I’m working on openCV software using CUDA function. I’m struggling having it works on the GPU. In the way to solve the issue I built some demo software coming from CUDA installation. One of these programs was deviceQuery (pretty simple). Finally, I also tried prebuilt version of the same program. For all my tries, I got the following error.

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

cudaGetDeviceCount returned 3
→ initialization error
Result = FAIL

What is the source of this error ?

Thank you