結果
| 問題 |
No.1321 塗るめた
|
| コンテスト | |
| ユーザー |
opt
|
| 提出日時 | 2020-12-18 20:35:09 |
| 言語 | C++17 (gcc 13.3.0 + boost 1.87.0) |
| 結果 |
AC
|
| 実行時間 | 148 ms / 2,000 ms |
| コード長 | 36,126 bytes |
| コンパイル時間 | 6,215 ms |
| コンパイル使用メモリ | 243,756 KB |
| 最終ジャッジ日時 | 2025-01-17 03:05:39 |
|
ジャッジサーバーID (参考情報) |
judge4 / judge2 |
(要ログイン)
| ファイルパターン | 結果 |
|---|---|
| sample | AC * 2 |
| other | AC * 45 |
ソースコード
#include <bits/stdc++.h>
using namespace std;
#include <algorithm>
#include <array>
#ifdef _MSC_VER
#include <intrin.h>
#endif
namespace atcoder {
namespace internal {
// @param n `0 <= n`
// @return minimum non-negative `x` s.t. `n <= 2**x`
int ceil_pow2(int n) {
int x = 0;
while ((1U << x) < (unsigned int)(n)) x++;
return x;
}
// @param n `1 <= n`
// @return minimum non-negative `x` s.t. `(n & (1 << x)) != 0`
int bsf(unsigned int n) {
#ifdef _MSC_VER
unsigned long index;
_BitScanForward(&index, n);
return index;
#else
return __builtin_ctz(n);
#endif
}
} // namespace internal
} // namespace atcoder
#include <utility>
#ifdef _MSC_VER
#include <intrin.h>
#endif
namespace atcoder {
namespace internal {
// @param m `1 <= m`
// @return x mod m
constexpr long long safe_mod(long long x, long long m) {
x %= m;
if (x < 0) x += m;
return x;
}
// Fast modular multiplication by barrett reduction
// Reference: https://en.wikipedia.org/wiki/Barrett_reduction
// NOTE: reconsider after Ice Lake
struct barrett {
unsigned int _m;
unsigned long long im;
// @param m `1 <= m < 2^31`
barrett(unsigned int m) : _m(m), im((unsigned long long)(-1) / m + 1) {}
// @return m
unsigned int umod() const { return _m; }
// @param a `0 <= a < m`
// @param b `0 <= b < m`
// @return `a * b % m`
unsigned int mul(unsigned int a, unsigned int b) const {
// [1] m = 1
// a = b = im = 0, so okay
// [2] m >= 2
// im = ceil(2^64 / m)
// -> im * m = 2^64 + r (0 <= r < m)
// let z = a*b = c*m + d (0 <= c, d < m)
// a*b * im = (c*m + d) * im = c*(im*m) + d*im = c*2^64 + c*r + d*im
// c*r + d*im < m * m + m * im < m * m + 2^64 + m <= 2^64 + m * (m + 1) < 2^64 * 2
// ((ab * im) >> 64) == c or c + 1
unsigned long long z = a;
z *= b;
#ifdef _MSC_VER
unsigned long long x;
_umul128(z, im, &x);
#else
unsigned long long x =
(unsigned long long)(((unsigned __int128)(z)*im) >> 64);
#endif
unsigned int v = (unsigned int)(z - x * _m);
if (_m <= v) v += _m;
return v;
}
};
// @param n `0 <= n`
// @param m `1 <= m`
// @return `(x ** n) % m`
constexpr long long pow_mod_constexpr(long long x, long long n, int m) {
if (m == 1) return 0;
unsigned int _m = (unsigned int)(m);
unsigned long long r = 1;
unsigned long long y = safe_mod(x, m);
while (n) {
if (n & 1) r = (r * y) % _m;
y = (y * y) % _m;
n >>= 1;
}
return r;
}
// Reference:
// M. Forisek and J. Jancina,
// Fast Primality Testing for Integers That Fit into a Machine Word
// @param n `0 <= n`
constexpr bool is_prime_constexpr(int n) {
if (n <= 1) return false;
if (n == 2 || n == 7 || n == 61) return true;
if (n % 2 == 0) return false;
long long d = n - 1;
while (d % 2 == 0) d /= 2;
constexpr long long bases[3] = {2, 7, 61};
for (long long a : bases) {
long long t = d;
long long y = pow_mod_constexpr(a, t, n);
while (t != n - 1 && y != 1 && y != n - 1) {
