running example fail: CUDA driver version is insufficient for CUDA runtime version

Accelerated Computing CUDA CUDA Setup and Installation
1

Hi,

I successfully compiled provided samples after installing cuda toolkit 9.0 via

sudo sh cuda_9.0.176_384.81_linux.run

. But, when I run

./deviceQuery

:

./deviceQuery Starting...

 CUDA Device Query (Runtime API) version (CUDART static linking)

cudaGetDeviceCount returned 35
-> CUDA driver version is insufficient for CUDA runtime version
Result = FAIL

I am using GeForce1060 on Debian 9. I think my cuda version and driver version are ok.

$ nvcc -V
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2017 NVIDIA Corporation
Built on Fri_Sep__1_21:08:03_CDT_2017
Cuda compilation tools, release 9.0, V9.0.176

$ nvidia-smi
Wed Mar  4 14:57:32 2020       
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 390.116                Driver Version: 390.116                   |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|===============================+======================+======================|
|   0  GeForce GTX 106...  Off  | 00000000:01:00.0  On |                  N/A |
| 37%   32C    P8     7W / 130W |    439MiB /  6075MiB |      0%      Default |
+-------------------------------+----------------------+----------------------+

Any suggestion? Thank you!

2

Hello, i am also facing the same problem. How did you solved this error ? Please share your views. Thanks in advance.

3

Hi, I think I had to install both toolkit and the cuda driver from the same runfile, other than separately. Good luck.