#include<iostream>
#include<string>
#include<vector>
#include<algorithm>
#include<numeric>
#include<cmath>
#include<utility>
#include<tuple>
#include<cstdint>
#include<cstdio>
#include<iomanip>
#include<map>
#include<queue>
#include<set>
#include<stack>
#include<deque>
#include<unordered_map>
#include<unordered_set>
#include<bitset>
#include<cctype>
#include<chrono>
#include<random>
#include<cassert>
#include<cstddef>
#include<iterator>
#include<string_view>
#include<type_traits>

#ifdef LOCAL
#  include "debug_print.hpp"
#  define debug(...) debug_print::multi_print(#__VA_ARGS__, __VA_ARGS__)
#else
#  define debug(...) (static_cast<void>(0))
#endif

using namespace std;
#define rep(i,n) for(int i=0; i<(n); i++)
#define rrep(i,n) for(int i=(n)-1; i>=0; i--)
#define FOR(i,a,b) for(int i=(a); i<(b); i++)
#define RFOR(i,a,b) for(int i=(b-1); i>=(a); i--)
#define ALL(v) v.begin(), v.end()
#define RALL(v) v.rbegin(), v.rend()
#define UNIQUE(v) v.erase( unique(v.begin(), v.end()), v.end() );
#define pb push_back
using ll = long long;
using D = double;
using LD = long double;
using P = pair<int, int>;
template<typename T> using PQ = priority_queue<T,vector<T>>;
template<typename T> using minPQ = priority_queue<T, vector<T>, greater<T>>;
template<class T>bool chmax(T &a, const T &b) { if (a<b) { a=b; return 1; } return 0; }
template<class T>bool chmin(T &a, const T &b) { if (b<a) { a=b; return 1; } return 0; }
void yesno(bool flag) {cout << (flag?"Yes":"No") << "\n";}

template<typename T, typename U>
ostream &operator<<(ostream &os, const pair<T, U> &p) {
    os << p.first << " " << p.second;
    return os;
}
template<typename T, typename U>
istream &operator>>(istream &is, pair<T, U> &p) {
    is >> p.first >> p.second;
    return is;
}

template<typename T>
ostream &operator<<(ostream &os, const vector<T> &v) {
    int s = (int)v.size();
    for (int i = 0; i < s; i++) os << (i ? " " : "") << v[i];
    return os;
}
template<typename T>
istream &operator>>(istream &is, vector<T> &v) {
    for (auto &x : v) is >> x;
    return is;
}
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, char sep = ' '>
void out(const T &t, const U &...u) {
    cout << t;
    if (sizeof...(u)) cout << sep;
    out(u...);
}
void outr() {}
template<typename T, class... U, char sep = ' '>
void outr(const T &t, const U &...u) {
    cout << t;
    outr(u...);
}

#include "atcoder/modint.hpp"
#include "atcoder/convolution.hpp"

using mint = atcoder::modint998244353;
constexpr int mod = 998244353;

constexpr ll modpow(const ll& a, ll n, ll mod) noexcept {
    if (n == 0) return 1;
    auto t = modpow(a, n / 2, mod);
    t = t * t % mod;
    if (n & 1) t = t * a % mod;
    return t;
}

int calc_primitive_root(int mod) {
    if (mod == 2) return 1;
    if (mod == 167772161) return 3;
    if (mod == 469762049) return 3;
    if (mod == 754974721) return 11;
    if (mod == 998244353) return 3;
    int divs[20] = {};
    divs[0] = 2;
    int cnt = 1;
    long long x = (mod - 1) / 2;
    while (x % 2 == 0) x /= 2;
    for (long long i = 3; i * i <= x; i += 2) {
        if (x % i == 0) {
            divs[cnt++] = i;
            while (x % i == 0) x /= i;
        }
    }
    if (x > 1) divs[cnt++] = x;
    for (int g = 2;; g++) {
        bool ok = true;
        for (int i = 0; i < cnt; i++) {
            if (modpow(g, (mod - 1) / divs[i], mod) == 1) {
                ok = false;
                break;
            }
        }
        if (ok) return g;
    }
}

constexpr int mx = 200005;
ll fact[mx];
ll inv[mx];
ll finv[mx];
ll p;
ll com(int n, int m){
    if(n < 0 or m < 0 or n < m) return 0;
    return (fact[n] * finv[m] * finv[n-m]) % p;
}

int main(){
    ios_base::sync_with_stdio(false);
    cin.tie(nullptr);
    ll n; in(n,p);
    ll g = calc_primitive_root(p);

    rep(i,mx) fact[i] = inv[i] = finv[i] = 1;
    for(int i = 2; i < mx; i++){
        fact[i] = fact[i-1] * i % p;
        inv[i] = (p-inv[p%i]) * (p/i) % p;
        finv[i] = finv[i-1] * inv[i] % p;
    }

    vector<int> nv;
    while(n > 0){
        nv.pb(n%p);
        n /= p;
    }
    reverse(ALL(nv));
    int k = nv.size();

    vector<ll> pow(p,1);
    vector<ll> ipow(p);
    FOR(i,1,p){
        pow[i] = pow[i-1]*g%p;
        ipow[pow[i]] = i%(p-1);
    }

    queue<vector<mint>> q;

    rep(i,k){
        vector<mint> c(p-1);
        rep(j,nv[i]+1){
            ll cc = com(nv[i],j);
            c[ipow[cc]]++;
        }
        q.push(c);
    }

    while(q.size() > 1){
        auto f1 = q.front(); q.pop();
        auto f2 = q.front(); q.pop();
        q.push(atcoder::convolution(f1,f2));
    }

    mint ans = 0;
    int m = q.front().size();
    rep(i,m){
        ll x = pow[i%(p-1)];
        ans += q.front()[i] * x;
    }
    out(ans.val());
}