Re: Some trouble to use NVIDIA CUDA with Xen

[Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>]

On Tue, Aug 13, 2013 at 09:59:48PM +0200, Martin Cerveny wrote:
> Hello.
> 
> 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:
> >8eaffa67b43e99ae581622c5133e20b0f48bcef1
> >c79c49826270b8b0061b2fca840fc3f013c8a78a
> >
> >And apply this patch:
> >
> >https://lkml.org/lkml/2012/2/10/229
> >
> >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).

Did you revert the other two git commits?
> 
> 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