#include <bits/stdc++.h>
#include <atcoder/all>
using namespace std;
using namespace atcoder;
typedef long long int ll;
typedef long double ld;
#define FOR(i,l,r) for(ll i=l;i<r;i++)
#define REP(i,n) FOR(i,0,n)
#define RFOR(i,l,r) for(ll i=r-1;i>=l;i--)
#define RREP(i,n) RFOR(i,0,n)
#define ALL(x) x.begin(),x.end()
#define P pair<ll,ll>
#define F first
#define S second
#define BS(A,x) binary_search(ALL(A),x)
#define LB(A,x) (ll)(lower_bound(ALL(A),x)-A.begin())
#define UB(A,x) (ll)(upper_bound(ALL(A),x)-A.begin())
#define COU(A,x) (UB(A,x)-LB(A,x))
template<typename T>using min_priority_queue=priority_queue<T,vector<T>,greater<T>>;
//using mint=modint1000000007;
using mint=modint998244353;
void chmax(ll&a,ll b){a=max(a,b);}
void chmin(ll&a,ll b){a=min(a,b);}
void print(vector<ll>&A){REP(i,A.size()){if(i)cout<<" ";cout<<A[i];}cout<<endl;}
ll dist(ll sx,ll sy,ll tx,ll ty){return (sx-tx)*(sx-tx)+(sy-ty)*(sy-ty);}
vector<vector<ld>>pro(vector<vector<ld>>A,vector<vector<ld>>B){
  ll N=A.size();
  vector<vector<ld>>res(N,vector<ld>(N));
  REP(i,N)REP(j,N)REP(k,N)res[i][j]+=A[i][k]*B[k][j];
  return res;
}
int main(){
  ll N,M;cin>>N>>M;
  vector<vector<mint>>DP(N+1,vector<mint>(M+1));
  vector<mint>sum(N+1);
  DP[0][0]=1;sum[0]=1;
  REP(i,N){
    DP[i+1]=DP[i];
    sum[i+1]=sum[i];
    FOR(j,1,M+1){
      DP[i+1][j]+=sum[i]-DP[i][j];
      if(i-j+1>=0)DP[i+1][j]+=DP[i-j+1][j]-sum[i-j+1];
    }
    REP(j,M+1)sum[i+1]+=DP[i+1][j]-DP[i][j];
  }
  cout<<(pow_mod(M,N,998244353)-sum[N]+sum[N-1]).val()<<endl;
  return 0;
}