結果
| 問題 | No.2004 Incremental Coins |
| ユーザー |
 maspy
|
| 提出日時 | 2022-10-14 08:32:34 |
| 言語 | C++17 (gcc 12.3.0 + boost 1.83.0) |
| 結果 |
AC
|
| 実行時間 | 590 ms / 2,000 ms |
| コード長 | 43,061 bytes |
| コンパイル時間 | 7,060 ms |
| コンパイル使用メモリ | 331,152 KB |
| 実行使用メモリ | 56,452 KB |
| 最終ジャッジ日時 | 2023-09-08 19:31:49 |
| 合計ジャッジ時間 | 14,300 ms |
|
ジャッジサーバーID （参考情報） |
judge13 / judge11 |
（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 | 2 ms
4,352 KB |
| testcase_01 | AC | 1 ms
4,352 KB |
| testcase_02 | AC | 1 ms
4,356 KB |
| testcase_03 | AC | 2 ms
4,356 KB |
| testcase_04 | AC | 2 ms
4,356 KB |
| testcase_05 | AC | 1 ms
4,356 KB |
| testcase_06 | AC | 3 ms
4,356 KB |
| testcase_07 | AC | 3 ms
4,356 KB |
| testcase_08 | AC | 353 ms
39,120 KB |
| testcase_09 | AC | 134 ms
20,752 KB |
| testcase_10 | AC | 590 ms
56,452 KB |
| testcase_11 | AC | 104 ms
20,512 KB |
| testcase_12 | AC | 119 ms
20,492 KB |
| testcase_13 | AC | 77 ms
20,496 KB |
| testcase_14 | AC | 92 ms
20,520 KB |
| testcase_15 | AC | 310 ms
38,120 KB |
| testcase_16 | AC | 328 ms
38,268 KB |
| testcase_17 | AC | 317 ms
38,668 KB |
| testcase_18 | AC | 229 ms
28,944 KB |
| testcase_19 | AC | 129 ms
19,932 KB |
| testcase_20 | AC | 126 ms
19,804 KB |
| testcase_21 | AC | 119 ms
19,236 KB |
ソースコード
#line 1 "/home/maspy/compro/library/my_template.hpp"
#pragma GCC optimize("Ofast")
#pragma GCC optimize("unroll-loops")
#include <bits/stdc++.h>
using namespace std;
using ll = long long;
using pi = pair<ll, ll>;
using vi = vector<ll>;
using u32 = unsigned int;
using u64 = unsigned long long;
using i128 = __int128;
template <class T>
using vc = vector<T>;
template <class T>
using vvc = vector<vc<T>>;
template <class T>
using vvvc = vector<vvc<T>>;
template <class T>
using vvvvc = vector<vvvc<T>>;
template <class T>
using vvvvvc = vector<vvvvc<T>>;
template <class T>
using pq = priority_queue<T>;
template <class T>
using pqg = priority_queue<T, vector<T>, greater<T>>;
#define vec(type, name, ...) vector<type> name(__VA_ARGS__)
#define vv(type, name, h, ...) \
vector<vector<type>> name(h, vector<type>(__VA_ARGS__))
#define vvv(type, name, h, w, ...) \
vector<vector<vector<type>>> name( \
h, vector<vector<type>>(w, vector<type>(__VA_ARGS__)))
#define vvvv(type, name, a, b, c, ...) \
vector<vector<vector<vector<type>>>> name( \
a, vector<vector<vector<type>>>( \
b, vector<vector<type>>(c, vector<type>(__VA_ARGS__))))
// https://trap.jp/post/1224/
#define FOR1(a) for (ll _ = 0; _ < ll(a); ++_)
#define FOR2(i, a) for (ll i = 0; i < ll(a); ++i)
#define FOR3(i, a, b) for (ll i = a; i < ll(b); ++i)
#define FOR4(i, a, b, c) for (ll i = a; i < ll(b); i += (c))
#define FOR1_R(a) for (ll i = (a)-1; i >= ll(0); --i)
#define FOR2_R(i, a) for (ll i = (a)-1; i >= ll(0); --i)
#define FOR3_R(i, a, b) for (ll i = (b)-1; i >= ll(a); --i)
#define FOR4_R(i, a, b, c) for (ll i = (b)-1; i >= ll(a); i -= (c))
#define overload4(a, b, c, d, e, ...) e
#define FOR(...) overload4(__VA_ARGS__, FOR4, FOR3, FOR2, FOR1)(__VA_ARGS__)
#define FOR_R(...) \
overload4(__VA_ARGS__, FOR4_R, FOR3_R, FOR2_R, FOR1_R)(__VA_ARGS__)
#define FOR_subset(t, s) for (ll t = s; t >= 0; t = (t == 0 ? -1 : (t - 1) & s))
#define all(x) x.begin(), x.end()
#define len(x) ll(x.size())
#define elif else if
#define eb emplace_back
#define mp make_pair
#define mt make_tuple
#define fi first
#define se second
#define stoi stoll
template <typename T, typename U>
T SUM(const vector<U> &A) {
T sum = 0;
for (auto &&a: A) sum += a;
return sum;
}
#define MIN(v) *min_element(all(v))
#define MAX(v) *max_element(all(v))
#define LB(c, x) distance((c).begin(), lower_bound(all(c), (x)))
#define UB(c, x) distance((c).begin(), upper_bound(all(c), (x)))
#define UNIQUE(x) sort(all(x)), x.erase(unique(all(x)), x.end())
int popcnt(int x) { return __builtin_popcount(x); }
int popcnt(u32 x) { return __builtin_popcount(x); }
int popcnt(ll x) { return __builtin_popcountll(x); }
int popcnt(u64 x) { return __builtin_popcountll(x); }
// (0, 1, 2, 3, 4) -> (-1, 0, 1, 1, 2)
int topbit(int x) { return (x == 0 ? -1 : 31 - __builtin_clz(x)); }
int topbit(u32 x) { return (x == 0 ? -1 : 31 - __builtin_clz(x)); }
int topbit(ll x) { return (x == 0 ? -1 : 63 - __builtin_clzll(x)); }
int topbit(u64 x) { return (x == 0 ? -1 : 63 - __builtin_clzll(x)); }
// (0, 1, 2, 3, 4) -> (-1, 0, 1, 0, 2)
int lowbit(int x) { return (x == 0 ? -1 : __builtin_ctz(x)); }
int lowbit(u32 x) { return (x == 0 ? -1 : __builtin_ctz(x)); }
int lowbit(ll x) { return (x == 0 ? -1 : __builtin_ctzll(x)); }
int lowbit(u64 x) { return (x == 0 ? -1 : __builtin_ctzll(x)); }
template <typename T>
T pick(deque<T> &que) {
T a = que.front();
que.pop_front();
return a;
}
template <typename T>
T pick(pq<T> &que) {
T a = que.top();
que.pop();
return a;
}
template <typename T>
T pick(pqg<T> &que) {
assert(que.size());
T a = que.top();
