[Xen-users] Direct somU access to GPGPU do-able?

[Carsten Aulbert <carsten.aulbert@xxxxxxxxxx>]

Hi all,

Ive searched the archives and FAQ but found nothing but an email from last 
week on this list which seem to remotely touch this subject.

I've asked the same to the KVM folks, so if you virtualize yourself with 
different approaches, you might recognize the rest:

We are running a largish cluster and are currently buying GPGPU systems (Tesla 
and soon Fermi based). We will have at least 2 possibly 4 of these cards per 
box and have the problem that some codes need different CUDA kernel drivers to 
run. As these boxes have 4 CPU cores, 12 GB of memory and CPU-VT support we 
thought that this might be solvable by creating (para-) virtualized guests on 
the boxes and passing one GPGPU device into a guest at a time. In there we 
then can run any kernel/driver combo necessary. All OS stuff will be Linux 
(Debian Lenny currently).

But since my current virtualization experience only stretches to OpenVZ and 
VirtualBox (tinkering with Xen a couple of years back), I don't know if Xen 
can help here. We need something which we can automatically set-up 
via CLI, i.e. starting and stopping the guests need to be fully automatic, we 
don't need a graphical environment within the guests, just plain text is good 
enough.

What do you think, is looking into Xen the right choice for this? Can we pass 
a device directly into a guest and fully use it there?

Thanks a lot in advance

Carsten

_______________________________________________
Xen-users mailing list
Xen-users@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-users