Hello All!
I have a Ubuntu 14.04 running CUDA 7.0 with GTX 980 (4GB) and everything was fine until we decided we need more memory on the GTX 980 card.
So we bought GTX 980 Ti (6GB) and thought it was just to change cards.
But after the change we are running in to problems.
Command nvidia-smi reports back on all categories except “Name” where it gives msg “ERR!”.
When we try to run sample “deviceQuery” we get msg:
—>8—
…./deviceQuery Starting…
CUDA Device Query (Runtime API) version (CUDART static linking)
cudaGetDeviceCount returned 38
→ no CUDA-capable device is detected
Result = FAIL
—>8—
We have tried to uninstall CUDA toolkit and reinstall it but same problem.
Any ideas what we have missed?
TTFN
//paus
Some extra system info:
smn1:/# ls -al /dev/nvi*
crw-rw-rw- 1 root root 195, 0 Jun 15 15:55 /dev/nvidia0
crw-rw-rw- 1 root root 195, 255 Jun 15 15:55 /dev/nvidiactl
smn1:/# lsmod | grep -i nvi*
nvidia 8370774 0
drm 310796 2 nvidia
smn1:/# modinfo nvidia
filename: /lib/modules/3.16.7-ckt10snm-gpu-3.16.0/kernel/drivers/video/nvidia.ko
alias: char-major-195-*
version: 346.46
supported: external
license: NVIDIA
alias: pci:v000010DEd00000E00svsdbc04sc80i00*
alias: pci:v000010DEd00000AA3svsdbc0Bsc40i00*
alias: pci:v000010DEdsvsdbc03sc02i00
alias: pci:v000010DEdsvsdbc03sc00i00
depends: drm
vermagic: 3.16.7-ckt10snm-gpu-3.16.0 SMP mod_unload modversions
parm: NVreg_Mobile:int
—>8—