[Openstack-operators] state of gpu processing / passthrough

Simon Pasquier spasquier at mirantis.com
Thu Oct 16 15:34:51 UTC 2014

Hello Joe,

Yes GPU passthrough is implemented with Xen [1] and it works with NVIDIA.
I've copied Guillaume that developed and tested the feature for the XLcloud
project, he may be able to provide more details. Bob Ball from Citrix even
made a blog post about it [2].

I know that at the time being, Guillaume had difficulties to do GPU
passthrough with NVIDIA cards and libvirt/KVM. This may have changed though.


[1] https://blueprints.launchpad.net/nova/+spec/pci-passthrough-xenapi

On Thu, Oct 16, 2014 at 5:22 PM, Joe Topjian <joe at topjian.net> wrote:

> Hi all,
> I did a standard google search and got a bunch of wiki pages, but I'm not
> sure if they are stale.
> Does anyone know what the state of GPU processing is in OpenStack? I could
> have swore I read it was available for Xen, but what about KVM?
> Is anyone doing it? If so, what hardware are you using?
> Thanks,
> Joe
> _______________________________________________
> OpenStack-operators mailing list
> OpenStack-operators at lists.openstack.org
> http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack-operators
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.openstack.org/pipermail/openstack-operators/attachments/20141016/fc4ba184/attachment.html>

More information about the OpenStack-operators mailing list