#include <algorithm>
#include <atcoder/all>
#include <bitset>
#include <cassert>
#include <cmath>
#include <ctime>
#include <functional>
#include <iomanip>
#include <iostream>
#include <map>
#include <queue>
#include <random>
#include <set>
#include <stack>
#include <string>
#include <tuple>
#include <unordered_map>
#include <unordered_set>
#include <utility>
#include <vector>
using namespace std;
using namespace atcoder;
typedef long long ll;
#define rep(i, n) for (int i = 0; i < (int)(n); i++)
#define repr(i, n) for (int i = (int)(n) - 1; i >= 0; i--)
#define repk(i, k, n) for (int i = k; i < (int)(n); i++)
#define all(v) v.begin(), v.end()
#define mod1 1000000007
#define mod2 998244353
#define mod3 100000007
#define vi vector<int>
#define vs vector<string>
#define vc vector<char>
#define vl vector<ll>
#define vb vector<bool>
#define vvi vector<vector<int>>
#define vvc vector<vector<char>>
#define vvl vector<vector<ll>>
#define vvb vector<vector<bool>>
#define vvvi vector<vector<vector<int>>>
#define vvvl vector<vector<vector<ll>>>
#define pii pair<int, int>
#define pil pair<int, ll>
#define pli pair<ll, int>
#define pll pair<ll, ll>
#define vpii vector<pair<int, int>>
#define vpll vector<pair<ll, ll>>
#define vvpii vector<vector<pair<int, int>>>
#define vvpll vector<vector<pair<ll, ll>>>

// using mint = modint998244353;

template <typename T>
void debug(T e) {
    cerr << e << endl;
}

template <typename T>
void debug(vector<T> &v) {
    rep(i, v.size()) { cerr << v[i] << " "; }
    cerr << endl;
}

template <typename T>
void debug(vector<vector<T>> &v) {
    rep(i, v.size()) {
        rep(j, v[i].size()) { cerr << v[i][j] << " "; }
        cerr << endl;
    }
}

template <typename T>
void debug(vector<pair<T, T>> &v) {
    rep(i, v.size()) { cerr << v[i].first << " " << v[i].second << endl; }
}

template <typename T>
void debug(set<T> &st) {
    for (auto itr = st.begin(); itr != st.end(); itr++) {
        cerr << *itr << " ";
    }
    cerr << endl;
}

template <typename T>
void debug(multiset<T> &ms) {
    for (auto itr = ms.begin(); itr != ms.end(); itr++) {
        cerr << *itr << " ";
    }
    cerr << endl;
}

template <typename T>
void debug(map<T, T> &mp) {
    for (auto itr = mp.begin(); itr != mp.end(); itr++) {
        cerr << itr->first << " " << itr->second << endl;
    }
}

void debug_out() { cerr << endl; }

template <typename Head, typename... Tail>
void debug_out(Head H, Tail... T) {
    cerr << H << " ";
    debug_out(T...);
}

using mint = modint;

void debug_mint1(vector<mint> &vec) {
    for (int i = 0; i < vec.size(); i++) {
        cerr << vec[i].val() << " ";
    }
    cerr << endl;
}

void debug_mint2(vector<vector<mint>> &vec) {
    for (int i = 0; i < vec.size(); i++) {
        for (int j = 0; j < vec[i].size(); j++) {
            cerr << vec[i][j].val() << " ";
        }
        cerr << endl;
    }
}

ll next(ll x, ll t, ll K) {
    ll ret;
    ll ho = x / (K * K);
    ll mu = (x - ho * K * K) / K;
    ll ra = x % K;

    if (t == 0) {
        ho++;
        ho %= K;
    } else if (t == 1) {
        mu += ho;
        mu %= K;
    } else if (t == 2) {
        ra += mu;
        ra %= K;
    }
    return ho * K * K + mu * K + ra;
}

// 行列累乗ライブラリ
// m_mul と p_mul を同時にインポートする

vector<vector<ll>> m_mul(vector<vector<ll>> &a, vector<vector<ll>> &b, ll mod) {
    ll n = a.size();
    vector<vector<ll>> ret(n, vector<ll>(n, 0));
    for (ll i = 0; i < n; i++) {
        for (ll j = 0; j < n; j++) {
            for (ll k = 0; k < n; k++) {
                ret[i][j] = (ret[i][j] + a[i][k] * b[k][j]) % mod;
            }
        }
    }
    return ret;
}

vector<vector<ll>> p_mul(vector<vector<ll>> a, ll k, ll mod) {
    ll n = a.size();
    vector<vector<ll>> ret(n, vector<ll>(n, 0));
    for (ll i = 0; i < n; i++) {
        ret[i][i] = 1;
    }
    while (k > 0) {
        if (k % 2 == 1) {
            ret = m_mul(a, ret, mod);
        }
        a = m_mul(a, a, mod);
        k /= 2;
    }
    return ret;
}

int main() {
    ll N, K;
    cin >> N >> K;
    vector<vector<ll>> M(K * K * K, vector<ll>(K * K * K, 0));
    for (ll i = 0; i < K * K * K; i++) {
        for (ll j = 0; j < 3; j++) {
            M[i][next(i, j, K)]++;
        }
    }

    vector<vector<ll>> M_mul = p_mul(M, N, mod2);
    ll ans = 0;
    for (ll i = 0; i < K * K * K; i++) {
        if (i % K == 0) {
            ans += M_mul[i][0];
            ans %= mod2;
        }
    }
    cout << ans << endl;
}