Changes

int j = blockIdx.x * blockDim.x + threadIdx.x; int i = blockIdx.y * blockDim.y + threadIdx.y; // removes from instructions because no need to do this NX amount of times float total = c*dt / dx;

if (i < nx && j < nx) { // format for coalesced memory access for (int it = 1; it <= nx- 1; it++) { if (i != 0 || i < nx ) { un[i * nx + it-1] = u[i * nx + it-1]; __syncthreads();