5

I have an ESXi 4.1 running on hardware that can run 4 16-lane PCI-e cards. I would like to have access to the underlying hardware from a Linux VM, to run some CUDA programs.

So far all I can see from inside of Linux VM is the generic VMware video card. I installed VMware tools, and lspci still gives me the same VGA compatible controller: VMware SVGA II Adapter.

Is it at all possible to access CUDA devices from a VM guest?

user9517
  • 114,104
  • 20
  • 206
  • 289
Marcin
  • 2,281
  • 1
  • 16
  • 14

2 Answers2

2

If your system is fully AMD-Vi or VT-d compliant then you should be able to go into the host's advance settings and 'pass through' the device/s to a given VM. This isn't certain to work or be stable but does work for quite a lot of kit, though it stops things like vMotion/FT/HA working properly if that matters to you. I'd say give it a go but if it doesn't work, well it doesn't work ok.

edit - here's grab of where to look;

enter image description here

So it's host/Configuration, Advanced Settings then choose 'Configure Passthrough' - you're on your own from there though as I haven't done this with a GPU.

Chopper3
  • 100,240
  • 9
  • 106
  • 238
  • BIOS is updated, all the VT-x/VT-d are enabled. How do you pass-through a video card in ESXi? I thought that's what vmware-tools do. – Marcin Feb 25 '11 at 22:21
  • Like I said it's under the advanced settings for the host when using the VSClient. I'll try to post some images on Monday. – Chopper3 Feb 26 '11 at 11:35
  • I configured the video cards to do passthrough, however I still do not see them inside of the VM, or cannot add them to the VM in VM guest settings as a video card or as a PCI device (they're grayed out). Are there any other tricks I should be aware of? – Marcin Feb 28 '11 at 14:51
  • No, sorry, there's very limited support for this function to be honest, pretty much just NICs really, sorry dude, at least your tried. – Chopper3 Feb 28 '11 at 16:34
1

We are running several ESXi servers at university. I was not able to pass through a GPU to a VM (Windows, Linux) to run a CUDA program. If you want to share / use a GPU in one or many VMs, please have a look at NVIDIA Grid. For more information please review:

semm0
  • 238
  • 1
  • 6