bn_reduce_once_in_place
bn_reduce_once_in_place(result_norm, /*carry=*/0, m_norm, tmp, 16);
bn_reduce_once_in_place(result, /*carry=*/0, m, tmp, 8);
bn_reduce_once_in_place(res1, /*carry=*/0, m1, storage, factor_size);
bn_reduce_once_in_place(res2, /*carry=*/0, m2, storage, factor_size);