stuntprogrammer

  using SomeVec = Vector<T>
  for (size_t i=0; i<n; ++i) {
    for (size_t j=0; k<n; j+=SomeVec::size()) {
      SomeVec c_ij = A[i][0] * SomeVec(&B[0],j, Aligned);
      for (size_t k = 1; k < n; ++k) {
        c_ij += A[i][k] * SomeVec(&N[k][j], Aligned);
      }
      c_ij.store(&C[i][j], Aligned);
    }
  }