#pragma GCC optimize("O2")
#include <algorithm>
#include <cassert>
#include <cmath>
#include <cstdarg>
#include <cstdio>
#include <cstring>
#include <deque>
#include <iomanip>
#include <iostream>
#include <iterator>
#include <map>
#include <numeric>
#include <queue>
#include <set>
#include <stack>
#include <string>
#include <utility>
#include <vector>

#define whlie while
#define mp make_pair
#define pb push_back
#define eb emplace_back
#define fi first
#define se second
#define inf 1001001001
#define infLL ( (1LL << 61))
#define MOD 998244353
#define FOR(i,a,b) for(int (i)=((int)a); (i)<((int)b); (i)++) // [a,b)
#define rep(i,N) FOR((i), 0, ((int)N)) // [0,N)
#define FORR(i,a,b) for(int (i)=((int)b) - 1; (i)>=((int)a); (i)--)
#define repr(i,N) FORR((i), 0, ((int)N))
#define all(v) (v).begin(),(v).end()
#define rall(v) (v).rbegin(),(v).rend()
#define sz(v) ((int)(v).size())
#define vrep(v,it) for(auto it=v.begin();it!=v.end();it++)
#define vrepr(v,it) for(auto it=v.rbegin();it!=v.rend();it++)
#define inx(t,...) t __VA_ARGS__; in(__VA_ARGS__)
#define ini(...) int __VA_ARGS__; in(__VA_ARGS__)
#define inl(...) ll __VA_ARGS__; in(__VA_ARGS__)
#define inc(...) char __VA_ARGS__; in(__VA_ARGS__)
#define ins(...) string __VA_ARGS__; in(__VA_ARGS__)
#define ind(...) double __VA_ARGS__; in(__VA_ARGS__)
#define inpii(...) pii __VA_ARGS__; in(__VA_ARGS__)
#define invi(v,...) vi v; in(v,##__VA_ARGS__)
#define invl(v,...) vl v; in(v,##__VA_ARGS__)
#define mem(ar,val) memset((ar), (val), sizeof(ar) )
#define mem0(ar) memset((ar),  0, sizeof(ar) )
#define mem1(ar) memset((ar), -1, sizeof(ar) )

#ifdef LOCAL
    #define dbg(...) fprintf(stderr, __VA_ARGS__)
    #define trc(...) do { cout << #__VA_ARGS__ << " = "; dbg_out(__VA_ARGS__);} while(0)
    #define stopif(val) assert( !(val) )
    #define vdbg(v,...) do { cout << #v << " = "; vector_debug(v , ##__VA_ARGS__);} while(0)
#else
    #define dbg(...) 1
    #define trc(...) 1
    #define stopif(...) 1
    #define vdbg(...) 1
#endif

using namespace std;
typedef long long ll;
typedef pair<int,int> pii;
typedef pair<ll,ll> pll;
typedef vector<int> vi;
typedef vector<ll> vl;
typedef vector<string> vs;
typedef vector<pii> vpii;
typedef vector< vector<int> > vvi;

struct IoSetup {
  IoSetup() {
    cin.tie(nullptr);
    ios::sync_with_stdio(false);
    cout << fixed << setprecision(15);
    cerr << fixed << setprecision(15);
  }
} iosetup;

