結果
| 問題 | No.2959 Dolls' Tea Party |
| ユーザー |
👑  tute7627
|
| 提出日時 | 2024-11-08 22:27:16 |
| 言語 | C++17 (gcc 12.3.0 + boost 1.83.0) |
| 結果 |
AC
|
| 実行時間 | 1,622 ms / 3,000 ms |
| コード長 | 32,764 bytes |
| コンパイル時間 | 3,826 ms |
| コンパイル使用メモリ | 255,276 KB |
| 実行使用メモリ | 10,624 KB |
| 最終ジャッジ日時 | 2024-11-08 22:27:47 |
| 合計ジャッジ時間 | 28,073 ms |
|
ジャッジサーバーID （参考情報） |
judge4 / judge3 |
（要ログイン）
テストケース
テストケース表示| 入力 | 結果 | 実行時間 実行使用メモリ |
|---|---|---|
| testcase_00 | AC | 12 ms
9,216 KB |
| testcase_01 | AC | 12 ms
9,088 KB |
| testcase_02 | AC | 12 ms
9,088 KB |
| testcase_03 | AC | 11 ms
9,088 KB |
| testcase_04 | AC | 11 ms
9,088 KB |
| testcase_05 | AC | 11 ms
9,088 KB |
| testcase_06 | AC | 59 ms
10,368 KB |
| testcase_07 | AC | 78 ms
10,368 KB |
| testcase_08 | AC | 63 ms
10,368 KB |
| testcase_09 | AC | 1,574 ms
10,496 KB |
| testcase_10 | AC | 1,588 ms
10,496 KB |
| testcase_11 | AC | 1,601 ms
10,624 KB |
| testcase_12 | AC | 1,622 ms
10,368 KB |
| testcase_13 | AC | 1,604 ms
10,496 KB |
| testcase_14 | AC | 97 ms
10,368 KB |
| testcase_15 | AC | 72 ms
10,368 KB |
| testcase_16 | AC | 1,225 ms
10,496 KB |
| testcase_17 | AC | 1,226 ms
10,496 KB |
| testcase_18 | AC | 1,214 ms
10,496 KB |
| testcase_19 | AC | 1,212 ms
10,496 KB |
| testcase_20 | AC | 1,230 ms
10,496 KB |
| testcase_21 | AC | 1,293 ms
10,496 KB |
| testcase_22 | AC | 1,307 ms
10,496 KB |
| testcase_23 | AC | 1,321 ms
10,496 KB |
| testcase_24 | AC | 13 ms
9,088 KB |
| testcase_25 | AC | 12 ms
9,088 KB |
| testcase_26 | AC | 12 ms
9,088 KB |
| testcase_27 | AC | 15 ms
9,216 KB |
| testcase_28 | AC | 15 ms
9,344 KB |
| testcase_29 | AC | 48 ms
10,496 KB |
| testcase_30 | AC | 36 ms
10,496 KB |
| testcase_31 | AC | 34 ms
10,368 KB |
| testcase_32 | AC | 784 ms
10,496 KB |
| testcase_33 | AC | 830 ms
10,496 KB |
| testcase_34 | AC | 866 ms
10,496 KB |
| testcase_35 | AC | 890 ms
10,624 KB |
| testcase_36 | AC | 818 ms
10,496 KB |
ソースコード
//#define _GLIBCXX_DEBUG
// #pragma GCC target("avx2")
// #pragma GCC optimize("O3")
// #pragma GCC optimize("unroll-loops")
#include<bits/stdc++.h>
using namespace std;
#ifdef LOCAL
#include <debug_print.hpp>
#define OUT(...) debug_print::multi_print(#__VA_ARGS__, __VA_ARGS__)
#else
#define OUT(...) (static_cast<void>(0))
#endif
#define endl '\n'
#define lfs cout<<fixed<<setprecision(15)
#define ALL(a) (a).begin(),(a).end()
#define ALLR(a) (a).rbegin(),(a).rend()
#define UNIQUE(a) (a).erase(unique((a).begin(),(a).end()),(a).end())
#define spa << " " <<
#define fi first
#define se second
#define MP make_pair
#define MT make_tuple
#define PB push_back
#define EB emplace_back
#define rep(i,n,m) for(ll i = (n); i < (ll)(m); i++)
#define rrep(i,n,m) for(ll i = (ll)(m) - 1; i >= (ll)(n); i--)
namespace template_tute{
using ll = long long;
using ld = long double;
const ll MOD1 = 1e9+7;
const ll MOD9 = 998244353;
const ll INF = 4.1e18;
using P = pair<ll, ll>;
template<typename T> using PQ = priority_queue<T>;
template<typename T> using QP = priority_queue<T,vector<T>,greater<T>>;
template<typename T1, typename T2>bool chmin(T1 &a,T2 b){if(a>b){a=b;return true;}else return false;}
template<typename T1, typename T2>bool chmax(T1 &a,T2 b){if(a<b){a=b;return true;}else return false;}
ll median(ll a,ll b, ll c){return a+b+c-max<ll>({a,b,c})-min<ll>({a,b,c});}
void ans1(bool x){if(x) cout<<"Yes"<<endl;else cout<<"No"<<endl;}
void ans2(bool x){if(x) cout<<"YES"<<endl;else cout<<"NO"<<endl;}
void ans3(bool x){if(x) cout<<"Yay!"<<endl;else cout<<":("<<endl;}
template<typename T1,typename T2>void ans(bool x,T1 y,T2 z){if(x)cout<<y<<endl;else cout<<z<<endl;}
template<typename T1,typename T2,typename T3>void anss(T1 x,T2 y,T3 z){ans(x!=y,x,z);};
