Hi, I have a code where I use RandomFunction and ParallelTable. Could somebody guide me how to make use of my GPUs for accelerating this computation? I have looked through the CUDA Programming (http://reference.wolfram.com/language/CUDALink/tutorial/Programming.html#135446596) but I do not understand the codes which are later linked through CUDAFunctionLoad.
I believe that if you want to use the GPU for a calculation like this, you basically have to program it yourself in C. Mathematica cannot do such things automatically for you.