EDIT: The driver saw my card after I ran nvidia-smi. (Which I tried on a whim.)
I’ve installed CUDA on ubuntu as described in this thread. The driver does not seem to recognize my Tesla card. (No /dev/nvidia* files, running the vectorAdd sample program gives the output “no CUDA-capable device is detected,” and deviceQuery says “cudaGetDeviceCount FAILED CUDA Driver and Runtime version may be mismatched.”)
“lspci -q” reports that there is a Tesla C1060 connected, so I am confused. Any suggestions as to what might have gone wrong?
I thought maybe the C1060 is no longer supported, but it is in the “supported nVidia GPU products page” of the 260.19.26 driver manual.
The problem is in some permissions. If you login as root, you may run SDK examples in console without a running X despite there is still no one /dev/nvidia… file.
It works for both sudo and su.