template<typename T>void debug(const T &v,ll h,ll w,string sv=" "){for(ll i=0;i<h;i++){cout<<v[i][0];for(ll j=1;j<w;j++)cout<<sv<<v[i][j];cout<<endl;}};
template<typename T>void debug(const T &v,ll n,string sv=" "){if(n!=0)cout<<v[0];for(ll i=1;i<n;i++)cout<<sv<<v[i];cout<<endl;};
template<typename T>void debug(const vector<T>&v){debug(v,v.size());}
template<typename T>void debug(const vector<vector<T>>&v){for(auto &vv:v)debug(vv,vv.size());}
template<typename T>void debug(stack<T> st){while(!st.empty()){cout<<st.top()<<" ";st.pop();}cout<<endl;}
template<typename T>void debug(queue<T> st){while(!st.empty()){cout<<st.front()<<" ";st.pop();}cout<<endl;}
template<typename T>void debug(deque<T> st){while(!st.empty()){cout<<st.front()<<" ";st.pop_front();}cout<<endl;}
template<typename T>void debug(PQ<T> st){while(!st.empty()){cout<<st.top()<<" ";st.pop();}cout<<endl;}
template<typename T>void debug(QP<T> st){while(!st.empty()){cout<<st.top()<<" ";st.pop();}cout<<endl;}
template<typename T>void debug(const set<T>&v){for(auto z:v)cout<<z<<" ";cout<<endl;}
template<typename T>void debug(const multiset<T>&v){for(auto z:v)cout<<z<<" ";cout<<endl;}
template<typename T,size_t size>void debug(const array<T, size> &a){for(auto z:a)cout<<z<<" ";cout<<endl;}
template<typename T,typename V>void debug(const map<T,V>&v){for(auto z:v)cout<<"["<<z.first<<"]="<<z.second<<",";cout<<endl;}
template<typename T>vector<vector<T>>vec(ll x, ll y, T w){vector<vector<T>>v(x,vector<T>(y,w));return v;}
vector<ll>dx={1,-1,0,0,1,1,-1,-1};vector<ll>dy={0,0,1,-1,1,-1,1,-1};
template<typename T>vector<T> make_v(size_t a,T b){return vector<T>(a,b);}
template<typename... Ts>auto make_v(size_t a,Ts... ts){return vector<decltype(make_v(ts...))>(a,make_v(ts...));}
template<typename T1, typename T2>ostream &operator<<(ostream &os, const pair<T1, T2>&p){return os << "(" << p.first << "," << p.second << ")";}
template<typename T>ostream &operator<<(ostream &os, const vector<T> &v){os<<"[";for(auto &z:v)os << z << ",";os<<"]"; return os;}
template<typename T>void rearrange(vector<int>&ord, vector<T>&v){
auto tmp = v;
for(int i=0;i<tmp.size();i++)v[i] = tmp[ord[i]];
}
template<typename Head, typename... Tail>void rearrange(vector<int>&ord,Head&& head, Tail&&... tail){
rearrange(ord, head);
rearrange(ord, tail...);
}
template<typename T> vector<int> ascend(const vector<T>&v){
vector<int>ord(v.size());iota(ord.begin(),ord.end(),0);
sort(ord.begin(),ord.end(),[&](int i,int j){return make_pair(v[i],i)<make_pair(v[j],j);});
return ord;
}
template<typename T> vector<int> descend(const vector<T>&v){
vector<int>ord(v.size());iota(ord.begin(),ord.end(),0);
sort(ord.begin(),ord.end(),[&](int i,int j){return make_pair(v[i],-i)>make_pair(v[j],-j);});
return ord;
}
template<typename T> vector<T> inv_perm(const vector<T>&ord){
vector<T>inv(ord.size());
for(int i=0;i<ord.size();i++)inv[ord[i]] = i;
return inv;
}
ll FLOOR(ll n,ll div){assert(div>0);return n>=0?n/div:(n-div+1)/div;}
ll CEIL(ll n,ll div){assert(div>0);return n>=0?(n+div-1)/div:n/div;}
ll digitsum(ll n){ll ret=0;while(n){ret+=n%10;n/=10;}return ret;}
ll modulo(ll n,ll d){return (n%d+d)%d;};
template<typename T>T min(const vector<T>&v){return *min_element(v.begin(),v.end());}
template<typename T>T max(const vector<T>&v){return *max_element(v.begin(),v.end());}
template<typename T>T acc(const vector<T>&v){return accumulate(v.begin(),v.end(),T(0));};
template<typename T>T reverse(const T &v){return T(v.rbegin(),v.rend());};
//mt19937 mt(chrono::steady_clock::now().time_since_epoch().count());
int popcount(ll x){return __builtin_popcountll(x);};
int poplow(ll x){return __builtin_ctzll(x);};
