[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Xen-devel] Some trouble to use NVIDIA CUDA with Xen


On Mon, 12 Aug 2013, Konrad Rzeszutek Wilk wrote:
On Mon, Aug 12, 2013 at 01:33:13PM +0100, Gordan Bobic wrote:
Your Nvidia device ID seems to imply a GTX770.
I could be wrong, but wasn't this only supported on Quadro/Grid GPUs?
Or is that limitation only applicable to Windows?

I did not try to use it in "multios" (domU) environment (only simple Dom0).

NVRM: PAT configuration unsupported.
Right, so there are couple of patches that can enable that back.

You need to revert these two:

And apply this patch:


That should re-enable PAT.  Try that and please report back.

I applied the patch to 3.9.11-200.PAT.fc18.x86_64 (3.10 is not working due to incompatibilities with nvidia driver source code).

Error persists:
"NVRM: PAT configuration unsupported."

There is one progress at least.
The tested programs are working in "normal speed" (as without Xen)
- speedup 20x to compare with non-patched kernel on Dom0.

The CUDA error still persists:

# /usr/bin/time ./bandwidthTest
[CUDA Bandwidth Test] - Starting...
Running on...

 Device 0: GeForce GTX 770
 Quick Mode

CUDA error at bandwidthTest.cu:719 code=46(cudaErrorDevicesUnavailable) "cudaEventCreate(&start)"

0.00user 0.20system 0:00.26elapsed 79%CPU (0avgtext+0avgdata 5236maxresident)k
0inputs+0outputs (0major+1182minor)pagefaults 0swaps

I reported the problem to NVIDIA too and waiting for solution.

Any other hint ?

Thanks, Martin Cerveny

Xen-devel mailing list



Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.