que.pop();
return a;
}
template <typename T>
T pick(vc<T> &que) {
assert(que.size());
T a = que.back();
que.pop_back();
return a;
}
template <typename T, typename U>
T ceil(T x, U y) {
return (x > 0 ? (x + y - 1) / y : x / y);
}
template <typename T, typename U>
T floor(T x, U y) {
return (x > 0 ? x / y : (x - y + 1) / y);
}
template <typename T, typename U>
pair<T, T> divmod(T x, U y) {
T q = floor(x, y);
return {q, x - q * y};
}
template <typename F>
ll binary_search(F check, ll ok, ll ng) {
assert(check(ok));
while (abs(ok - ng) > 1) {
auto x = (ng + ok) / 2;
tie(ok, ng) = (check(x) ? mp(x, ng) : mp(ok, x));
}
return ok;
}
template <typename F>
double binary_search_real(F check, double ok, double ng, int iter = 100) {
FOR(iter) {
double x = (ok + ng) / 2;
tie(ok, ng) = (check(x) ? mp(x, ng) : mp(ok, x));
}
return (ok + ng) / 2;
}
template <class T, class S>
inline bool chmax(T &a, const S &b) {
return (a < b ? a = b, 1 : 0);
}
template <class T, class S>
inline bool chmin(T &a, const S &b) {
return (a > b ? a = b, 1 : 0);
}
vc<int> s_to_vi(const string &S, char first_char) {
vc<int> A(S.size());
FOR(i, S.size()) { A[i] = S[i] - first_char; }
return A;
}
template <typename T, typename U>
vector<T> cumsum(vector<U> &A, int off = 1) {
int N = A.size();
vector<T> B(N + 1);
FOR(i, N) { B[i + 1] = B[i] + A[i]; }
if (off == 0) B.erase(B.begin());
return B;
}
template <typename CNT, typename T>
vc<CNT> bincount(const vc<T> &A, int size) {
vc<CNT> C(size);
for (auto &&x: A) { ++C[x]; }
return C;
}
// stable
template <typename T>
vector<int> argsort(const vector<T> &A) {
vector<int> ids(A.size());
iota(all(ids), 0);
sort(all(ids),
[&](int i, int j) { return A[i] < A[j] || (A[i] == A[j] && i < j); });
return ids;
}
// A[I[0]], A[I[1]], ...
template <typename T>
vc<T> rearrange(const vc<T> &A, const vc<int> &I) {
int n = len(I);
vc<T> B(n);
FOR(i, n) B[i] = A[I[i]];
return B;
}
#line 1 "/home/maspy/compro/library/other/io.hpp"
// based on yosupo's fastio
#include <unistd.h>
namespace detail {
template <typename T, decltype(&T::is_modint) = &T::is_modint>
std::true_type check_value(int);
template <typename T>
std::false_type check_value(long);
} // namespace detail
template <typename T>
struct is_modint : decltype(detail::check_value<T>(0)) {};
template <typename T>
using is_modint_t = enable_if_t<is_modint<T>::value>;
template <typename T>
using is_not_modint_t = enable_if_t<!is_modint<T>::value>;
struct Scanner {
FILE *fp;
char line[(1 << 15) + 1];
size_t st = 0, ed = 0;
void reread() {
memmove(line, line + st, ed - st);
ed -= st;
st = 0;
ed += fread(line + ed, 1, (1 << 15) - ed, fp);
line[ed] = '\0';
}
bool succ() {
while (true) {
if (st == ed) {
reread();
if (st == ed) return false;
}
while (st != ed && isspace(line[st])) st++;
if (st != ed) break;
}
if (ed - st <= 50) {
bool sep = false;
for (size_t i = st; i < ed; i++) {
if (isspace(line[i])) {
sep = true;
break;
}
}
if (!sep) reread();
}
return true;
}
template <class T, enable_if_t<is_same<T, string>::value, int> = 0>
bool read_single(T &ref) {
if (!succ()) return false;
while (true) {
size_t sz = 0;
while (st + sz < ed && !isspace(line[st + sz])) sz++;
ref.append(line + st, sz);
st += sz;
if (!sz || st != ed) break;
reread();
}
return true;
}
template <class T, enable_if_t<is_integral<T>::value, int> = 0>
bool read_single(T &ref) {
if (!succ()) return false;
bool neg = false;
if (line[st] == '-') {
neg = true;
st++;
}
ref = T(0);
while (isdigit(line[st])) { ref = 10 * ref + (line[st++] & 0xf); }
if (neg) ref = -ref;
return true;
}
template <class T, is_modint_t<T> * = nullptr>
bool read_single(T &ref) {
long long val = 0;
bool f = read_single(val);
ref = T(val);
return f;
}
bool read_single(double &ref) {
string s;
if (!read_single(s)) return false;
ref = std::stod(s);
return true;
}
bool read_single(char &ref) {
string s;
if (!read_single(s) || s.size() != 1) return false;
ref = s[0];
return true;
}
template <class T>
bool read_single(vector<T> &ref) {
for (auto &d: ref) {
if (!read_single(d)) return false;
}
return true;
}
template <class T, class U>
bool read_single(pair<T, U> &p) {
return (read_single(p.first) && read_single(p.second));
}
template <class A, class B, class C>
bool read_single(tuple<A, B, C> &p) {
return (read_single(get<0>(p)) && read_single(get<1>(p))
&& read_single(get<2>(p)));
}
template <class A, class B, class C, class D>
bool read_single(tuple<A, B, C, D> &p) {
return (read_single(get<0>(p)) && read_single(get<1>(p))
&& read_single(get<2>(p)) && read_single(get<3>(p)));
}
void read() {}
template <class H, class... T>
void read(H &h, T &... t) {
bool f = read_single(h);
assert(f);
read(t...);
}
Scanner(FILE *fp) : fp(fp) {}
};
struct Printer {
Printer(FILE *_fp) : fp(_fp) {}
~Printer() { flush(); }
static constexpr size_t SIZE = 1 << 15;
FILE *fp;
