How to dynamically allocate arrays inside a kernel?

Question

I need to dynamically allocate some arrays inside the kernel function. How can a I do that?

My code is something like that:

__global__ func(float *gr         


        

Answer 1

Maybe you should test

cudaMalloc(&foo,sizeof(int) * ARRAY_SIZE * ITERATIONS);
cudaFree(foo);

instead

for (int i = 0; i < ITERATIONS; ++ i) {
    if (i == 1) cuda_malloc_timer.start(); // let it warm up one cycle
    int * foo;
    cudaMalloc(&foo, sizeof(int) * ARRAY_SIZE);
    cudaFree(foo);
}