Changes

for (int it = 1; it <= nx - 1; it++) { s[t - 1] = u[(i - 1) * nx + it - 1];

u[it] = s[1]; __syncthreads();

u[i * nx + it] = s[t] - total * (s[t] - s[t - 1]); __syncthreads(); } } }