void *compute_gauss(void *threadid){

  int local_row, local_norm, col;
  float multiplier;
  long tid;
  tid = (long)threadid;

  fprintf(stdout, "Thread %ld has startedn", tid);

  while (global_norm < N){

    while (global_row < N) {
      pthread_mutex_lock(&global_row_lock);
      local_row = global_row;
      global_row++;
      pthread_mutex_unlock(&global_row_lock);

      print_inputs();
      multiplier = A[local_row][global_norm] / A[global_norm][global_norm];

      for (col = global_norm; col < N; col++) {
        A[local_row][col] -= A[global_norm][col] * multiplier;
      }

      B[local_row] -= B[global_norm] * multiplier;

    }

    pthread_barrier_wait(&barrier);
    if (tid == 0){
      global_norm++;
      global_row=global_norm+1;
    }
    pthread_barrier_wait(&barrier); // wait until all threads arrive
  }
}