GPU Computing

cancel
Showing results for 
Search instead for 
Did you mean: 

CUDA driver error -359631 when running Multi-channel FFT example

Thanks for all the helpful info!

0 Kudos
Message 11 of 13
(1,423 Views)

I finally got this example working after I upgraded to a newer GPU (Quadro P2200). The newer graphics card has a driver that is compatible with CUDA 10.2 and then this vi worked right away. Yay! For others trying to track down a problem like this, NVIDIA has a web page that lists the latest driver that a certain generation of GPUs are compatible with and then which version of CUDA supports which driver version. My original card had only a Compute Capability of 2.0, confining it to an older driver and an older version of CUDA. For more details, see Tables 1 & 2 in this link:

 

https://docs.nvidia.com/deploy/cuda-compatibility/index.html

0 Kudos
Message 12 of 13
(1,411 Views)

Great sleuthing job!   I had not seen that page before.  I've had problems with users having incompatible display drivers (or older hardware that didn't support the latest drivers) and now I see why:

 

"or example, an application built against the CUDA 3.2 SDK will continue to function even on today’s driver stack. On the other hand, the CUDA runtime does not provide these guarantees. If your application dynamically links against the CUDA 9.2 runtime, it will only work in the presence of the dynamic 9.2 CUDA runtime on the target system. If the runtime was statically linked into the application, it will function on a minimum supported driver, and any driver beyond"

Looks like static linking would be best for compatibility. Also for compatibility I've noticed that I need to specify the all the GPUs that the application will be compatible with using the arch and code compiler flags like this:

--generate-code arch=compute_53,code=sm_53

https://docs.nvidia.com/cuda/cuda-compiler-driver-nvcc/index.html#options-for-steering-gpu-code-gene...

 

 

 

 

0 Kudos
Message 13 of 13
(1,401 Views)