int pophigh(ll x){return 63 - __builtin_clzll(x);};
template<typename T>T poll(queue<T> &q){auto ret=q.front();q.pop();return ret;};
template<typename T>T poll(priority_queue<T> &q){auto ret=q.top();q.pop();return ret;};
template<typename T>T poll(QP<T> &q){auto ret=q.top();q.pop();return ret;};
template<typename T>T poll(stack<T> &s){auto ret=s.top();s.pop();return ret;};
ll MULT(ll x,ll y){if(LLONG_MAX/x<=y)return LLONG_MAX;return x*y;}
ll POW2(ll x, ll k){ll ret=1,mul=x;while(k){if(mul==LLONG_MAX)return LLONG_MAX;if(k&1)ret=MULT(ret,mul);mul=MULT(mul,mul);k>>=1;}return ret;}
ll POW(ll x, ll k){ll ret=1;for(int i=0;i<k;i++){if(LLONG_MAX/x<=ret)return LLONG_MAX;ret*=x;}return ret;}
std::ostream &operator<<(std::ostream &dest, __int128_t value) {
std::ostream::sentry s(dest);
if (s) {
__uint128_t tmp = value < 0 ? -value : value;
char buffer[128];
char *d = std::end(buffer);
do {
--d;
*d = "0123456789"[tmp % 10];
tmp /= 10;
} while (tmp != 0);
if (value < 0) {
--d;
*d = '-';
}
int len = std::end(buffer) - d;
if (dest.rdbuf()->sputn(d, len) != len) {
dest.setstate(std::ios_base::badbit);
}
}
return dest;
}
namespace converter{
int dict[500];
const string lower="abcdefghijklmnopqrstuvwxyz";
const string upper="ABCDEFGHIJKLMNOPQRSTUVWXYZ";
const string digit="0123456789";
const string digit1="123456789";
void regi_str(const string &t){
for(int i=0;i<t.size();i++){
dict[t[i]]=i;
}
}
void regi_int(const string &t){
for(int i=0;i<t.size();i++){
dict[i]=t[i];
}
}
vector<int>to_int(const string &s,const string &t){
regi_str(t);
vector<int>ret(s.size());
for(int i=0;i<s.size();i++){
ret[i]=dict[s[i]];
}
return ret;
}
vector<int>to_int(const string &s){
auto t=s;
sort(t.begin(),t.end());
t.erase(unique(t.begin(),t.end()),t.end());
return to_int(s,t);
}
vector<vector<int>>to_int(const vector<string>&s,const string &t){
regi_str(t);
vector<vector<int>>ret(s.size(),vector<int>(s[0].size()));
for(int i=0;i<s.size();i++){
for(int j=0;j<s[0].size();j++){
ret[i][j]=dict[s[i][j]];
}
}
return ret;
}
vector<vector<int>>to_int(const vector<string>&s){
string t;
for(int i=0;i<s.size();i++){
t+=s[i];
}
sort(t.begin(),t.end());t.erase(unique(t.begin(),t.end()),t.end());
return to_int(s,t);
}
string to_str(const vector<int>&s,const string &t){
regi_int(t);
string ret;
for(auto z:s)ret+=dict[z];
return ret;
}
vector<string> to_str(const vector<vector<int>>&s,const string &t){
regi_int(t);
vector<string>ret(s.size());
for(int i=0;i<s.size();i++){
for(auto z:s[i])ret[i]+=dict[z];
}
return ret;
}
}
template< typename T = int >
struct edge {
int to;
T cost;
int id;
edge():to(-1),id(-1){};
edge(int to, T cost = 1, int id = -1):to(to), cost(cost), id(id){}
operator int() const { return to; }
};
template<typename T>
using Graph = vector<vector<edge<T>>>;
template<typename T>
Graph<T>revgraph(const Graph<T> &g){
Graph<T>ret(g.size());
for(int i=0;i<g.size();i++){
for(auto e:g[i]){
int to = e.to;
e.to = i;
ret[to].push_back(e);
}
}
return ret;
}
template<typename T>
Graph<T> readGraph(int n,int m,int indexed=1,bool directed=false,bool weighted=false){
Graph<T> ret(n);
for(int es = 0; es < m; es++){
int u,v;
T w=1;
cin>>u>>v;u-=indexed,v-=indexed;
if(weighted)cin>>w;
ret[u].emplace_back(v,w,es);
if(!directed)ret[v].emplace_back(u,w,es);
}
return ret;
}
template<typename T>
Graph<T> readParent(int n,int indexed=1,bool directed=true){
Graph<T>ret(n);
for(int i=1;i<n;i++){
int p;cin>>p;
p-=indexed;
ret[p].emplace_back(i);
if(!directed)ret[i].emplace_back(p);
}
return ret;
}
}
using namespace template_tute;
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); }
friend ModInt operator+(const ModInt& lhs, const ModInt& rhs) {
