The first important thing is that I think non-CUDA devices are still not
supported by AMBER, or for instance NAMD. Although they are supported by
OpenMM and I think LAMMPS.
Concerning the performance due to GPU to MB bandwidth, I think it's
probably only a major concern with a package like NAMD, that splits the
load between the GPU and the CPU and therefore requires communication back
and forth at each timestep, whereas AMBER and OpenMM for instance are
purely on the GPU, so I can't see that this bandwidth would have any effect
unless you were doing something crazy like writing out trajectories or
energy information every step.
Could be wrong though,
~Aron
On Thu, Feb 28, 2013 at 9:53 PM, Jonathan Gough
<jonathan.d.gough.gmail.com>wrote:
> While doing some window shopping I noticed that the current AMD chipset
> doesn't support PCI-E 3.0 x16 while Intel does. Muy understanding is this
> would/does have an impact on the communication speed between the GPU and
> the MOBO, but would that (or does anyone know if it does) have an effect on
> the overall simulation speed (GPU-intercommunication)?
>
> Apparently ASUS recently launched a MOBO that has an onboard chip to
> compensate or cover the distance(?) such that 3.0 bandwidth is possible.
> That being said I wonder if and how that might interfere with calculations.
>
> any thoughts?
> JOnathan
> _______________________________________________
> AMBER mailing list
> AMBER.ambermd.org
> http://lists.ambermd.org/mailman/listinfo/amber
>
--
Aron Broom M.Sc
PhD Student
Department of Chemistry
University of Waterloo
_______________________________________________
AMBER mailing list
AMBER.ambermd.org
http://lists.ambermd.org/mailman/listinfo/amber
Received on Thu Feb 28 2013 - 21:30:03 PST