y = y * y % n;
t <<= 1;
}
if (y != n - 1 && t % 2 == 0) {
return false;
}
}
return true;
}
template <int n> constexpr bool is_prime = is_prime_constexpr(n);
// @param b `1 <= b`
// @return pair(g, x) s.t. g = gcd(a, b), xa = g (mod b), 0 <= x < b/g
constexpr std::pair<long long, long long> inv_gcd(long long a, long long b) {
a = safe_mod(a, b);
if (a == 0) return {b, 0};
// Contracts:
// [1] s - m0 * a = 0 (mod b)
// [2] t - m1 * a = 0 (mod b)
// [3] s * |m1| + t * |m0| <= b
long long s = b, t = a;
long long m0 = 0, m1 = 1;
while (t) {
long long u = s / t;
s -= t * u;
m0 -= m1 * u; // |m1 * u| <= |m1| * s <= b
// [3]:
// (s - t * u) * |m1| + t * |m0 - m1 * u|
// <= s * |m1| - t * u * |m1| + t * (|m0| + |m1| * u)
// = s * |m1| + t * |m0| <= b
auto tmp = s;
s = t;
t = tmp;
tmp = m0;
m0 = m1;
m1 = tmp;
}
// by [3]: |m0| <= b/g
// by g != b: |m0| < b/g
if (m0 < 0) m0 += b / s;
return {s, m0};
}
// Compile time primitive root
// @param m must be prime
// @return primitive root (and minimum in now)
constexpr int primitive_root_constexpr(int m) {
if (m == 2) return 1;
if (m == 167772161) return 3;
if (m == 469762049) return 3;
if (m == 754974721) return 11;
if (m == 998244353) return 3;
int divs[20] = {};
divs[0] = 2;
int cnt = 1;
int x = (m - 1) / 2;
while (x % 2 == 0) x /= 2;
for (int i = 3; (long long)(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 (pow_mod_constexpr(g, (m - 1) / divs[i], m) == 1) {
ok = false;
break;
}
}
if (ok) return g;
}
}
template <int m> constexpr int primitive_root = primitive_root_constexpr(m);
} // namespace internal
} // namespace atcoder
#include <cassert>
#include <numeric>
#include <type_traits>
namespace atcoder {
namespace internal {
#ifndef _MSC_VER
template <class T>
using is_signed_int128 =
typename std::conditional<std::is_same<T, __int128_t>::value ||
std::is_same<T, __int128>::value,
std::true_type,
std::false_type>::type;
template <class T>
using is_unsigned_int128 =
typename std::conditional<std::is_same<T, __uint128_t>::value ||
std::is_same<T, unsigned __int128>::value,
std::true_type,
std::false_type>::type;
template <class T>
using make_unsigned_int128 =
typename std::conditional<std::is_same<T, __int128_t>::value,
__uint128_t,
unsigned __int128>;
template <class T>
using is_integral = typename std::conditional<std::is_integral<T>::value ||
is_signed_int128<T>::value ||
is_unsigned_int128<T>::value,
std::true_type,
std::false_type>::type;
template <class T>
using is_signed_int = typename std::conditional<(is_integral<T>::value &&
std::is_signed<T>::value) ||
is_signed_int128<T>::value,
std::true_type,
std::false_type>::type;
template <class T>
using is_unsigned_int =
typename std::conditional<(is_integral<T>::value &&
std::is_unsigned<T>::value) ||
is_unsigned_int128<T>::value,
std::true_type,
std::false_type>::type;
template <class T>
using to_unsigned = typename std::conditional<
is_signed_int128<T>::value,
make_unsigned_int128<T>,
typename std::conditional<std::is_signed<T>::value,
std::make_unsigned<T>,
std::common_type<T>>::type>::type;
#else
template <class T> using is_integral = typename std::is_integral<T>;
template <class T>
using is_signed_int =
typename std::conditional<is_integral<T>::value && std::is_signed<T>::value,