return ModInt(lhs) += rhs;
}
friend ModInt operator-(const ModInt& lhs, const ModInt& rhs) {
return ModInt(lhs) -= rhs;
}
friend ModInt operator*(const ModInt& lhs, const ModInt& rhs) {
return ModInt(lhs) *= rhs;
}
friend ModInt operator/(const ModInt& lhs, const ModInt& rhs) {
return ModInt(lhs) /= rhs;
}
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;
}
pair<int,int>frac(){
for(int j=1;j<=300;j++){
for(int i=-300;i<=300;i++){
if(ModInt(i)/j==*this){
return make_pair(i,j);
}
}
}
return make_pair(-1,-1);
}
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);
}
static constexpr int get_mod() { return mod; }
};
template< typename T >
struct Combination {
vector< T > _fact, _rfact, _inv;
Combination(ll sz) : _fact(sz + 1), _rfact(sz + 1), _inv(sz + 1) {
_fact[0] = _rfact[sz] = _inv[0] = 1;
for(ll i = 1; i <= sz; i++) _fact[i] = _fact[i - 1] * i;
_rfact[sz] /= _fact[sz];
for(ll i = sz - 1; i >= 0; i--) _rfact[i] = _rfact[i + 1] * (i + 1);
for(ll i = 1; i <= sz; i++) _inv[i] = _rfact[i] * _fact[i - 1];
}
inline T fact(ll k) const { return _fact[k]; }
inline T rfact(ll k) const { return _rfact[k]; }
inline T inv(ll k) const { return _inv[k]; }
T P(ll n, ll r) const {
if(r < 0 || n < r) return 0;
return fact(n) * rfact(n - r);
}
T C(ll p, ll q) const {
if(q < 0 || p < q) return 0;
return fact(p) * rfact(q) * rfact(p - q);
}
T RC(ll p, ll q) const {
if(q < 0 || p < q) return 0;
return rfact(p) * fact(q) * fact(p - q);
}
T H(ll n, ll r) const {
if(n < 0 || r < 0) return (0);
return r == 0 ? 1 : C(n + r - 1, r);
}
//+1がm個、-1がn個で prefix sumが常にk以上
T catalan(ll m,ll n,ll k){
if(n>m-k)return 0;
else return C(n+m,m)-C(n+m,n+k-1);
}
};
using modint = ModInt< MOD9 >;modint mpow(ll n, ll x){return modint(n).pow(x);}modint mpow(modint n, ll x){return n.pow(x);}
//using modint=ld;modint mpow(ll n, ll x){return pow(n,x);}modint mpow(modint n, ll x){return pow(n,x);}
using Comb=Combination<modint>;
template< typename Mint >
struct NumberTheoreticTransformFriendlyModInt {
static constexpr uint32_t get_pr() {
uint32_t _mod = Mint::get_mod();
using u64 = uint64_t;
u64 ds[32] = {};
int idx = 0;
u64 m = _mod - 1;
for (u64 i = 2; i * i <= m; ++i) {
if (m % i == 0) {
ds[idx++] = i;
while (m % i == 0) m /= i;
}
}
if (m != 1) ds[idx++] = m;
uint32_t _pr = 2;
while (1) {
int flg = 1;
for (int i = 0; i < idx; ++i) {
u64 a = _pr, b = (_mod - 1) / ds[i], r = 1;
while (b) {
if (b & 1) r = r * a % _mod;
a = a * a % _mod;
b >>= 1;
}
if (r == 1) {
flg = 0;
break;
}
}
if (flg == 1) break;
++_pr;
}
return _pr;
};
static constexpr uint32_t root = get_pr();
static vector< Mint > dw, idw;
NumberTheoreticTransformFriendlyModInt() = default;
static void init() {
dw.resize(level);
idw.resize(level);
setwy(level);
}
static void fft4(vector<Mint> &a, int k) {
if ((int)a.size() <= 1) return;
if (k == 1) {
Mint a1 = a[1];
a[1] = a[0] - a[1];
a[0] = a[0] + a1;
return;
}
if (k & 1) {
int v = 1 << (k - 1);
for (int j = 0; j < v; ++j) {
Mint ajv = a[j + v];
a[j + v] = a[j] - ajv;
a[j] += ajv;
}
}
int u = 1 << (2 + (k & 1));
int v = 1 << (k - 2 - (k & 1));
Mint one = Mint(1);
Mint imag = dw[1];
while (v) {
// jh = 0
{
int j0 = 0;
int j1 = v;
int j2 = j1 + v;
int j3 = j2 + v;
for (; j0 < v; ++j0, ++j1, ++j2, ++j3) {
Mint t0 = a[j0], t1 = a[j1], t2 = a[j2], t3 = a[j3];
Mint t0p2 = t0 + t2, t1p3 = t1 + t3;
Mint t0m2 = t0 - t2, t1m3 = (t1 - t3) * imag;
a[j0] = t0p2 + t1p3, a[j1] = t0p2 - t1p3;
a[j2] = t0m2 + t1m3, a[j3] = t0m2 - t1m3;
}
}
// jh >= 1
Mint ww = one, xx = one * dw[2], wx = one;
for (int jh = 4; jh < u;) {
ww = xx * xx, wx = ww * xx;
int j0 = jh * v;
int je = j0 + v;
int j2 = je + v;
for (; j0 < je; ++j0, ++j2) {
Mint t0 = a[j0], t1 = a[j0 + v] * xx, t2 = a[j2] * ww,
t3 = a[j2 + v] * wx;
Mint t0p2 = t0 + t2, t1p3 = t1 + t3;
Mint t0m2 = t0 - t2, t1m3 = (t1 - t3) * imag;
a[j0] = t0p2 + t1p3, a[j0 + v] = t0p2 - t1p3;
a[j2] = t0m2 + t1m3, a[j2 + v] = t0m2 - t1m3;
}
xx *= dw[__builtin_ctzll((jh += 4))];
}
u <<= 2;
v >>= 2;
}
}
static void ifft4(vector<Mint> &a, int k) {
if ((int)a.size() <= 1) return;
if (k == 1) {
Mint a1 = a[1];
a[1] = a[0] - a[1];
a[0] = a[0] + a1;
return;
}
int u = 1 << (k - 2);
int v = 1;
Mint one = Mint(1);
Mint imag = idw[1];
while (u) {
// jh = 0
{
int j0 = 0;
int j1 = v;
int j2 = v + v;
int j3 = j2 + v;
for (; j0 < v; ++j0, ++j1, ++j2, ++j3) {
Mint t0 = a[j0], t1 = a[j1], t2 = a[j2], t3 = a[j3];
Mint t0p1 = t0 + t1, t2p3 = t2 + t3;
Mint t0m1 = t0 - t1, t2m3 = (t2 - t3) * imag;
a[j0] = t0p1 + t2p3, a[j2] = t0p1 - t2p3;
a[j1] = t0m1 + t2m3, a[j3] = t0m1 - t2m3;
}
}
// jh >= 1
Mint ww = one, xx = one * idw[2], yy = one;
u <<= 2;
for (int jh = 4; jh < u;) {
ww = xx * xx, yy = xx * imag;
int j0 = jh * v;
int je = j0 + v;
int j2 = je + v;
for (; j0 < je; ++j0, ++j2) {
Mint t0 = a[j0], t1 = a[j0 + v], t2 = a[j2], t3 = a[j2 + v];
Mint t0p1 = t0 + t1, t2p3 = t2 + t3;
Mint t0m1 = (t0 - t1) * xx, t2m3 = (t2 - t3) * yy;
a[j0] = t0p1 + t2p3, a[j2] = (t0p1 - t2p3) * ww;
a[j0 + v] = t0m1 + t2m3, a[j2 + v] = (t0m1 - t2m3) * ww;
}
xx *= idw[__builtin_ctzll(jh += 4)];
}
u >>= 4;
v <<= 2;
}
if (k & 1) {
u = 1 << (k - 1);
for (int j = 0; j < u; ++j) {
Mint ajv = a[j] - a[j + u];
a[j] += a[j + u];
a[j + u] = ajv;
}
}
}
static void ntt(vector<Mint> &a) {
if ((int)a.size() <= 1) return;
fft4(a, __builtin_ctz(a.size()));
}
static void intt(vector<Mint> &a) {
if ((int)a.size() <= 1) return;
ifft4(a, __builtin_ctz(a.size()));
Mint iv = Mint(a.size()).inverse();
for (auto &x : a) x *= iv;
}
static constexpr int mod = Mint::get_mod();
static constexpr int level = __builtin_ctzll(mod - 1);
static void setwy(int k) {
Mint w[level], y[level];
w[k - 1] = Mint(root).pow((mod - 1) / (1 << k));
y[k - 1] = w[k - 1].inverse();
for (int i = k - 2; i > 0; --i)
w[i] = w[i + 1] * w[i + 1], y[i] = y[i + 1] * y[i + 1];
dw[1] = w[1], idw[1] = y[1], dw[2] = w[2], idw[2] = y[2];
for (int i = 3; i < k; ++i) {
dw[i] = dw[i - 1] * y[i - 2] * w[i];
idw[i] = idw[i - 1] * w[i - 2] * y[i];
}
}
static vector<Mint> multiply(const vector<Mint> &a, const vector<Mint> &b) {
int l = a.size() + b.size() - 1;
if (min<int>(a.size(), b.size()) <= 40) {
vector<Mint> s(l);
for (int i = 0; i < (int)a.size(); ++i)
for (int j = 0; j < (int)b.size(); ++j) s[i + j] += a[i] * b[j];
return s;
}
int k = 2, M = 4;
while (M < l) M <<= 1, ++k;
setwy(k);
vector<Mint> s(M);
for (int i = 0; i < (int)a.size(); ++i) s[i] = a[i];
fft4(s, k);
if (a.size() == b.size() && a == b) {
for (int i = 0; i < M; ++i) s[i] *= s[i];
} else {
vector<Mint> t(M);
for (int i = 0; i < (int)b.size(); ++i) t[i] = b[i];
fft4(t, k);
for (int i = 0; i < M; ++i) s[i] *= t[i];
}
ifft4(s, k);
s.resize(l);
Mint invm = Mint(M).inverse();
for (int i = 0; i < l; ++i) s[i] *= invm;
return s;
}
static void ntt_doubling(vector<Mint> &a) {
int M = (int)a.size();
auto b = a;
intt(b);
Mint r = 1, zeta = Mint(root).pow((Mint::get_mod() - 1) / (M << 1));
for (int i = 0; i < M; i++) b[i] *= r, r *= zeta;
ntt(b);
copy(begin(b), end(b), back_inserter(a));
}
};
template< typename Mint >
vector< Mint > NumberTheoreticTransformFriendlyModInt<Mint>::dw = vector< Mint >();
template< typename Mint >
vector< Mint > NumberTheoreticTransformFriendlyModInt< Mint >::idw = vector< Mint >();
//ret[i-j]=x[i]*y[j]
template<typename Conv, typename T>
vector<T>multiply_minus(vector<T>x,vector<T>y){
reverse(y.begin(),y.end());
auto tmp = Conv::multiply(x,y);
