Basic CUDA kernel construct.

cuda

// Copyright (c) 2015 Radovan Bast
// Licensed under the MIT license - http://opensource.org/licenses/MIT

__global__ void foo_kernel(int n,
                           double *a,
                           double *b,
                           double *c)
{
    int tid = threadIdx.x + blockIdx.x*blockDim.x;

    while (tid < n) {
        c[tid] = a[tid]*b[tid];
        tid += blockDim.x*gridDim.x;
    }
}