How can I run my own CUDA code?

I have a ptx, and a cu files and I want to implement into my code but I dont know how.

I have read this section but I dont understand how can I call my code

https://www.mathworks.com/help/parallel-computing/run-cuda-or-ptx-code-on-gpu.html#bsic5ih-1

I have created a kernel:

like this:

k = parallel.gpu.CUDAKernel('kernel.ptx','kernel.cu');

and that's all

here is the inputs what use the cuda code:

limit = 50;
m = 4;

and here is how can I call

kernel<<<grid, block>>>(surfacePoints, d_surface_x, d_surface_y, d_surface_z,

                                             d_electrodes_x, d_electrodes_y, d_electrodes_z,

                                             d_potential, d_laplacian, d_mX, limit, m)

So my problem is, how can I implement a cuda code into the matlab script use that values (the d_ values are known)

Answer 1

[Edric Ellis]

To call the kernel, you must first set up the ThreadBlockSize and GridSize properties of k. See this page for more https://www.mathworks.com/help/parallel-computing/cudakernel.html . Then, you call the feval method, supplying either standard MATLAB arrays or gpuArray data for each input. something a little bit like this:

k.ThreadBlockSize = <>;
k.GridSize = <>;
feval(k, d_surface_x, ... % d_surface_x is a standard array or a gpuArray
    ... % more inputs
    limit, m);

There is another option instead of using CUDAKernel that might be more appropriate: use cudamex instead.

[Question Mr]

Thank you!