vector<T>ret(x.size());
for(int i = 0; i < x.size(); i++){
ret[i] = tmp[y.size() - 1 + i];
}
return ret;
}
//NumberTheoreticTransformFriendlyModInt<modint>::init();
template< typename T >
struct FormalPowerSeriesFriendlyNTT : vector< T > {
using vector< T >::vector;
using P = FormalPowerSeriesFriendlyNTT;
using NTT = NumberTheoreticTransformFriendlyModInt< T >;
P pre(int deg) const {
return P(begin(*this), begin(*this) + min((int) this->size(), deg));
}
P rev(int deg = -1) const {
P ret(*this);
if(deg != -1) ret.resize(deg, T(0));
reverse(begin(ret), end(ret));
return ret;
}
void ntt(){
NTT::ntt(*this);
}
void intt(){
NTT::intt(*this);
}
void ntt_doubling(){
NTT::ntt_doubling(*this);
}
void shrink() {
while(this->size() && this->back() == T(0)) this->pop_back();
}
P operator+(const P &r) const { return P(*this) += r; }
P operator+(const T &v) const { return P(*this) += v; }
P operator-(const P &r) const { return P(*this) -= r; }
P operator-(const T &v) const { return P(*this) -= v; }
P operator*(const P &r) const { return P(*this) *= r; }
P operator*(const T &v) const { return P(*this) *= v; }
P operator/(const P &r) const { return P(*this) /= r; }
P operator%(const P &r) const { return P(*this) %= r; }
P &operator+=(const P &r) {
if(r.size() > this->size()) this->resize(r.size());
for(int i = 0; i < (int) r.size(); i++) (*this)[i] += r[i];
return *this;
}
P &operator-=(const P &r) {
if(r.size() > this->size()) this->resize(r.size());
for(int i = 0; i < (int) r.size(); i++) (*this)[i] -= r[i];
return *this;
}
// https://judge.yosupo.jp/problem/convolution_mod
P &operator*=(const P &r) {
if(this->empty() || r.empty()) {
this->clear();
return *this;
}
auto ret = NTT::multiply(*this, r);
return *this = {begin(ret), end(ret)};
}
P &operator/=(const P &r) {
if(this->size() < r.size()) {
this->clear();
return *this;
}
int n = this->size() - r.size() + 1;
return *this = (rev().pre(n) * r.rev().inv(n)).pre(n).rev(n);
}
P &operator%=(const P &r) {
*this -= *this / r * r;
shrink();
return *this;
}
// https://judge.yosupo.jp/problem/division_of_polynomials
pair< P, P > div_mod(const P &r) {
P q = *this / r;
P x = *this - q * r;
x.shrink();
return make_pair(q, x);
}
P operator-() const {
P ret(this->size());
for(int i = 0; i < (int) this->size(); i++) ret[i] = -(*this)[i];
return ret;
}
P &operator+=(const T &r) {
if(this->empty()) this->resize(1);
(*this)[0] += r;
return *this;
}
P &operator-=(const T &r) {
if(this->empty()) this->resize(1);
(*this)[0] -= r;
return *this;
}
P &operator*=(const T &v) {
for(int i = 0; i < (int) this->size(); i++) (*this)[i] *= v;
return *this;
}
P dot(P r) const {
P ret(min(this->size(), r.size()));
for(int i = 0; i < (int) ret.size(); i++) ret[i] = (*this)[i] * r[i];
return ret;
}
P operator>>(int sz) const {
if((int) this->size() <= sz) return {};
P ret(*this);
ret.erase(ret.begin(), ret.begin() + sz);
return ret;
}
P operator<<(int sz) const {
P ret(*this);
ret.insert(ret.begin(), sz, T(0));
return ret;
}
T operator()(T x) const {
T r = 0, w = 1;
for(auto &v : *this) {
r += w * v;
w *= x;
}
return r;
}
P diff() const {
const int n = (int) this->size();
P ret(max(0, n - 1));
for(int i = 1; i < n; i++) ret[i - 1] = (*this)[i] * T(i);
return ret;
}
P integral() const {
const int n = (int) this->size();
P ret(n + 1);
ret[0] = T(0);
for(int i = 0; i < n; i++) ret[i + 1] = (*this)[i] / T(i + 1);
return ret;
}
// https://judge.yosupo.jp/problem/inv_of_formal_power_series
// F(0) must not be 0
P inv(int deg = -1) const {
assert(((*this)[0]) != T(0));
const int n = (int) this->size();
if(deg == -1) deg = n;
P res(deg);
res[0] = {T(1) / (*this)[0]};
for(int d = 1; d < deg; d <<= 1) {