int gcd(int a, int b){if(a>b) swap(a,b); return a==0 ? b : gcd(b%a,a);} ll gcd(ll a, ll b){if(a>b) swap(a,b); return a==0 ? b : gcd(b%a,a);}
int lcm(int a, int b){return (a / gcd(a,b)) * b;} ll lcm(ll a, ll b){return (a / gcd(a,b)) * b;}
inline ll pow(int a, int b){ll ans = 1; rep(i,b) ans *= a; return ans;} inline ll pow(ll a, ll b){ll ans = 1; rep(i,b) ans*= a; return ans;}
inline ll pow(int a, ll b){ll ans = 1; rep(i,b) ans *= a; return ans;} inline ll pow(ll a, int b){ll ans = 1; rep(i,b) ans*= a; return ans;}
template<typename T, typename U> inline bool amin(T &x, U y) { return (y < x) ? (x = y, true) : false; }
template<typename T, typename U> inline bool amax(T &x, U y) { return (x < y) ? (x = y, true) : false; }
template<typename C> inline void _cin(C &c){cin >> c;}
template<typename T,typename U> inline void _cin(pair<T,U> &p){cin >> p.fi; cin >> p.se;}
template<typename C> inline void _cout(const C &c){cout << c;}
template<typename T,typename U> inline void _cout(const pair<T,U> &p){cout << p.fi << ' ' << p.se;}
void in(){} template <typename T,class... U> void in(T &t,U &...u){ _cin(t); in(u...);}
void out(){cout << "\n";} template <typename T,class... U> void out(const T &t,U ...u){ _cout(t); if(sizeof...(u)) cout << ' '; out(u...);}
template<typename C> inline void in(vector<C> &v,int N=-1){if(sz(v) != 0){int M=(N == -1) ? sz(v) : N; rep(i,M) _cin(v[i]);}else{C c;rep(i,N) v.pb((_cin(c),c));}}
template<typename C> inline void in(C v[],int N){rep(i,N) _cin(v[i]);}
template<typename C> inline void out(const vector<C> &v,int N=-1){int M=(N == -1) ? sz(v) : N; rep(i,M) {cout<<( (i)?" ":"" ); _cout(v[i]);} cout<<"\n";}
template<typename C> inline void out(C v[],int N){rep(i,N) {cout<<( (i)?" ":"" ); _cout(v[i]);} cout<<"\n";}
template<typename C> inline void vector_debug(const vector<C> &v,int N=-1){cout << "{"; int M=(N == -1) ? sz(v) : N; rep(i,M) {cout<<( (i)?", ":"" ); _cout(v[i]);} cout<<"}"<<endl;}
template<typename C> inline void vector_debug(C v[], int N){cout << "{"; rep(i,N) {cout<<((i)?", ":""); _cout(*(v+i));} cout<<"}"<<endl;}
void dbg_out(){cout << endl;} template <typename T,class... U> void dbg_out(const T &t,U ...u){ _cout(t); if(sizeof...(u)) cout << ", "; dbg_out(u...);}
template<typename C,class... U> void dbg_out(const vector<C> &v,U ...u){vector_debug(v); if(sizeof...(u)) cout << ", "; dbg_out(u...);}
template<typename C,class... U> void dbg_out(const vector<vector<C>> &v,U ...u){cout << "{ "; rep(i,sz(v)) {if(i)cout<<", "; vector_debug(v[i]);} cout << " }"; if(sizeof...(u)) cout << ", "; dbg_out(u...);}
template<typename C> inline C vmax(const vector<C> &v){C n=v[0]; rep(i,sz(v)) amax(n,v[i]); return n;} template<typename C> inline C vmax(C v[], int N){C n=v[0]; rep( i , N ) amax(n,v[i]); return n;}
template<typename C> inline C vmin(const vector<C> &v){C n=v[0]; rep(i,sz(v)) amin(n,v[i]); return n;} template<typename C> inline C vmin(C v[], int N){C n=v[0]; rep( i , N ) amin(n,v[i]); return n;}
template<typename C> inline C vsum(const vector<C> &v){C n=0; rep(i,sz(v)) n+=v[i]; return n;} template<typename C> inline C vsum(C v[], int N){C n=0; rep( i , N ) n+=v[i]; return n;}

////////////
/// main ///
////////////

template< int mod >
struct ModInt {
  int x;

  ModInt() : x(0) {}

  ModInt(int64_t y) : x(y >= 0 ? y % mod : (mod - (-y) % mod) % mod) {}

  ModInt &operator+=(const ModInt &p) {
    if((x += p.x) >= mod) x -= mod;
    return *this;
  }

  ModInt &operator-=(const ModInt &p) {
    if((x += mod - p.x) >= mod) x -= mod;
    return *this;
  }

  ModInt &operator*=(const ModInt &p) {
    x = (int) (1LL * x * p.x % mod);
    return *this;
  }

  ModInt &operator/=(const ModInt &p) {
    *this *= p.inverse();
    return *this;
  }

  ModInt operator-() const { return ModInt(-x); }

  ModInt operator+(const ModInt &p) const { return ModInt(*this) += p; }

  ModInt operator-(const ModInt &p) const { return ModInt(*this) -= p; }

  ModInt operator*(const ModInt &p) const { return ModInt(*this) *= p; }

  ModInt operator/(const ModInt &p) const { return ModInt(*this) /= p; }

  bool operator==(const ModInt &p) const { return x == p.x; }

  bool operator!=(const ModInt &p) const { return x != p.x; }

  ModInt inverse() const {
    int a = x, b = mod, u = 1, v = 0, t;
    while(b > 0) {
      t = a / b;
      swap(a -= t * b, b);
      swap(u -= t * v, v);
    }
    return ModInt(u);
  }