char line[SIZE], small[50];
size_t pos = 0;
void flush() {
fwrite(line, 1, pos, fp);
pos = 0;
}
void write(const char &val) {
if (pos == SIZE) flush();
line[pos++] = val;
}
template <class T, enable_if_t<is_integral<T>::value, int> = 0>
void write(T val) {
if (pos > (1 << 15) - 50) flush();
if (val == 0) {
write('0');
return;
}
if (val < 0) {
write('-');
val = -val; // todo min
}
size_t len = 0;
while (val) {
small[len++] = char(0x30 | (val % 10));
val /= 10;
}
for (size_t i = 0; i < len; i++) { line[pos + i] = small[len - 1 - i]; }
pos += len;
}
void write(const string &s) {
for (char c: s) write(c);
}
void write(const char *s) {
size_t len = strlen(s);
for (size_t i = 0; i < len; i++) write(s[i]);
}
void write(const double &x) {
ostringstream oss;
oss << fixed << setprecision(15) << x;
string s = oss.str();
write(s);
}
void write(const long double &x) {
ostringstream oss;
oss << fixed << setprecision(15) << x;
string s = oss.str();
write(s);
}
template <class T, is_modint_t<T> * = nullptr>
void write(T &ref) {
write(ref.val);
}
template <class T>
void write(const vector<T> &val) {
auto n = val.size();
for (size_t i = 0; i < n; i++) {
if (i) write(' ');
write(val[i]);
}
}
template <class T, class U>
void write(const pair<T, U> &val) {
write(val.first);
write(' ');
write(val.second);
}
template <class A, class B, class C>
void write(const tuple<A, B, C> &val) {
auto &[a, b, c] = val;
write(a), write(' '), write(b), write(' '), write(c);
}
template <class A, class B, class C, class D>
void write(const tuple<A, B, C, D> &val) {
auto &[a, b, c, d] = val;
write(a), write(' '), write(b), write(' '), write(c), write(' '), write(d);
}
template <class A, class B, class C, class D, class E>
void write(const tuple<A, B, C, D, E> &val) {
auto &[a, b, c, d, e] = val;
write(a), write(' '), write(b), write(' '), write(c), write(' '), write(d), write(' '), write(e);
}
template <class A, class B, class C, class D, class E, class F>
void write(const tuple<A, B, C, D, E, F> &val) {
auto &[a, b, c, d, e, f] = val;
write(a), write(' '), write(b), write(' '), write(c), write(' '), write(d), write(' '), write(e), write(' '), write(f);
}
template <class T, size_t S>
void write(const array<T, S> &val) {
auto n = val.size();
for (size_t i = 0; i < n; i++) {
if (i) write(' ');
write(val[i]);
}
}
void write(i128 val) {
string s;
bool negative = 0;
if(val < 0){
negative = 1;
val = -val;
}
while (val) {
s += '0' + int(val % 10);
val /= 10;
}
if(negative) s += "-";
reverse(all(s));
if (len(s) == 0) s = "0";
write(s);
}
};
Scanner scanner = Scanner(stdin);
Printer printer = Printer(stdout);
void flush() { printer.flush(); }
void print() { printer.write('\n'); }
template <class Head, class... Tail>
void print(Head &&head, Tail &&... tail) {
printer.write(head);
if (sizeof...(Tail)) printer.write(' ');
print(forward<Tail>(tail)...);
}
void read() {}
template <class Head, class... Tail>
void read(Head &head, Tail &... tail) {
scanner.read(head);
read(tail...);
}
#define INT(...) \
int __VA_ARGS__; \
read(__VA_ARGS__)
#define LL(...) \
ll __VA_ARGS__; \
read(__VA_ARGS__)
#define STR(...) \
string __VA_ARGS__; \
read(__VA_ARGS__)
#define CHAR(...) \
char __VA_ARGS__; \
read(__VA_ARGS__)
#define DBL(...) \
double __VA_ARGS__; \
read(__VA_ARGS__)
#define VEC(type, name, size) \
vector<type> name(size); \
read(name)
#define VV(type, name, h, w) \
vector<vector<type>> name(h, vector<type>(w)); \
read(name)
void YES(bool t = 1) { print(t ? "YES" : "NO"); }
void NO(bool t = 1) { YES(!t); }
void Yes(bool t = 1) { print(t ? "Yes" : "No"); }
void No(bool t = 1) { Yes(!t); }
void yes(bool t = 1) { print(t ? "yes" : "no"); }
void no(bool t = 1) { yes(!t); }
#line 2 "/home/maspy/compro/library/mod/modint.hpp"
template <int mod>
struct modint {
static constexpr bool is_modint = true;
int val;
constexpr modint(const ll val = 0) noexcept
: val(val >= 0 ? val % mod : (mod - (-val) % mod) % mod) {}
bool operator<(const modint &other) const {
return val < other.val;
} // To use std::map
modint &operator+=(const modint &p) {
if ((val += p.val) >= mod) val -= mod;
return *this;
}
modint &operator-=(const modint &p) {
if ((val += mod - p.val) >= mod) val -= mod;
return *this;
}
modint &operator*=(const modint &p) {
val = (int)(1LL * val * p.val % mod);
return *this;
}
modint &operator/=(const modint &p) {
*this *= p.inverse();
return *this;
}
modint operator-() const { return modint(-val); }
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 val == p.val; }
bool operator!=(const modint &p) const { return val != p.val; }
modint inverse() const {
int a = val, 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(val);
while (n > 0) {
if (n & 1) ret *= mul;
mul *= mul;
n >>= 1;
}
return ret;
}
static constexpr int get_mod() { return mod; }
};
struct ArbitraryModInt {
static constexpr bool is_modint = true;