P f(2 * d), g(2 * d);
for(int j = 0; j < min(n, 2 * d); j++) f[j] = (*this)[j];
for(int j = 0; j < d; j++) g[j] = res[j];
NTT::ntt(f);
NTT::ntt(g);
f = f.dot(g);
NTT::intt(f);
for(int j = 0; j < d; j++) f[j] = 0;
NTT::ntt(f);
for(int j = 0; j < 2 * d; j++) f[j] *= g[j];
NTT::intt(f);
for(int j = d; j < min(2 * d, deg); j++) res[j] = -f[j];
}
return res;
}
// https://judge.yosupo.jp/problem/log_of_formal_power_series
// F(0) must be 1
P log(int deg = -1) const {
assert((*this)[0] == T(1));
const int n = (int) this->size();
if(deg == -1) deg = n;
return (this->diff() * this->inv(deg)).pre(deg - 1).integral();
}
// https://judge.yosupo.jp/problem/sqrt_of_formal_power_series
P sqrt(int deg = -1, const function< T(T) > &get_sqrt = [](T) { return T(1); }) const {
const int n = (int) this->size();
if(deg == -1) deg = n;
if((*this)[0] == T(0)) {
for(int i = 1; i < n; i++) {
if((*this)[i] != T(0)) {
if(i & 1) return {};
if(deg - i / 2 <= 0) break;
auto ret = (*this >> i).sqrt(deg - i / 2, get_sqrt);
if(ret.empty()) return {};
ret = ret << (i / 2);
if((int) ret.size() < deg) ret.resize(deg, T(0));
return ret;
}
}
return P(deg, 0);
}
auto sqr = T(get_sqrt((*this)[0]));
if(sqr * sqr != (*this)[0]) return {};
P ret{sqr};
T inv2 = T(1) / T(2);
for(int i = 1; i < deg; i <<= 1) {
ret = (ret + pre(i << 1) * ret.inv(i << 1)) * inv2;
}
return ret.pre(deg);
}
P sqrt(const function< T(T) > &get_sqrt, int deg = -1) const {
return sqrt(deg, get_sqrt);
}
// https://judge.yosupo.jp/problem/exp_of_formal_power_series
// F(0) must be 0
P exp(int deg = -1) const {
if(deg == -1) deg = this->size();
assert((*this)[0] == T(0));
P inv;
inv.reserve(deg + 1);
inv.push_back(T(0));
inv.push_back(T(1));
auto inplace_integral = [&](P &F) -> void {
const int n = (int) F.size();
auto mod = T::get_mod();
while((int) inv.size() <= n) {
int i = inv.size();
inv.push_back((-inv[mod % i]) * (mod / i));
}
F.insert(begin(F), T(0));
for(int i = 1; i <= n; i++) F[i] *= inv[i];
};
auto inplace_diff = [](P &F) -> void {
if(F.empty()) return;
F.erase(begin(F));
T coeff = 1, one = 1;
for(int i = 0; i < (int) F.size(); i++) {
F[i] *= coeff;
coeff += one;
}
};
P b{1, 1 < (int) this->size() ? (*this)[1] : 0}, c{1}, z1, z2{1, 1};
for(int m = 2; m < deg; m *= 2) {
auto y = b;
y.resize(2 * m);
NTT::ntt(y);
z1 = z2;
P z(m);
for(int i = 0; i < m; ++i) z[i] = y[i] * z1[i];
NTT::intt(z);
fill(begin(z), begin(z) + m / 2, T(0));
NTT::ntt(z);
for(int i = 0; i < m; ++i) z[i] *= -z1[i];
NTT::intt(z);
c.insert(end(c), begin(z) + m / 2, end(z));
z2 = c;
z2.resize(2 * m);
NTT::ntt(z2);
P x(begin(*this), begin(*this) + min< int >(this->size(), m));
inplace_diff(x);
x.push_back(T(0));
NTT::ntt(x);
for(int i = 0; i < m; ++i) x[i] *= y[i];
NTT::intt(x);
x -= b.diff();
x.resize(2 * m);
for(int i = 0; i < m - 1; ++i) x[m + i] = x[i], x[i] = T(0);
NTT::ntt(x);
for(int i = 0; i < 2 * m; ++i) x[i] *= z2[i];
NTT::intt(x);
x.pop_back();
inplace_integral(x);
for(int i = m; i < min< int >(this->size(), 2 * m); ++i) x[i] += (*this)[i];
fill(begin(x), begin(x) + m, T(0));
NTT::ntt(x);
for(int i = 0; i < 2 * m; ++i) x[i] *= y[i];
NTT::intt(x);
b.insert(end(b), begin(x) + m, end(x));
}
return P{begin(b), begin(b) + deg};
}
// https://judge.yosupo.jp/problem/pow_of_formal_power_series
P pow(int64_t k, int deg = -1) const {
const int n = (int) this->size();
if(deg == -1) deg = n;
for(int i = 0; i < n; i++) {
if((*this)[i] != T(0)) {
T rev = T(1) / (*this)[i];
P ret = (((*this * rev) >> i).log(deg) * k).exp() * ((*this)[i].pow(k));
if(i * k > deg) return P(deg, T(0));
ret = (ret << (i * k)).pre(deg);
if((int) ret.size() < deg) ret.resize(deg, T(0));
return ret;
}
}
return *this;
}
