Hello,
Currently I’m trying to use CUDA on Xen VM, with Passthrough.
After all setting, guest VM can recognize the nvidia graphic card.
root@ubuntu:~# lspci | grep NVIDIA
00:05.0 VGA compatible controller: NVIDIA Corporation Device 1180 (rev a1)
00:06.0 Audio device: NVIDIA Corporation Device 0e0a (rev a1)
However, for running CUDA, it shows an error message.
root@ubuntu:~# nvidia-smi
NVIDIA: could not open the device file /dev/nvidia0 (Input/output error).
Failed to initialize NVML: Unknown Error
root@ubuntu:~# dmesg | tail
[60538.989544] NVRM: RmInitAdapter failed! (0x23:0x2f:674)
[60538.989551] NVRM: rm_init_adapter(0) failed
However, there exist “nvidia” on the module list and nvidia0 on the /dev directory.
root@ubuntu:~# lsmod | grep nvidia
nvidia 12319300 0
root@ubuntu:~# ls /dev/nvidia*
/dev/nvidia0 /dev/nvidiactl
Does anyone know the reason?
Thank you.
Dongjin Kim
_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel
