 56 of https://goo.gl/7DnSri
Fig 5 of http://doi.wiley.com/10.1002/jcc.24030  (or
http://arxiv.org/abs/1507.00898)

Therefore, I suggest that you try it yourself, if you have multiple
runs to do either sequentially or all in parallel, try 1-8-way
concurrency (given your 8-core CPU) and pick what's best for you!

Cheers,
--
Szilárd

>
> In my case (6k atoms + Reaction field + 8 cores 2.2Ghz + TitanX Pascal),
> I've got ~440 ns/day. However, I get ~280 ns/day running 2 jobs and sharing
> the GPU.
>
> Cheers!
> --
> Marcelo
> --
> Gromacs Users mailing list
>
> * Please search the archive at http://www.gromacs.org/Support/Mailing_Lists/GMX-Users_List before posting!
>
> * Can't post? Read http://www.gromacs.org/Support/Mailing_Lists
>
> * For (un)subscribe requests visit
> https://maillist.sys.kth.se/mailman/listinfo/gromacs.org_gmx-users or send a mail to gmx-users-request at gromacs.org.