#include <bits/stdc++.h>
using namespace std;
// #include <atcoder/all>
// using namespace atcoder;

// #define int long long
#define rep(i, n) for (int i = (int)(0); i < (int)(n); ++i)
#define reps(i, n) for (int i = (int)(1); i <= (int)(n); ++i)
#define rrep(i, n) for (int i = ((int)(n)-1); i >= 0; i--)
#define rreps(i, n) for (int i = ((int)(n)); i > 0; i--)
#define irep(i, m, n) for (int i = (int)(m); i < (int)(n); ++i)
#define ireps(i, m, n) for (int i = (int)(m); i <= (int)(n); ++i)
#define irreps(i, m, n) for (int i = ((int)(n)-1); i > (int)(m); ++i)
#define SORT(v, n) sort(v, v + n);
#define REVERSE(v, n) reverse(v, v+n);
#define vsort(v) sort(v.begin(), v.end());
#define all(v) v.begin(), v.end()
#define mp(n, m) make_pair(n, m);
#define cinline(n) getline(cin,n);
#define replace_all(s, b, a) replace(s.begin(),s.end(), b, a);
#define PI (acos(-1))
#define FILL(v, n, x) fill(v, v + n, x);
#define sz(x) (int)(x.size())

using ll = long long;
using vi = vector<int>;
using vvi = vector<vi>;
using vll = vector<ll>;
using vvll = vector<vll>;
using pii = pair<int, int>;
using pll = pair<ll, ll>;
using vs = vector<string>;
using vpll = vector<pair<ll, ll>>;
using vtp = vector<tuple<ll,ll,ll>>;
using vb = vector<bool>;
using ld = long double;

template<class T> inline bool chmax(T& a, T b) { if (a < b) { a = b; return 1; } return 0; }
template<class T> inline bool chmin(T& a, T b) { if (a > b) { a = b; return 1; } return 0; }

template<class t> using vc=vector<t>;
template<class t> using vvc=vc<vc<t>>;

const ll INF = 1e9+10;
// const ll MOD = 1e9+7;
const ll MOD = 998244353;
const ll LINF = 1e18;

#define mat vector<vector<ll>>

/// 行列積
mat mat_mul(mat &a, mat &b) {
  mat res(a.size(), vector<ll>(b[0].size()));
  for (int i = 0; i < a.size(); i++) {
    for (int j = 0; j < b[0].size(); j++) {
      for (int k = 0; k < b.size(); k++) {
        (res[i][j] += a[i][k] * b[k][j]) %= MOD;
      }
    }
  }
  return res;
}

/// 行列累乗
mat mat_pow(mat a, long long n) {
  mat res(a.size(), vector<ll>(a.size()));
  // 単位行列で初期化
  for (int i = 0; i < a.size(); i++)
    res[i][i] = 1;
  // 繰り返し二乗法
  while (n > 0) {
    if (n & 1) res = mat_mul(a, res);
    a = mat_mul(a, a);
    n >>= 1;
  }
  return res;
}

signed main()
{
  cin.tie( 0 ); ios::sync_with_stdio( false );
  
  ll n,k; cin>>n>>k;
  mat m(k*k*k,vc<ll>(k*k*k));
  rep(i,k) rep(j,k) rep(l,k){
    // k進数として見る
    // k^2 k^1 k^0 .. 3桁目をh,2桁目をm,1桁目をrの個数に対応させる
    // i*k*k+j*k+lの状態、つまりdp[i][j][k]からの遷移に対応する
    m[(i+1)%k*k*k+j*k+l][i*k*k+j*k+l]++; // 末尾にhを追加
    m[i*k*k+(j+i)%k*k+l][i*k*k+j*k+l]++; // 末尾にmを追加
    m[i*k*k+j*k+(l+j)%k][i*k*k+j*k+l]++; // 末尾にrを追加
  }
  m = mat_pow(m,n);
  ll ans=0;
  rep(i,k) rep(j,k) (ans+=m[i*k*k+j*k][0])%=MOD;
  cout<<ans<<endl;
}