CUDA

(Compute Unified Device Architecture) is NVIDIA’s platform for using GPUs to perform general-purpose computations, not just graphics.

CUDA works as long as nvidia-smi sees the GPU and the driver is installed. OpenGL or graphics output isn’t required for CUDA compute tasks.

You can compile CUDA code without a nvidia cards, but you won’t be able to execute it withtout the proper driver.

# Testing CUDA ⮺

Check that CUDA toolkit is installed

$ nvcc --version

# if above is missing
$ sudo apt install nvidia-cuda-toolkit

Install CUDA Samples

$ git clone https://github.com/NVIDIA/cuda-samples.git
$ mkdir build && cd build
$ cmake ..
$ make deviceQuery

# test
$ ./Sample/1_Utilities/deviceQuery/deviceQuery
# If this require sudo (to fix nodevice found) there is a permission issue

see

Written on October 1, 2026, Last update on
nvidia cuda gpu