int val;
ArbitraryModInt() : val(0) {}
ArbitraryModInt(int64_t y)
: val(y >= 0 ? y % get_mod()
: (get_mod() - (-y) % get_mod()) % get_mod()) {}
bool operator<(const ArbitraryModInt &other) const {
return val < other.val;
} // To use std::map<ArbitraryModInt, T>
static int &get_mod() {
static int mod = 0;
return mod;
}
static void set_mod(int md) { get_mod() = md; }
ArbitraryModInt &operator+=(const ArbitraryModInt &p) {
if ((val += p.val) >= get_mod()) val -= get_mod();
return *this;
}
ArbitraryModInt &operator-=(const ArbitraryModInt &p) {
if ((val += get_mod() - p.val) >= get_mod()) val -= get_mod();
return *this;
}
ArbitraryModInt &operator*=(const ArbitraryModInt &p) {
long long a = (long long)val * p.val;
int xh = (int)(a >> 32), xl = (int)a, d, m;
asm("divl %4; \n\t" : "=a"(d), "=d"(m) : "d"(xh), "a"(xl), "r"(get_mod()));
val = m;
return *this;
}
ArbitraryModInt &operator/=(const ArbitraryModInt &p) {
*this *= p.inverse();
return *this;
}
ArbitraryModInt operator-() const { return ArbitraryModInt(get_mod() - val); }
ArbitraryModInt operator+(const ArbitraryModInt &p) const {
return ArbitraryModInt(*this) += p;
}
ArbitraryModInt operator-(const ArbitraryModInt &p) const {
return ArbitraryModInt(*this) -= p;
}
ArbitraryModInt operator*(const ArbitraryModInt &p) const {
return ArbitraryModInt(*this) *= p;
}
ArbitraryModInt operator/(const ArbitraryModInt &p) const {
return ArbitraryModInt(*this) /= p;
}
bool operator==(const ArbitraryModInt &p) const { return val == p.val; }
bool operator!=(const ArbitraryModInt &p) const { return val != p.val; }
ArbitraryModInt inverse() const {
int a = val, b = get_mod(), u = 1, v = 0, t;
while (b > 0) {
t = a / b;
swap(a -= t * b, b), swap(u -= t * v, v);
}
return ArbitraryModInt(u);
}
ArbitraryModInt pow(int64_t n) const {
ArbitraryModInt ret(1), mul(val);
while (n > 0) {
if (n & 1) ret *= mul;
mul *= mul;
n >>= 1;
}
return ret;
}
};
template <typename mint>
mint inv(int n) {
static const int mod = mint::get_mod();
static vector<mint> dat = {0, 1};
assert(0 <= n);
if (n >= mod) n %= mod;
while (int(dat.size()) <= n) {
int k = dat.size();
auto q = (mod + k - 1) / k;
int r = k * q - mod;
dat.emplace_back(dat[r] * mint(q));
}
return dat[n];
}
template <typename mint>
mint fact(int n) {
static const int mod = mint::get_mod();
static vector<mint> dat = {1, 1};
assert(0 <= n);
if (n >= mod) return 0;
while (int(dat.size()) <= n) {
int k = dat.size();
dat.emplace_back(dat[k - 1] * mint(k));
}
return dat[n];
}
template <typename mint>
mint fact_inv(int n) {
static const int mod = mint::get_mod();
static vector<mint> dat = {1, 1};
assert(0 <= n && n < mod);
while (int(dat.size()) <= n) {
int k = dat.size();
dat.emplace_back(dat[k - 1] * inv<mint>(k));
}
return dat[n];
}
template <typename mint>
mint C_dense(int n, int k) {
static vvc<mint> C;
static int H = 0, W = 0;
auto calc = [&](int i, int j) -> mint {
if (i == 0) return (j == 0 ? mint(1) : mint(0));
return C[i - 1][j] + (j ? C[i - 1][j - 1] : 0);
};
if (W <= k) {
FOR(i, H) {
C[i].resize(k + 1);
FOR(j, W, k + 1) { C[i][j] = calc(i, j); }
}
W = k + 1;
}
if (H <= n) {
C.resize(n + 1);
FOR(i, H, n + 1) {
C[i].resize(W);
FOR(j, W) { C[i][j] = calc(i, j); }
}
H = n + 1;
}
return C[n][k];
}
template <typename mint, bool large = false, bool dense = false>
mint C(ll n, ll k) {
assert(n >= 0);
if (k < 0 || n < k) return 0;
if (dense) return C_dense<mint>(n, k);
if (!large) return fact<mint>(n) * fact_inv<mint>(k) * fact_inv<mint>(n - k);
k = min(k, n - k);
mint x(1);
FOR(i, k) { x *= mint(n - i); }
x *= fact_inv<mint>(k);
return x;
}
template <typename mint, bool large = false>
mint C_inv(ll n, ll k) {
assert(n >= 0);
assert(0 <= k && k <= n);
if (!large) return fact_inv<mint>(n) * fact<mint>(k) * fact<mint>(n - k);
return mint(1) / C<mint, 1>(n, k);
}
// [x^d] (1-x) ^ {-n} の計算
template <typename mint, bool large = false, bool dense = false>
mint C_negative(ll n, ll d) {
assert(n >= 0);
if (d < 0) return mint(0);
if (n == 0) { return (d == 0 ? mint(1) : mint(0)); }
return C<mint, large, dense>(n + d - 1, d);
}
using modint107 = modint<1000000007>;
using modint998 = modint<998244353>;
using amint = ArbitraryModInt;
#line 2 "/home/maspy/compro/library/graph/base.hpp"
template <typename T>
struct Edge {
int frm, to;
T cost;
int id;
};
template <typename T = int, bool directed = false>
struct Graph {
int N, M;
using cost_type = T;
using edge_type = Edge<T>;
vector<edge_type> edges;
vector<int> indptr;
vector<edge_type> csr_edges;
vc<int> vc_deg, vc_indeg, vc_outdeg;
bool prepared;
class OutgoingEdges {
public:
OutgoingEdges(const Graph* G, int l, int r) : G(G), l(l), r(r) {}
const edge_type* begin() const {
if (l == r) { return 0; }
return &G->csr_edges[l];
}
const edge_type* end() const {
if (l == r) { return 0; }
return &G->csr_edges[r];
}
private:
const Graph* G;
int l, r;
};
bool is_prepared() { return prepared; }
constexpr bool is_directed() { return directed; }
Graph() : N(0), M(0), prepared(0) {}
Graph(int N) : N(N), M(0), prepared(0) {}
void resize(int n) { N = n; }
void add(int frm, int to, T cost = 1, int i = -1) {
assert(!prepared);
assert(0 <= frm && 0 <= to && to < N);
if (i == -1) i = M;
auto e = edge_type({frm, to, cost, i});
edges.eb(e);
++M;
}
// wt, off
void read_tree(bool wt = false, int off = 1) { read_graph(N - 1, wt, off); }
void read_graph(int M, bool wt = false, int off = 1) {
for (int m = 0; m < M; ++m) {
INT(a, b);
a -= off, b -= off;
if (!wt) {
add(a, b);
} else {
T c;
read(c);
add(a, b, c);
}
}
build();
}
void read_parent(int off = 1) {
for (int v = 1; v < N; ++v) {
INT(p);
p -= off;
add(p, v);
}
build();
}
void build() {
assert(!prepared);
prepared = true;
indptr.assign(N + 1, 0);
for (auto&& e: edges) {
indptr[e.frm + 1]++;
if (!directed) indptr[e.to + 1]++;
}
for (int v = 0; v < N; ++v) { indptr[v + 1] += indptr[v]; }
auto counter = indptr;
csr_edges.resize(indptr.back() + 1);
for (auto&& e: edges) {
csr_edges[counter[e.frm]++] = e;
if (!directed)
csr_edges[counter[e.to]++] = edge_type({e.to, e.frm, e.cost, e.id});
}
}
OutgoingEdges operator[](int v) const {
assert(prepared);
return {this, indptr[v], indptr[v + 1]};
}
vc<int> deg_array() {
if (vc_deg.empty()) calc_deg();
return vc_deg;
}
pair<vc<int>, vc<int>> deg_array_inout() {
if (vc_indeg.empty()) calc_deg_inout();
return {vc_indeg, vc_outdeg};
}
int deg(int v) {
if (vc_deg.empty()) calc_deg();
return vc_deg[v];
}
int in_deg(int v) {
if (vc_indeg.empty()) calc_deg_inout();
return vc_indeg[v];
}
int out_deg(int v) {
if (vc_outdeg.empty()) calc_deg_inout();
return vc_outdeg[v];
}
void debug() {
print("Graph");
if (!prepared) {
print("frm to cost id");
for (auto&& e: edges) print(e.frm, e.to, e.cost, e.id);
} else {
print("indptr", indptr);
print("frm to cost id");
FOR(v, N) for (auto&& e: (*this)[v]) print(e.frm, e.to, e.cost, e.id);
}
}
private:
void calc_deg() {
assert(vc_deg.empty());
vc_deg.resize(N);
for (auto&& e: edges) vc_deg[e.frm]++, vc_deg[e.to]++;
}
void calc_deg_inout() {
assert(vc_indeg.empty());
vc_indeg.resize(N);
vc_outdeg.resize(N);
for (auto&& e: edges) { vc_indeg[e.to]++, vc_outdeg[e.frm]++; }
}
};
#line 3 "/home/maspy/compro/library/graph/tree.hpp"
// HLD euler tour をとっていろいろ。
// 木以外、非連結でも dfs 順序や親がとれる。
template <typename Graph>
struct TREE {
Graph &G;
using Graph_type = Graph;
using WT = typename Graph::cost_type;
int N;
bool hld;
vector<int> LID, RID, head, V, parent, root;
vc<int> depth;
vc<WT> depth_weighted;
vector<bool> in_tree;
TREE(Graph &G, int r = -1, bool hld = 1)
: G(G),
N(G.N),
hld(hld),
LID(G.N),
RID(G.N),
head(G.N, r),
V(G.N),
parent(G.N, -1),
root(G.N, -1),
depth(G.N, -1),
depth_weighted(G.N, 0),
in_tree(G.M, 0) {
assert(G.is_prepared());
int t1 = 0;
if (r != -1) {
dfs_sz(r, -1);
dfs_hld(r, t1);
} else {
for (int r = 0; r < N; ++r) {
if (parent[r] == -1) {
head[r] = r;
dfs_sz(r, -1);
dfs_hld(r, t1);
}
}
}
for (auto &&v: V) root[v] = (parent[v] == -1 ? v : root[parent[v]]);
}
void dfs_sz(int v, int p) {
auto &sz = RID;
parent[v] = p;
depth[v] = (p == -1 ? 0 : depth[p] + 1);
sz[v] = 1;
int l = G.indptr[v], r = G.indptr[v + 1];
auto &csr = G.csr_edges;
// 使う辺があれば先頭にする
for (int i = r - 2; i >= l; --i) {
if (depth[csr[i + 1].to] == -1) swap(csr[i], csr[i + 1]);
}
int hld_sz = 0;
for (int i = l; i < r; ++i) {
auto e = csr[i];
if (depth[e.to] != -1) continue;
in_tree[e.id] = 1;
depth_weighted[e.to] = depth_weighted[v] + e.cost;
dfs_sz(e.to, v);
sz[v] += sz[e.to];
if (hld && chmax(hld_sz, sz[e.to]) && l < i) { swap(csr[l], csr[i]); }
}
}
void dfs_hld(int v, int ×) {
LID[v] = times++;
RID[v] += LID[v];
V[LID[v]] = v;
bool heavy = true;
for (auto &&e: G[v]) {
if (!in_tree[e.id] || depth[e.to] <= depth[v]) continue;
head[e.to] = (heavy ? head[v] : e.to);
heavy = false;
dfs_hld(e.to, times);
}
}
vc<int> heavy_path_at(int v) {
vc<int> P = {v};
while (1) {
int a = P.back();
for (auto &&e: G[a]) {
if (e.to != parent[a] && head[e.to] == v) {
P.eb(e.to);
break;
}
}
if (P.back() == a) break;
}
return P;
}
int e_to_v(int eid) {
auto e = G.edges[eid];
return (parent[e.frm] == e.to ? e.frm : e.to);
}
int ELID(int v) { return 2 * LID[v] - depth[v]; }
int ERID(int v) { return 2 * RID[v] - depth[v] - 1; }
/* k: 0-indexed */
int LA(int v, int k) {
assert(k <= depth[v]);
while (1) {
int u = head[v];
if (LID[v] - k >= LID[u]) return V[LID[v] - k];
k -= LID[v] - LID[u] + 1;
v = parent[u];
}
}
int LCA(int u, int v) {
for (;; v = parent[head[v]]) {
if (LID[u] > LID[v]) swap(u, v);
if (head[u] == head[v]) return u;
}
}
int lca(int u, int v) { return LCA(u, v); }
int la(int u, int v) { return LA(u, v); }
int subtree_size(int v) { return RID[v] - LID[v]; }
int dist(int a, int b) {
int c = LCA(a, b);
return depth[a] + depth[b] - 2 * depth[c];
}
WT dist(int a, int b, bool weighted) {
assert(weighted);
int c = LCA(a, b);
return depth_weighted[a] + depth_weighted[b] - WT(2) * depth_weighted[c];
}
// a is in b
bool in_subtree(int a, int b) { return LID[b] <= LID[a] && LID[a] < RID[b]; }
int jump(int a, int b, ll k = 1) {
if (k == 1) {
if (a == b) return -1;
return (in_subtree(b, a) ? LA(b, depth[b] - depth[a] - 1) : parent[a]);
}
int c = LCA(a, b);
int d_ac = depth[a] - depth[c];
int d_bc = depth[b] - depth[c];
if (k > d_ac + d_bc) return -1;
if (k <= d_ac) return LA(a, k);
return LA(b, d_ac + d_bc - k);
}
vc<int> collect_child(int v) {
vc<int> res;
for (auto &&e: G[v])
if (e.to != parent[v]) res.eb(e.to);
return res;
}
vc<pair<int, int>> get_path_decomposition(int u, int v, bool edge) {
// [始点, 終点] の"閉"区間列。
vc<pair<int, int>> up, down;
while (1) {
if (head[u] == head[v]) break;
if (LID[u] < LID[v]) {
down.eb(LID[head[v]], LID[v]);
v = parent[head[v]];
} else {
up.eb(LID[u], LID[head[u]]);
u = parent[head[u]];
}
}
if (LID[u] < LID[v]) down.eb(LID[u] + edge, LID[v]);
elif (LID[v] + edge <= LID[u]) up.eb(LID[u], LID[v] + edge);
reverse(all(down));
up.insert(up.end(), all(down));
return up;
}
void debug() {
print("V", V);
print("LID", LID);
print("RID", RID);
print("parent", parent);
print("depth", depth);
print("head", head);
print("in_tree(edge)", in_tree);
print("root", root);
}
};
#line 2 "/home/maspy/compro/library/mod/mod_inv.hpp"
// long でも大丈夫
ll mod_inv(ll val, ll mod) {
val %= mod;
if (val < 0) val += mod;
ll a = val, b = mod, u = 1, v = 0, t;
while (b > 0) {
t = a / b;
swap(a -= t * b, b), swap(u -= t * v, v);
}
if (u < 0) u += mod;
return u;
}
#line 1 "/home/maspy/compro/library/poly/convolution_naive.hpp"
template <class T>
vector<T> convolution_naive(const vector<T>& a, const vector<T>& b) {
int n = int(a.size()), m = int(b.size());
vector<T> ans(n + m - 1);
if (n < m) {
FOR(j, m) FOR(i, n) ans[i + j] += a[i] * b[j];
} else {
FOR(i, n) FOR(j, m) ans[i + j] += a[i] * b[j];
}
return ans;
}
#line 2 "/home/maspy/compro/library/poly/ntt.hpp"
template <class mint>
struct ntt_info {
static constexpr int bsf_constexpr(unsigned int n) {
int x = 0;
while (!(n & (1 << x))) x++;
return x;
}
static constexpr int rank2 = bsf_constexpr(mint::get_mod() - 1);
array<mint, rank2 + 1> root;
array<mint, rank2 + 1> iroot;
array<mint, max(0, rank2 - 1)> rate2;
array<mint, max(0, rank2 - 1)> irate2;
array<mint, max(0, rank2 - 2)> rate3;
array<mint, max(0, rank2 - 2)> irate3;
ntt_info() {
int g = primitive_root(mint::get_mod());
root[rank2] = mint(g).pow((mint::get_mod() - 1) >> rank2);
iroot[rank2] = mint(1) / root[rank2];
FOR_R(i, rank2) {
root[i] = root[i + 1] * root[i + 1];
iroot[i] = iroot[i + 1] * iroot[i + 1];
}
{
mint prod = 1, iprod = 1;
for (int i = 0; i <= rank2 - 2; i++) {
rate2[i] = root[i + 2] * prod;
irate2[i] = iroot[i + 2] * iprod;
prod *= iroot[i + 2];
iprod *= root[i + 2];
}
}
{
mint prod = 1, iprod = 1;
for (int i = 0; i <= rank2 - 3; i++) {
rate3[i] = root[i + 3] * prod;
irate3[i] = iroot[i + 3] * iprod;
prod *= iroot[i + 3];
iprod *= root[i + 3];
}
}
}
constexpr int primitive_root(int m) {
if (m == 167772161) return 3;
if (m == 469762049) return 3;
if (m == 754974721) return 11;
if (m == 880803841) return 26;
if (m == 998244353) return 3;
return -1;
}
};
template <class mint>
void ntt(vector<mint>& a, bool inverse) {
int n = int(a.size());
int h = topbit(n);
assert(n == 1 << h);
static const ntt_info<mint> info;
if (!inverse) {
int len = 0; // a[i, i+(n>>len), i+2*(n>>len), ..] is transformed
while (len < h) {
if (h - len == 1) {
int p = 1 << (h - len - 1);
mint rot = 1;
FOR(s, 1 << len) {
int offset = s << (h - len);
FOR(i, p) {
auto l = a[i + offset];
auto r = a[i + offset + p] * rot;
a[i + offset] = l + r;
a[i + offset + p] = l - r;
}
rot *= info.rate2[topbit(~s & -~s)];
}
len++;
} else {
int p = 1 << (h - len - 2);
mint rot = 1, imag = info.root[2];
for (int s = 0; s < (1 << len); s++) {
mint rot2 = rot * rot;
mint rot3 = rot2 * rot;
int offset = s << (h - len);
for (int i = 0; i < p; i++) {
auto mod2 = 1ULL * mint::get_mod() * mint::get_mod();
auto a0 = 1ULL * a[i + offset].val;
auto a1 = 1ULL * a[i + offset + p].val * rot.val;
auto a2 = 1ULL * a[i + offset + 2 * p].val * rot2.val;
auto a3 = 1ULL * a[i + offset + 3 * p].val * rot3.val;
auto a1na3imag = 1ULL * mint(a1 + mod2 - a3).val * imag.val;
auto na2 = mod2 - a2;
a[i + offset] = a0 + a2 + a1 + a3;
a[i + offset + 1 * p] = a0 + a2 + (2 * mod2 - (a1 + a3));
a[i + offset + 2 * p] = a0 + na2 + a1na3imag;
a[i + offset + 3 * p] = a0 + na2 + (mod2 - a1na3imag);
}
rot *= info.rate3[topbit(~s & -~s)];
}
len += 2;
}
}
} else {
mint coef = mint(1) / mint(len(a));
FOR(i, len(a)) a[i] *= coef;
int len = h;
while (len) {
if (len == 1) {
int p = 1 << (h - len);
mint irot = 1;
FOR(s, 1 << (len - 1)) {