P mod_pow(int64_t k, P g) const {
P modinv = g.rev().inv();
auto get_div = [&](P base) {
if(base.size() < g.size()) {
base.clear();
return base;
}
int n = base.size() - g.size() + 1;
return (base.rev().pre(n) * modinv.pre(n)).pre(n).rev(n);
};
P x(*this), ret{1};
while(k > 0) {
if(k & 1) {
ret *= x;
ret -= get_div(ret) * g;
ret.shrink();
}
x *= x;
x -= get_div(x) * g;
x.shrink();
k >>= 1;
}
return ret;
}
// https://judge.yosupo.jp/problem/polynomial_taylor_shift
P taylor_shift(T c) const {
int n = (int) this->size();
vector< T > fact(n), rfact(n);
fact[0] = rfact[0] = T(1);
for(int i = 1; i < n; i++) fact[i] = fact[i - 1] * T(i);
rfact[n - 1] = T(1) / fact[n - 1];
for(int i = n - 1; i > 1; i--) rfact[i - 1] = rfact[i] * T(i);
P p(*this);
for(int i = 0; i < n; i++) p[i] *= fact[i];
p = p.rev();
P bs(n, T(1));
for(int i = 1; i < n; i++) bs[i] = bs[i - 1] * c * rfact[i] * fact[i - 1];
p = (p * bs).pre(n);
p = p.rev();
for(int i = 0; i < n; i++) p[i] *= rfact[i];
return p;
}
void mul(vector<pair<int, T>> g, bool extend = false){
if(extend)this->resize(this->size() + g.back().first);
int n = this->size();
int d = g[0].first;
T c = g[0].second;
if(d == 0)g.erase(g.begin());
else c = 0;
for(int i = n - 1; i >= 0; i--){
(*this)[i] *= c;
for(auto z : g){
if(z.first > i)continue;
(*this)[i] += (*this)[i-z.first] * z.second;
}
}
}
void div(vector<pair<int, T>>g){//定数項は非ゼロ
int n = this->size();
int d = g[0].first;
T c = g[0].second;
c = T(1) / c;
g.erase(g.begin());
for(int i = 0; i < n; i++){
for(auto z : g){
if(z.first > i)continue;
(*this)[i] -= (*this)[i-z.first] * z.second;
}
(*this)[i] *= c;
}
}
template<typename C>
P recover(const C &comb){
int sz = this->size();
P x(sz),y(sz);
for(int i = 0; i < sz; i++){
x[sz - i - 1] = (*this)[i] * comb.fact(i);
y[i] = comb.rfact(i) * (i % 2 == 0 ? 1 : -1);
}
P tmp(sz);
rep(i,0,sz)tmp[i]=comb.rfact(i);
auto z = x * y;
P ret(z.begin(), z.begin() + sz);
reverse(ret.begin(), ret.end());
for(int i = 0; i < sz; i++){
ret[i] *= comb.rfact(i);
}
return ret;
}
};
template< typename Mint >
using FPS = FormalPowerSeriesFriendlyNTT< Mint >;
template<typename Poly>
Poly multiply_all(vector<Poly>&fs){
queue<Poly>que;
for(auto f:fs)que.push(f);
while(que.size()>=2){
auto p=que.front();
que.pop();
auto q=que.front();
que.pop();
que.push(p*q);
}
return que.front();
}
// sum f[i]/g[i]
template<typename Poly>
Poly sum_of_fractions(vector<Poly>&f,vector<Poly>&g,int deg){
queue<pair<Poly,Poly>>que;
assert(f.size()==g.size());
for(int i=0;i<f.size();i++){
que.emplace(f[i],g[i]);
}
while(que.size()>=2){
auto p=que.front();
que.pop();
auto q=que.front();
que.pop();
que.emplace(p.first*q.second+p.second*q.first,p.second*q.second);
}
return que.front().first*(que.front().second.inv(deg));
}
template<typename T>
using FormalPowerSeries=FormalPowerSeriesFriendlyNTT<T>;
using fps=FormalPowerSeriesFriendlyNTT<modint>;
//mainに持っていくこと！
void solve(){
ll res=0,buf=0;
bool judge = true;
NumberTheoreticTransformFriendlyModInt<modint>::init();
int n,k;cin>>n>>k;
vector<int>a(n);
rep(i,0,n){
cin>>a[i];
//a[i]=CEIL(i,100);
}
modint ret=0;
map<int,int>mp;
rep(i,0,k){
mp[gcd(i,k)]++;
}
Comb comb(500005);
for(auto z:mp){
map<int,int>cnt;
int d=k/z.first;
rep(i,0,n){
cnt[min<int>(z.fi,a[i]/d)]++;
}
//OUT(z.fi,cnt.size());
fps g(z.fi+1);
for(auto zz:cnt){
auto x=min(zz.fi,z.fi);
fps f(x+1);
rep(i,0,x+1)f[i]=comb.rfact(i);
f=f.log(z.fi+1);
rep(i,0,f.size()){
g[i]+=f[i]*zz.se;
}
}
g=g.exp(z.fi+1);
//OUT(z,cnt,g);
ret+=g[z.fi]*comb.fact(z.fi)*z.se;
}
cout<<ret/k<<endl;
}
int main(){
cin.tie(nullptr);
ios_base::sync_with_stdio(false);
ll res=0,buf=0;
bool judge = true;
int T = 1;
//cin>>T;
while(T--){
solve();
}
return 0;
}