#include <iostream>
#include <fstream>
#include <cstdio>
#include <cmath>
#include <vector>
#include <string>
#include <set>
#include <map>
#include <stack>
#include <queue>
#include <deque>
#include <bitset>
#include <algorithm>
#include <complex>
#include <array>
using namespace std;
 
#define REP(i,n) for(int i=0; i<n; ++i)
#define FOR(i,a,b) for(int i=a; i<=b; ++i)
#define FORR(i,a,b) for (int i=a; i>=b; --i)
#define ALL(c) (c).begin(), (c).end()
 
typedef long long ll;
typedef vector<int> VI;
typedef vector<ll> VL;
typedef vector<VI> VVI;
typedef vector<VL> VVL;
typedef pair<int,int> P;
typedef pair<ll,ll> PL;
typedef vector<double> VD;
typedef vector<VD> VVD;

template<typename T> void chmin(T &a, T b) { if (a > b) a = b; }
template<typename T> void chmax(T &a, T b) { if (a < b) a = b; }

int in() { int x; scanf("%d", &x); return x; }
ll lin() { ll x; scanf("%lld", &x); return x; }

const ll mod = 998244353;

VVL mulmat(VVL A, VVL B){
    int n = A.size();
    VVL C(n, VL(n));
    REP(i,n) REP(j,n) REP(k,n) (C[i][j] += A[i][k] * B[k][j]) %= mod;
    return C;
}

VVL powmat(VVL A, ll x){
    int n = A.size();
    VVL B(n, VL(n));
    REP(i,n) B[i][i] = 1;
    while (x) {
        if (x & 1) B = mulmat(B, A);
        A = mulmat(A, A);
        x >>= 1;
    }
    return B;
}

int main() {
    ll n, k;
    cin >> n >> k;
    ll m = k * k * k;
    VVL A(m, VL(m));

    REP(x,k) REP(y,k) REP(z,k){
        int c = x * k * k + y * k + z;
        A[x * k * k + y * k + (z + 1) % k][c]++;
        A[x * k * k + ((y + z) % k) * k + z][c]++;
        A[((x + y) % k) * k * k + y * k + z][c]++;
    }

    A = powmat(A, n);
    ll ans = 0;
    REP(i,k*k) ans = (ans + A[i][0]) % mod;
    cout << ans << endl;

    return 0;
}