CUDA driver version is insufficient for CUDA runtime version despite being on newest drivers

Question

So I have a very similar question to: What can I do against 'CUDA driver version is insufficient for CUDA runtime version'?

When I make and run deviceQuery, I get the exact same error:

./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

Here's my system:

andycui97@andycui97-Z10PE-D8-WS:~$ nvidia-settings -q NvidiaDriverVersion

  Attribute 'NvidiaDriverVersion' (andycui97-Z10PE-D8-WS:0.0): 367.35
  Attribute 'NvidiaDriverVersion' (andycui97-Z10PE-D8-WS:0[gpu:0]): 367.35

andycui97@andycui97-Z10PE-D8-WS:~$ cat /proc/driver/nvidia/version
NVRM version: NVIDIA UNIX x86_64 Kernel Module  367.35  Mon Jul 11 23:14:21 PDT 2016
GCC version:  gcc version 5.4.0 20160609 (Ubuntu 5.4.0-6ubuntu1~16.04.1)

andycui97@andycui97-Z10PE-D8-WS:~$ nvcc -V
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2016 NVIDIA Corporation
Built on Wed_May__4_21:01:56_CDT_2016
Cuda compilation tools, release 8.0, V8.0.26

andycui97@andycui97-Z10PE-D8-WS:~$ nvidia-smi
Sat Jul 16 17:48:19 2016       
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 367.35                 Driver Version: 367.35                    |
|-------------------------------+----------------------+----------------------+
| 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 1070    Off  | 0000:03:00.0      On |                  N/A |
| 27%   39C    P5    12W / 151W |    545MiB /  8106MiB |     31%      Default |
+-------------------------------+----------------------+----------------------+

+-----------------------------------------------------------------------------+
| Processes:                                                       GPU Memory |
|  GPU       PID  Type  Process name                               Usage      |
|=============================================================================|
|    0       900    G   /usr/lib/xorg/Xorg                             241MiB |
|    0      1556    G   compiz                                         140MiB |
|    0      7455    G   ...s-passed-by-fd --v8-snapshot-passed-by-fd   136MiB |
|    0      9861    G   /home/andycui97/.steam/ubuntu12_32/steam        25MiB |
+-----------------------------------------------------------------------------+

So I have a gtx 1070 and I installed cuda 8rc from the runfile for linux 16.04

If I'm not mistaken, my driver version is the absolute latest, literally released a day ago according to http://www.nvidia.com/download/driverResults.aspx/105343/en-us, so I am confused as to how my CUDA driver version is insufficient.

Any help would be appreciated!

Cuda 8 is release candidate at the moment. Driver update system gets newest drivers which are not release candidate compatible. I am having exact same issue on Windows. — Florent DUGUET
So is there an older driver that supports CUDA 8 or do I have to wait? — andycui97
367.27, built it from the runfile on the nvidia website. Seems to work for now.... — andycui97

andycui97 andycui97 · Accepted Answer · 2016-07-19T22:15:24

2

votes

Solution:

Use the runfile from Nvidia site for the slightly older driver, 367.27

CUDA driver version is insufficient for CUDA runtime version despite being on newest drivers

1 Answers