In particular I'd like to more carefully choose gpu card (and number of
cards) as well as CPU


1) In case of GPU I have to possible options
2 x GeForce 680 (256 bit, 4gb ram ) or 1 x  Geforce 690 (320 bit, 6 gb ram).
>From what option the best performance should be expected ? What GPU's
parameters would be most crucial for simulations ?

2) In case of CPU I'd like to use Core i7 (4 cores). Should the performance
with that CPU be better than with Core I5 ( also 4 cores) ?

3) Any other setups ? (e.g based on the server-like hardware Xeon CPU )
Could also someone provide me with some bechmark tests of new Gromacs 4.6
with different hardware setups ?

Thanks for help

James

2013/5/24 James Starlight <jmsstarli...@gmail.com>

> Dear Gromacs Users!
>
>
> I'd like to build new workstation for performing simulation on GPU with
> Gromacs 4.6 native cuda support.
> Recently I've used such setup with  Core i5 cpu and nvidia 670 GTX video
> and obtain good performance ( ~ 20 ns\day for typical 60.000 atom system
> with SD integrator)
>
>
> Now I'd like to build multi-gpu wokstation.
>
> My question - How much GPU would give me best performance on the typical
> home-like workstation. What algorithm of Ncidia GPU integration should I
> use (e.g SLI etc) ?
>
>
> Thanks for help,
>
>
> James
-- 
gmx-users mailing list    gmx-users@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-requ...@gromacs.org.
* Can't post? Read http://www.gromacs.org/Support/Mailing_Lists

Reply via email to