#include <bits/stdc++.h>
using namespace std;
#define debug(x) cerr << #x << " == " << x << endl
#define int long long
#define el '\n'
#define fir first
#define sec second
typedef long long ll;
typedef pair<int, int> PII;
const int mod = 998244353;
const int inf = 0x3f3f3f3f;
const int N = 1000020;
ll phi[N], vis[N], prime[N];
ll sum[N];
ll up(ll x)
{
	return (x % mod + mod) % mod;
}
void solve()
{
	int n, k;
	cin >> n >> k;
	vector<ll> ans(n + 1, 0), fac(n + 1, 1);
	vector<ll> dp0(n + 1, 0), dp2(n + 1, 0), dp1(n + 1, 0);
	ll cnt = sum[k];
	for (int i = 1; i <= n; i++) {
		fac[i] = up(fac[i - 1] * (2 * k + 1));
	}
	// cout << cnt << endl;
	dp0[1] = 3, dp1[1] = 2 * cnt + 1, dp2[1] = fac[1];
	for (int m = 2; m <= n; m++) {
		dp0[m] = up(dp0[m - 1] + 2 * dp1[m - 1]);
		dp1[m] = up(2 * cnt * dp2[m - 1] + dp1[m - 1]);
		dp2[m] = fac[m];
		/*ans[m] = ans[m - 1] + 2 * (2 * cnt + 1) % mod * fac[m - 2] % mod;
		ans[m] = up(ans[m]);*/
	}
	cout << dp0[n] << el;
}
signed main()
{
	ios::sync_with_stdio(false);
	cin.tie(nullptr);
	cout.tie(nullptr);
	int T = 1;
	// cin >> T;
	phi[1] = 1;
	int cnt = 0;
	for (int i = 2; i <= 1000000; i++) {
		if (!vis[i]) {
			vis[i] = i;
			prime[cnt++] = i;
			phi[i] = i - 1;
		}
		for (int j = 0; j < cnt; j++) {
			if (i * prime[j] > 1000000)
				break;
			vis[i * prime[j]] = prime[j];
			if (i % prime[j] == 0) {
				phi[i * prime[j]] = phi[i] * prime[j];
				break;
			}
			phi[i * prime[j]] = phi[i] * phi[prime[j]];
		}
	}
	sum[1] = 1;
	for (int i = 2; i <= 1000000; i++) {
		sum[i] = sum[i - 1] + phi[i] * 2;
		sum[i] = up(sum[i]);
	}
	while (T--) {
		solve();
	}
	return 0;
}