using namespace std;

__global__ void matrixKernel(float* a, float* b, float dcent, int n, int m, int xmin, int xmax,

int ymin, int ymax, float dx, float dy, float dxxinv, float dyyinv) {//MODIFY to suit algorithm

}

// Set grid size and number of iterations

const int save_iters = 20;

dim3 dGrid(nblocks);

dim3 dBlock(1024);

// Carry out Jacobi iterations

for (k = 1; k <= total_iters; k++) {

}

}

cudaMemcpy(a, d_a, n* m * sizeof(float), cudaMemcpyDeviceToHost);

outputImage("jacobi out", a);