std::true_type,
std::false_type>::type;
template <class T>
using is_unsigned_int =
typename std::conditional<is_integral<T>::value &&
std::is_unsigned<T>::value,
std::true_type,
std::false_type>::type;
template <class T>
using to_unsigned = typename std::conditional<is_signed_int<T>::value,
std::make_unsigned<T>,
std::common_type<T>>::type;
#endif
template <class T>
using is_signed_int_t = std::enable_if_t<is_signed_int<T>::value>;
template <class T>
using is_unsigned_int_t = std::enable_if_t<is_unsigned_int<T>::value>;
template <class T> using to_unsigned_t = typename to_unsigned<T>::type;
} // namespace internal
} // namespace atcoder
#include <cassert>
#include <numeric>
#include <type_traits>
#ifdef _MSC_VER
#include <intrin.h>
#endif
namespace atcoder {
namespace internal {
struct modint_base {};
struct static_modint_base : modint_base {};
template <class T> using is_modint = std::is_base_of<modint_base, T>;
template <class T> using is_modint_t = std::enable_if_t<is_modint<T>::value>;
} // namespace internal
template <int m, std::enable_if_t<(1 <= m)>* = nullptr>
struct static_modint : internal::static_modint_base {
using mint = static_modint;
public:
static constexpr int mod() { return m; }
static mint raw(int v) {
mint x;
x._v = v;
return x;
}
static_modint() : _v(0) {}
template <class T, internal::is_signed_int_t<T>* = nullptr>
static_modint(T v) {
long long x = (long long)(v % (long long)(umod()));
if (x < 0) x += umod();
_v = (unsigned int)(x);
}
template <class T, internal::is_unsigned_int_t<T>* = nullptr>
static_modint(T v) {
_v = (unsigned int)(v % umod());
}
static_modint(bool v) { _v = ((unsigned int)(v) % umod()); }
unsigned int val() const { return _v; }
mint& operator++() {
_v++;
if (_v == umod()) _v = 0;
return *this;
}
mint& operator--() {
if (_v == 0) _v = umod();
_v--;
return *this;
}
mint operator++(int) {
mint result = *this;
++*this;
return result;
}
mint operator--(int) {
mint result = *this;
--*this;
return result;
}
mint& operator+=(const mint& rhs) {
_v += rhs._v;
if (_v >= umod()) _v -= umod();
return *this;
}
mint& operator-=(const mint& rhs) {
_v -= rhs._v;
if (_v >= umod()) _v += umod();
return *this;
}
mint& operator*=(const mint& rhs) {
unsigned long long z = _v;
z *= rhs._v;
_v = (unsigned int)(z % umod());
return *this;
}
mint& operator/=(const mint& rhs) { return *this = *this * rhs.inv(); }
mint operator+() const { return *this; }
mint operator-() const { return mint() - *this; }
mint pow(long long n) const {
assert(0 <= n);
mint x = *this, r = 1;
while (n) {
if (n & 1) r *= x;
x *= x;
n >>= 1;
}
return r;
}
mint inv() const {
if (prime) {
assert(_v);
return pow(umod() - 2);
} else {
auto eg = internal::inv_gcd(_v, m);
assert(eg.first == 1);
return eg.second;
}
}
friend mint operator+(const mint& lhs, const mint& rhs) {
return mint(lhs) += rhs;
}
friend mint operator-(const mint& lhs, const mint& rhs) {
return mint(lhs) -= rhs;
}
friend mint operator*(const mint& lhs, const mint& rhs) {
return mint(lhs) *= rhs;
}
friend mint operator/(const mint& lhs, const mint& rhs) {
return mint(lhs) /= rhs;
}
friend bool operator==(const mint& lhs, const mint& rhs) {
return lhs._v == rhs._v;