int offset = s << (h - len + 1);
FOR(i, p) {
auto l = a[i + offset];
auto r = a[i + offset + p];
a[i + offset] = l + r;
a[i + offset + p]
= (unsigned long long)(mint::get_mod() + l.val - r.val)
* irot.val;
;
}
irot *= info.irate2[topbit(~s & -~s)];
}
len--;
} else {
int p = 1 << (h - len);
mint irot = 1, iimag = info.iroot[2];
FOR(s, (1 << (len - 2))) {
mint irot2 = irot * irot;
mint irot3 = irot2 * irot;
int offset = s << (h - len + 2);
for (int i = 0; i < p; i++) {
auto a0 = 1ULL * a[i + offset + 0 * p].val;
auto a1 = 1ULL * a[i + offset + 1 * p].val;
auto a2 = 1ULL * a[i + offset + 2 * p].val;
auto a3 = 1ULL * a[i + offset + 3 * p].val;
auto a2na3iimag
= 1ULL * mint((mint::get_mod() + a2 - a3) * iimag.val).val;
a[i + offset] = a0 + a1 + a2 + a3;
a[i + offset + 1 * p]
= (a0 + (mint::get_mod() - a1) + a2na3iimag) * irot.val;
a[i + offset + 2 * p]
= (a0 + a1 + (mint::get_mod() - a2) + (mint::get_mod() - a3))
* irot2.val;
a[i + offset + 3 * p]
= (a0 + (mint::get_mod() - a1) + (mint::get_mod() - a2na3iimag))
* irot3.val;
}
irot *= info.irate3[topbit(~s & -~s)];
}
len -= 2;
}
}
}
}
#line 1 "/home/maspy/compro/library/poly/fft.hpp"
namespace CFFT {
using real = double;
struct C {
real x, y;
C() : x(0), y(0) {}
C(real x, real y) : x(x), y(y) {}
inline C operator+(const C& c) const { return C(x + c.x, y + c.y); }
inline C operator-(const C& c) const { return C(x - c.x, y - c.y); }
inline C operator*(const C& c) const {
return C(x * c.x - y * c.y, x * c.y + y * c.x);
}
inline C conj() const { return C(x, -y); }
};
const real PI = acosl(-1);
int base = 1;
vector<C> rts = {{0, 0}, {1, 0}};
vector<int> rev = {0, 1};
void ensure_base(int nbase) {
if (nbase <= base) return;
rev.resize(1 << nbase);
rts.resize(1 << nbase);
for (int i = 0; i < (1 << nbase); i++) {
rev[i] = (rev[i >> 1] >> 1) + ((i & 1) << (nbase - 1));
}
while (base < nbase) {
real angle = PI * 2.0 / (1 << (base + 1));
for (int i = 1 << (base - 1); i < (1 << base); i++) {
rts[i << 1] = rts[i];
real angle_i = angle * (2 * i + 1 - (1 << base));
rts[(i << 1) + 1] = C(cos(angle_i), sin(angle_i));
}
++base;
}
}
void fft(vector<C>& a, int n) {
assert((n & (n - 1)) == 0);
int zeros = __builtin_ctz(n);
ensure_base(zeros);
int shift = base - zeros;
for (int i = 0; i < n; i++) {
if (i < (rev[i] >> shift)) { swap(a[i], a[rev[i] >> shift]); }
}
for (int k = 1; k < n; k <<= 1) {
for (int i = 0; i < n; i += 2 * k) {
for (int j = 0; j < k; j++) {
C z = a[i + j + k] * rts[j + k];
a[i + j + k] = a[i + j] - z;
a[i + j] = a[i + j] + z;
}
}
}
}
} // namespace CFFT
#line 7 "/home/maspy/compro/library/poly/convolution.hpp"
template <class mint>
vector<mint> convolution_ntt(vector<mint> a, vector<mint> b) {
int n = int(a.size()), m = int(b.size());
int sz = 1;
while (sz < n + m - 1) sz *= 2;
// sz = 2^k のときの高速化。分割統治的なやつで損しまくるので。
if ((n + m - 3) <= sz / 2) {
auto a_last = a.back(), b_last = b.back();
a.pop_back(), b.pop_back();
auto c = convolution(a, b);
c.resize(n + m - 1);
c[n + m - 2] = a_last * b_last;
FOR(i, len(a)) c[i + len(b)] += a[i] * b_last;
FOR(i, len(b)) c[i + len(a)] += b[i] * a_last;
return c;
}
a.resize(sz), b.resize(sz);
bool same = a == b;
ntt(a, 0);
if (same) {
b = a;
} else {
ntt(b, 0);
}
FOR(i, sz) a[i] *= b[i];
ntt(a, 1);
a.resize(n + m - 1);
return a;
}
template <typename mint>
vector<mint> convolution_garner(const vector<mint>& a, const vector<mint>& b) {
int n = len(a), m = len(b);
if (!n || !m) return {};
static const long long nttprimes[] = {754974721, 167772161, 469762049};
using mint0 = modint<754974721>;
using mint1 = modint<167772161>;
using mint2 = modint<469762049>;
vc<mint0> a0(n), b0(m);
vc<mint1> a1(n), b1(m);
vc<mint2> a2(n), b2(m);
FOR(i, n) a0[i] = a[i].val, a1[i] = a[i].val, a2[i] = a[i].val;
FOR(i, m) b0[i] = b[i].val, b1[i] = b[i].val, b2[i] = b[i].val;
auto c0 = convolution_ntt<mint0>(a0, b0);
auto c1 = convolution_ntt<mint1>(a1, b1);
auto c2 = convolution_ntt<mint2>(a2, b2);
static const long long m01 = 1LL * nttprimes[0] * nttprimes[1];
static const long long m0_inv_m1 = mint1(nttprimes[0]).inverse().val;
static const long long m01_inv_m2 = mint2(m01).inverse().val;
static const int mod = mint::get_mod();
auto garner = [&](mint0 x0, mint1 x1, mint2 x2) -> mint {
int r0 = x0.val, r1 = x1.val, r2 = x2.val;
int v1 = (m0_inv_m1 * (r1 + nttprimes[1] - r0)) % nttprimes[1];
auto v2 = (mint2(r2) - r0 - mint2(nttprimes[0]) * v1) * mint2(m01_inv_m2);
return mint(r0 + 1LL * nttprimes[0] * v1 + m01 % mod * v2.val);
};
vc<mint> c(len(c0));
FOR(i, len(c)) c[i] = garner(c0[i], c1[i], c2[i]);
return c;
}
template <typename R>
vc<double> convolution_fft(const vc<R>& a, const vc<R>& b) {
using C = CFFT::C;
int need = (int)a.size() + (int)b.size() - 1;
int nbase = 1;
while ((1 << nbase) < need) nbase++;
CFFT::ensure_base(nbase);
int sz = 1 << nbase;
vector<C> fa(sz);
