[torquedev] GPU Hardware

Troy Baer tbaer at utk.edu
Thu Oct 21 10:16:54 MDT 2010

On Thu, 2010-10-21 at 09:58 -0600, Ken Nielson wrote:
> We would like to know what kind of GPU hardware is deployed in your data 
> centers so we can better understand what we need to do to provide GPU 
> support in TORQUE.
> If you currently have GPUs deployed would you please reply and let us 
> know the details of the hardware and any other information you think is 
> relevant.

We currently have one system currently in production with GPUs and
another arriving in the next couple weeks.  The system currently in
production is an SGI Altix UV1000, which has 4 Nvidia S2050 units (i.e.
16 GPUs total) attached to it; that system operates as a single system
image, and is perhaps a little unusual in that the GPUs are intended
primarily for remote vidualization service rather than GPGPU computing.
The system on the way is a 120-node cluster of some breed with 3
Fermi-generation GPUs per node, but I don't recall the specifics of
either the nodes or the GPUs.

Troy Baer, HPC System Administrator
National Institute for Computational Sciences, University of Tennessee
Phone:  865-241-4233

More information about the torquedev mailing list