}
friend bool operator!=(const mint& lhs, const mint& rhs) {
return lhs._v != rhs._v;
}
private:
unsigned int _v;
static constexpr unsigned int umod() { return m; }
static constexpr bool prime = internal::is_prime<m>;
};
template <int id> struct dynamic_modint : internal::modint_base {
using mint = dynamic_modint;
public:
static int mod() { return (int)(bt.umod()); }
static void set_mod(int m) {
assert(1 <= m);
bt = internal::barrett(m);
}
static mint raw(int v) {
mint x;
x._v = v;
return x;
}
dynamic_modint() : _v(0) {}
template <class T, internal::is_signed_int_t<T>* = nullptr>
dynamic_modint(T v) {
long long x = (long long)(v % (long long)(mod()));
if (x < 0) x += mod();
_v = (unsigned int)(x);
}
template <class T, internal::is_unsigned_int_t<T>* = nullptr>
dynamic_modint(T v) {
_v = (unsigned int)(v % mod());
}
dynamic_modint(bool v) { _v = ((unsigned int)(v) % mod()); }
unsigned int val() const { return _v; }
mint& operator++() {
_v++;
if (_v == umod()) _v = 0;
return *this;
}
mint& operator--() {
if (_v == 0) _v = umod();
_v--;
return *this;
}
mint operator++(int) {
mint result = *this;
++*this;
return result;
}
mint operator--(int) {
mint result = *this;
--*this;
return result;
}
mint& operator+=(const mint& rhs) {
_v += rhs._v;
if (_v >= umod()) _v -= umod();
return *this;
}
mint& operator-=(const mint& rhs) {
_v += mod() - rhs._v;
if (_v >= umod()) _v -= umod();
return *this;
}
mint& operator*=(const mint& rhs) {
_v = bt.mul(_v, rhs._v);
return *this;
}
mint& operator/=(const mint& rhs) { return *this = *this * rhs.inv(); }
mint operator+() const { return *this; }
mint operator-() const { return mint() - *this; }
mint pow(long long n) const {
assert(0 <= n);
mint x = *this, r = 1;
while (n) {
if (n & 1) r *= x;
x *= x;
n >>= 1;
}
return r;
}
mint inv() const {
auto eg = internal::inv_gcd(_v, mod());
assert(eg.first == 1);
return eg.second;
}
friend mint operator+(const mint& lhs, const mint& rhs) {
return mint(lhs) += rhs;
}
friend mint operator-(const mint& lhs, const mint& rhs) {
return mint(lhs) -= rhs;
}
friend mint operator*(const mint& lhs, const mint& rhs) {
return mint(lhs) *= rhs;
}
friend mint operator/(const mint& lhs, const mint& rhs) {
return mint(lhs) /= rhs;
}
friend bool operator==(const mint& lhs, const mint& rhs) {
return lhs._v == rhs._v;
}
friend bool operator!=(const mint& lhs, const mint& rhs) {
return lhs._v != rhs._v;
}
private:
unsigned int _v;
static internal::barrett bt;
static unsigned int umod() { return bt.umod(); }
};
template <int id> internal::barrett dynamic_modint<id>::bt = 998244353;
using modint998244353 = static_modint<998244353>;
using modint1000000007 = static_modint<1000000007>;
using modint = dynamic_modint<-1>;
namespace internal {
template <class T>
using is_static_modint = std::is_base_of<internal::static_modint_base, T>;
template <class T>
using is_static_modint_t = std::enable_if_t<is_static_modint<T>::value>;
template <class> struct is_dynamic_modint : public std::false_type {};
template <int id>
struct is_dynamic_modint<dynamic_modint<id>> : public std::true_type {};
template <class T>
using is_dynamic_modint_t = std::enable_if_t<is_dynamic_modint<T>::value>;
} // namespace internal