for (int i = 0; i < sz; i++) {
int x = (i < (int)a.size() ? a[i] : 0);
int y = (i < (int)b.size() ? b[i] : 0);
fa[i] = C(x, y);
}
CFFT::fft(fa, sz);
C r(0, -0.25 / (sz >> 1)), s(0, 1), t(0.5, 0);
for (int i = 0; i <= (sz >> 1); i++) {
int j = (sz - i) & (sz - 1);
C z = (fa[j] * fa[j] - (fa[i] * fa[i]).conj()) * r;
fa[j] = (fa[i] * fa[i] - (fa[j] * fa[j]).conj()) * r;
fa[i] = z;
}
for (int i = 0; i < (sz >> 1); i++) {
C A0 = (fa[i] + fa[i + (sz >> 1)]) * t;
C A1 = (fa[i] - fa[i + (sz >> 1)]) * t * CFFT::rts[(sz >> 1) + i];
fa[i] = A0 + A1 * s;
}
CFFT::fft(fa, sz >> 1);
vector<double> ret(need);
for (int i = 0; i < need; i++) {
ret[i] = (i & 1 ? fa[i >> 1].y : fa[i >> 1].x);
}
return ret;
}
vector<ll> convolution(const vector<ll>& a, const vector<ll>& b) {
int n = len(a), m = len(b);
if (!n || !m) return {};
if (min(n, m) <= 60) return convolution_naive(a, b);
ll abs_sum_a = 0, abs_sum_b = 0;
ll LIM = 1e15;
FOR(i, n) abs_sum_a = min(LIM, abs_sum_a + abs(a[i]));
FOR(i, n) abs_sum_b = min(LIM, abs_sum_b + abs(b[i]));
if (i128(abs_sum_a) * abs_sum_b < 1e15) {
vc<double> c = convolution_fft<ll>(a, b);
vc<ll> res(len(c));
FOR(i, len(c)) res[i] = ll(floor(c[i] + .5));
return res;
}
static constexpr unsigned long long MOD1 = 754974721; // 2^24
static constexpr unsigned long long MOD2 = 167772161; // 2^25
static constexpr unsigned long long MOD3 = 469762049; // 2^26
static constexpr unsigned long long M2M3 = MOD2 * MOD3;
static constexpr unsigned long long M1M3 = MOD1 * MOD3;
static constexpr unsigned long long M1M2 = MOD1 * MOD2;
static constexpr unsigned long long M1M2M3 = MOD1 * MOD2 * MOD3;
static const unsigned long long i1 = mod_inv(MOD2 * MOD3, MOD1);
static const unsigned long long i2 = mod_inv(MOD1 * MOD3, MOD2);
static const unsigned long long i3 = mod_inv(MOD1 * MOD2, MOD3);
using mint1 = modint<MOD1>;
using mint2 = modint<MOD2>;
using mint3 = modint<MOD3>;
vc<mint1> a1(n), b1(m);
vc<mint2> a2(n), b2(m);
vc<mint3> a3(n), b3(m);
FOR(i, n) a1[i] = a[i], a2[i] = a[i], a3[i] = a[i];
FOR(i, m) b1[i] = b[i], b2[i] = b[i], b3[i] = b[i];
auto c1 = convolution_ntt<mint1>(a1, b1);
auto c2 = convolution_ntt<mint2>(a2, b2);
auto c3 = convolution_ntt<mint3>(a3, b3);
vc<ll> c(n + m - 1);
FOR(i, n + m - 1) {
u64 x = 0;
x += (c1[i].val * i1) % MOD1 * M2M3;
x += (c2[i].val * i2) % MOD2 * M1M3;
x += (c3[i].val * i3) % MOD3 * M1M2;
ll diff = c1[i].val - ((long long)(x) % (long long)(MOD1));
if (diff < 0) diff += MOD1;
static constexpr unsigned long long offset[5]
= {0, 0, M1M2M3, 2 * M1M2M3, 3 * M1M2M3};
x -= offset[diff % 5];
c[i] = x;
}
return c;
}
template <typename mint>
enable_if_t<is_same<mint, modint998>::value, vc<mint>> convolution(
const vc<mint>& a, const vc<mint>& b) {
int n = len(a), m = len(b);
if (!n || !m) return {};
if (min(n, m) <= 60) return convolution_naive(a, b);
return convolution_ntt(a, b);
}
template <typename mint>
enable_if_t<!is_same<mint, modint998>::value, vc<mint>> convolution(
const vc<mint>& a, const vc<mint>& b) {
int n = len(a), m = len(b);
if (!n || !m) return {};
if (min(n, m) <= 60) return convolution_naive(a, b);
return convolution_garner(a, b);
}
#line 6 "main.cpp"
using mint = modint998;
void solve() {
LL(N, K);
VEC(mint, A, N + 1);
Graph<int, 1> G(N + 1);
FOR(v, 1, N + 1) {
LL(p);
G.add(p, v);
}
G.build();
TREE<decltype(G)> tree(G);
vc<mint> ANS(N + 1);
vc<mint> X(N + 1);
{
mint x = 1;
FOR(k, N + 1) {
X[k] = x;
x *= mint(K - k);
x *= inv<mint>(k + 1);
}
}
using poly = vc<mint>;
auto dfs = [&](auto& dfs, int v) -> poly {
auto P = tree.heavy_path_at(v);
const int n = len(P);
vc<poly> dat(n);
FOR(i, n) {
int w = P[i];
poly f = {A[w]};
for (auto&& e: G[w]) {
if (tree.head[e.to] == v) continue;
poly g = dfs(dfs, e.to);
g.insert(g.begin(), mint(0));
FOR(k, len(g)) {
if (k >= len(f)) f.resize(k + 1);
f[k] += g[k];
}
}
dat[i] = f;
}
FOR(i, n) {
auto& f = dat[i];
FOR(k, len(f)) ANS[P[i]] += f[k] * X[k];
}
/* ここを分割統治で高速化
FOR(i, n) FOR(j, i + 1, n) {
int d = j - i;
auto& f = dat[j];
FOR(k, len(f)) { ANS[P[i]] += f[k] * X[k + d]; }
}
*/
vc<pi> LR;
LR.eb(0, n);
while (len(LR)) {
auto [L, R] = pick(LR);
if (R - L <= 1) continue;
int M = (L + R) / 2;
LR.eb(L, M);
LR.eb(M, R);
vc<mint> g;
FOR(j, M, R) {
int d = j - M;
auto& f = dat[j];
FOR(k, len(f)) {
if (len(g) <= k + d) g.resize(k + d + 1);
g[k + d] += f[k];
}
}
reverse(all(g));
vc<mint> Y = {X.begin(), X.begin() + (len(g) + M - L)};
auto h = convolution(g, Y);
FOR(i, L, M) {
int d = M - i;
// FOR(k, len(g)) { ANS[P[i]] += g[len(g) - 1 - k] * X[k + M - i]; }
ANS[P[i]] += h[len(g) - 1 + M - i];
}
}
vc<mint> F;
FOR(i, n) {
auto& f = dat[i];
FOR(k, len(f)) {
int to = k + i;
if (len(F) <= to) F.resize(to + 1);
F[to] += f[k];
}
}
return F;
};
dfs(dfs, 0);
for (auto&& x: ANS) print(x);
}
signed main() {
cout << fixed << setprecision(15);
ll T = 1;
// LL(T);
FOR(T) solve();
return 0;
}