  ModInt pow(int64_t n) const {
    ModInt ret(1), mul(x);
    while(n > 0) {
      if(n & 1) ret *= mul;
      mul *= mul;
      n >>= 1;
    }
    return ret;
  }

  friend ostream &operator<<(ostream &os, const ModInt &p) {
    return os << p.x;
  }

  friend istream &operator>>(istream &is, ModInt &a) {
    int64_t t;
    is >> t;
    a = ModInt< mod >(t);
    return (is);
  }
};

using modint = ModInt< MOD >;

template< class T >
struct Matrix {
  vector< vector< T > > A;

  Matrix() {}

  Matrix(size_t n, size_t m) : A(n, vector< T >(m, 0)) {}

  Matrix(size_t n) : A(n, vector< T >(n, 0)) {};

  size_t height() const {
    return (A.size());
  }

  size_t width() const {
    return (A[0].size());
  }

  inline const vector< T > &operator[](int k) const {
    return (A.at(k));
  }

  inline vector< T > &operator[](int k) {
    return (A.at(k));
  }

  static Matrix I(size_t n) {
    Matrix mat(n);
    for(int i = 0; i < n; i++) mat[i][i] = 1;
    return (mat);
  }

  Matrix &operator+=(const Matrix &B) {
    size_t n = height(), m = width();
    assert(n == B.height() && m == B.width());
    for(int i = 0; i < n; i++)
      for(int j = 0; j < m; j++)
        (*this)[i][j] += B[i][j];
    return (*this);
  }

  Matrix &operator-=(const Matrix &B) {
    size_t n = height(), m = width();
    assert(n == B.height() && m == B.width());
    for(int i = 0; i < n; i++)
      for(int j = 0; j < m; j++)
        (*this)[i][j] -= B[i][j];
    return (*this);
  }

  Matrix &operator*=(const Matrix &B) {
    size_t n = height(), m = B.width(), p = width();
    assert(p == B.height());
    vector< vector< T > > C(n, vector< T >(m, 0));
    for(int i = 0; i < n; i++)
      for(int j = 0; j < m; j++)
        for(int k = 0; k < p; k++)
          C[i][j] = (C[i][j] + (*this)[i][k] * B[k][j]);
    A.swap(C);
    return (*this);
  }

  Matrix &operator^=(long long k) {
    Matrix B = Matrix::I(height());
    while(k > 0) {
      if(k & 1) B *= *this;
      *this *= *this;
      k >>= 1LL;
    }
    A.swap(B.A);
    return (*this);
  }

  Matrix operator+(const Matrix &B) const {
    return (Matrix(*this) += B);
  }

  Matrix operator-(const Matrix &B) const {
    return (Matrix(*this) -= B);
  }

  Matrix operator*(const Matrix &B) const {
    return (Matrix(*this) *= B);
  }

  Matrix operator^(const long long k) const {
    return (Matrix(*this) ^= k);
  }

  friend ostream &operator<<(ostream &os, Matrix &p) {
    size_t n = p.height(), m = p.width();
    for(int i = 0; i < n; i++) {
      os << "[";
      for(int j = 0; j < m; j++) {
        os << p[i][j] << (j + 1 == m ? "]\n" : ",");
      }
    }
    return (os);
  }


  T determinant() {
    Matrix B(*this);
    assert(width() == height());
    T ret = 1;
    for(int i = 0; i < width(); i++) {
      int idx = -1;
      for(int j = i; j < width(); j++) {
        if(B[j][i] != 0) idx = j;
      }
      if(idx == -1) return (0);
      if(i != idx) {
        ret *= -1;
        swap(B[i], B[idx]);
      }
      ret *= B[i][i];
      T vv = B[i][i];
      for(int j = 0; j < width(); j++) {
        B[i][j] /= vv;
      }
      for(int j = i + 1; j < width(); j++) {
        T a = B[j][i];
        for(int k = 0; k < width(); k++) {
          B[j][k] -= B[i][k] * a;
        }
      }
    }
    return (ret);
  }
};

int main(){
  inl(N); ini(K);
  Matrix<modint> M(K*K*K);
  rep(i,K) rep(j,K) rep(l,K){
    int cur = i*K*K + j*K + l;
    int new1 = ( (i+1)%K)*K*K + j*K + l;
    M[new1][cur] += 1;
    int new2 = i*K*K + (j+i)%K * K + l;
    M[new2][cur] += 1;
    int new3 = i*K*K + j*K + (j+l)%K;
    M[new3][cur] += 1;
  }
  M = M ^ N;

  Matrix<modint> M2 (K*K*K , 1);
  M2[0][0] = 1;
  
  Matrix<modint> Mans = M * M2;
  modint ans = 0;
  rep(i,K) rep(j,K) rep(l,K){
    int cur = i*K*K + j*K + l;
    if(l == 0) ans += Mans[cur][0];
  }
  out(ans);

}