Is there an easy way of parallel processing with GPU with a defined python function?

Question

First of all, I've read multiple forums, papers and articles in the subject. I had not had the need to implement the use of a GPU in my processes, however they have become more robust. The problem is that I have a somewhat complex function created in python, vectorized in numpy and using @jit to make it run faster.

However, my GPU (AMD) does not show use in the task panel (0%). I have seen PyOpenCL, however I want to know if there is something simpler than translating the code. The function is fast, the problem is that I want to use parallel processing to iterate that function 18 million times which currently takes me 5 hours into multiple proceso, I know that I can use multiprocessing on the CPU, but I want to use my GPU, there is some 'easy' way to split the task on the GPU?

question from:https://stackoverflow.com/questions/65924564/is-there-an-easy-way-of-parallel-processing-with-gpu-with-a-defined-python-funct

Answer 1

We had some discussion, whether Numba can compile code for GPU automatically. I think it was able to, but now this is deprecated way. The other approach is to use @numba.cuda.jit and write code in terms of CUDA blocks, threads and so on. It works well. With it you enter big and fascinating (I am not joking) world of CUDA programming. You can maybe parallelize running of your big function with different parameters. Maybe you will even not need to rewrite it itself for this...