#include <bits/stdc++.h>
//#include <ext/pb_ds/assoc_container.hpp>
//#include <ext/pb_ds/tree_policy.hpp>
using namespace std;
//using namespace __gnu_pbds;

// #pragma GCC optimize("O3,unroll-loops")
// #pragma GCC target("avx2")
#define watch(x) cout<<(#x)<<"="<<(x)<<'\n'
#define mset(d,val) memset(d,val,sizeof(d))
#define cbug if(DEBUG) cout
#define setp(x) cout<<fixed<<setprecision(x)
#define sz(x) (int)(x).size()
#define all(x) begin(x), end(x)
#define forn(i,a,b) for(int i=(a);i<(b);i++)
#define rep(i,a,b) for(int i=(a);i<(b);i++)
#define fore(i,a,b) for(int i=(a);i<=(b);i++)
#define pb push_back
#define F first
#define S second
#define fbo find_by_order
#define ook order_of_key
typedef long long ll;
typedef long double ld;
typedef pair<ll,ll> ii;
typedef vector<ll> vi;
typedef vector<ii> vii;
//template<typename T>
//using pbds = tree<T, null_type, less<T>, rb_tree_tag, tree_order_statistics_node_update>;
void SD(int t=0){ cout<<"PASSED "<<t<<endl; }
ostream& operator<<(ostream &out, ii x){ out<<"("<<x.F<<","<<x.S<<")"; return out; }
template<typename T> void amax(T &a, T b){ a=max(a,b); }
template<typename T> void amin(T &a, T b){ a=min(a,b); }
struct Hash {
    static uint64_t splitmix64(uint64_t x) {
        // http://xorshift.di.unimi.it/splitmix64.c
        x += 0x9e3779b97f4a7c15;
        x = (x ^ (x >> 30)) * 0xbf58476d1ce4e5b9;
        x = (x ^ (x >> 27)) * 0x94d049bb133111eb;
        return x ^ (x >> 31);
    }
    size_t operator()(uint64_t x) const {
        static const uint64_t FIXED_RANDOM = chrono::steady_clock::now().time_since_epoch().count();
        return splitmix64(x + FIXED_RANDOM);
    }
};

const ll INF = ll(1e18);
const int MOD = 998244353;
const bool DEBUG = 0;
const int MAXN = 100005;
const int LG = 21;

vector<ll> fact,ifact,inv,pow2;
ll add(ll a, ll b, ll m = MOD)
{
	a+=b;
	if(abs(a)>=m) a%=m;
	if(a<0) a+=m;
	return a;
}
ll mult(ll a, ll b, ll m = MOD)
{
	if(abs(a)>=m) a%=m;
	if(abs(b)>=m) b%=m;
	a*=b;
	if(abs(a)>=m) a%=m;
	if(a<0) a+=m;
	return a;
}
void radd(ll &a, ll b, ll m = MOD){ a=add(a,b,m); }
void rmult(ll &a, ll b, ll m = MOD){ a=mult(a,b,m); }
ll pw(ll a, ll b, ll m = MOD)
{
	assert(b >= 0);  // can return 0 if desired
	if(abs(a)>=m) a%=m;
	if(a==0 && b==0) return 0; // value of 0^0
	ll r=1;
	while(b){
		if(b&1) r=mult(r,a,m);
		a=mult(a,a,m);
		b>>=1;
	}
	return r;
}
ll inverse(ll a, ll m = MOD)
{
	return pw(a,m-2);
}
ll choose(ll a, ll b)
{
	if(a<b) return 0;
	if(b==0) return 1;
	if(a==b) return 1;
	return mult(fact[a],mult(ifact[b],ifact[a-b]));
}
void init(ll _n)
{
	fact.clear(); ifact.clear(); inv.clear(); pow2.clear();
	fact.resize(_n+1); ifact.resize(_n+1); inv.resize(_n+1); pow2.resize(_n+1);
	pow2[0]=1; ifact[0]=1; fact[0]=1;
	for(int i=1;i<=_n;i++){
		pow2[i]=add(pow2[i-1],pow2[i-1]);
		fact[i]=mult(fact[i-1],i);
	}
	ifact[_n] = inverse(fact[_n]);
	for(int i=_n-1;i>=1;i--){
	    ifact[i] = mult(ifact[i+1], i+1);
	}
	for(int i=1;i<=_n;i++){
	    inv[i] = mult(fact[i-1], ifact[i]);
	}
}

const ll mod = (119 << 23) + 1, root = 62; // = 998244353
// For p < 2^30 there is also e.g. 5 << 25, 7 << 26, 479 << 21
// and 483 << 21 (same root). The last two are > 10^9.
typedef vector<ll> vl;
ll modpow(ll b, ll e) {
	ll ans = 1;
	for (; e; b = b * b % mod, e /= 2)
		if (e & 1) ans = ans * b % mod;
	return ans;
}
void ntt(vl &a) {
	int n = sz(a), L = 31 - __builtin_clz(n);
	static vl rt(2, 1);
	for (static int k = 2, s = 2; k < n; k *= 2, s++) {
		rt.resize(n);
		ll z[] = {1, modpow(root, mod >> s)};
		rep(i,k,2*k) rt[i] = rt[i / 2] * z[i & 1] % mod;
	}
	vi rev(n);
	rep(i,0,n) rev[i] = (rev[i / 2] | (i & 1) << L) / 2;
	rep(i,0,n) if (i < rev[i]) swap(a[i], a[rev[i]]);
	for (int k = 1; k < n; k *= 2)
		for (int i = 0; i < n; i += 2 * k) rep(j,0,k) {
			ll z = rt[j + k] * a[i + j + k] % mod, &ai = a[i + j];
			a[i + j + k] = ai - z + (z > ai ? mod : 0);
			ai += (ai + z >= mod ? z - mod : z);
		}
}
vl conv(const vl &a, const vl &b) {
	if (a.empty() || b.empty()) return {};
	int s = sz(a) + sz(b) - 1, B = 32 - __builtin_clz(s), n = 1 << B;
	int inv = modpow(n, mod - 2);
	vl L(a), R(b), out(n);
	L.resize(n), R.resize(n);
	ntt(L), ntt(R);
	rep(i,0,n) out[-i & (n - 1)] = (ll)L[i] * R[i] % mod * inv % mod;
	ntt(out);
	return {out.begin(), out.begin() + s};
}

vi pw(vi a, ll b)
{
	assert(b >= 0);  // can return 0 if desired
	vi r{1};
	while(b){
		if(b&1) r=conv(r,a);
		a=conv(a,a);
		b>>=1;
	}
	return r;
}

int main()
{
    cin.tie(0)->sync_with_stdio(0);

    ll n,m; cin>>n>>m;
    init(n * m);
    vi v(m + 1);
    fore(i,0,m)
    {
        ll mCi = choose(m, i);
        v[i] = mult(mult(mCi, mCi), fact[i]);
    }
    vi r = pw(v, n);
    ll ans = 0;
    forn(i,0,sz(r))
    {
        ll k = n * m - i;
        ll inc = 1;
        rmult(inc, r[i]);
        rmult(inc, fact[k]);
        if (i & 1) inc = -inc;
        radd(ans, inc);
    }
    cout << ans << '\n';

    return 0;
}