} // namespace atcoder
#include <cassert>
#include <type_traits>
#include <vector>
namespace atcoder {
namespace internal {
template <class mint, internal::is_static_modint_t<mint>* = nullptr>
void butterfly(std::vector<mint>& a) {
static constexpr int g = internal::primitive_root<mint::mod()>;
int n = int(a.size());
int h = internal::ceil_pow2(n);
static bool first = true;
static mint sum_e[30]; // sum_e[i] = ies[0] * ... * ies[i - 1] * es[i]
if (first) {
first = false;
mint es[30], ies[30]; // es[i]^(2^(2+i)) == 1
int cnt2 = bsf(mint::mod() - 1);
mint e = mint(g).pow((mint::mod() - 1) >> cnt2), ie = e.inv();
for (int i = cnt2; i >= 2; i--) {
// e^(2^i) == 1
es[i - 2] = e;
ies[i - 2] = ie;
e *= e;
ie *= ie;
}
mint now = 1;
for (int i = 0; i <= cnt2 - 2; i++) {
sum_e[i] = es[i] * now;
now *= ies[i];
}
}
for (int ph = 1; ph <= h; ph++) {
int w = 1 << (ph - 1), p = 1 << (h - ph);
mint now = 1;
for (int s = 0; s < w; s++) {
int offset = s << (h - ph + 1);
for (int i = 0; i < p; i++) {
auto l = a[i + offset];
auto r = a[i + offset + p] * now;
a[i + offset] = l + r;
a[i + offset + p] = l - r;
}
now *= sum_e[bsf(~(unsigned int)(s))];
}
}
}
template <class mint, internal::is_static_modint_t<mint>* = nullptr>
void butterfly_inv(std::vector<mint>& a) {
static constexpr int g = internal::primitive_root<mint::mod()>;
int n = int(a.size());
int h = internal::ceil_pow2(n);
static bool first = true;
static mint sum_ie[30]; // sum_ie[i] = es[0] * ... * es[i - 1] * ies[i]
if (first) {
first = false;
mint es[30], ies[30]; // es[i]^(2^(2+i)) == 1
int cnt2 = bsf(mint::mod() - 1);
mint e = mint(g).pow((mint::mod() - 1) >> cnt2), ie = e.inv();
for (int i = cnt2; i >= 2; i--) {
// e^(2^i) == 1
es[i - 2] = e;
ies[i - 2] = ie;
e *= e;
ie *= ie;
}
mint now = 1;
for (int i = 0; i <= cnt2 - 2; i++) {
sum_ie[i] = ies[i] * now;
now *= es[i];
}
}
for (int ph = h; ph >= 1; ph--) {
int w = 1 << (ph - 1), p = 1 << (h - ph);
mint inow = 1;
for (int s = 0; s < w; s++) {
int offset = s << (h - ph + 1);
for (int i = 0; i < p; i++) {
auto l = a[i + offset];
auto r = a[i + offset + p];
a[i + offset] = l + r;
a[i + offset + p] =
(unsigned long long)(mint::mod() + l.val() - r.val()) *
inow.val();
}
inow *= sum_ie[bsf(~(unsigned int)(s))];
}
}
}
} // namespace internal
template <class mint, internal::is_static_modint_t<mint>* = nullptr>
std::vector<mint> convolution(std::vector<mint> a, std::vector<mint> b) {
int n = int(a.size()), m = int(b.size());
if (!n || !m) return {};
if (std::min(n, m) <= 60) {
if (n < m) {
std::swap(n, m);
std::swap(a, b);
}
std::vector<mint> ans(n + m - 1);
for (int i = 0; i < n; i++) {
for (int j = 0; j < m; j++) {
ans[i + j] += a[i] * b[j];
}
}
return ans;
}
int z = 1 << internal::ceil_pow2(n + m - 1);
a.resize(z);
internal::butterfly(a);
b.resize(z);
internal::butterfly(b);
for (int i = 0; i < z; i++) {
a[i] *= b[i];
}
internal::butterfly_inv(a);
a.resize(n + m - 1);
mint iz = mint(z).inv();
for (int i = 0; i < n + m - 1; i++) a[i] *= iz;
return a;
}
template <unsigned int mod = 998244353,
class T,
std::enable_if_t<internal::is_integral<T>::value>* = nullptr>
std::vector<T> convolution(const std::vector<T>& a, const std::vector<T>& b) {
int n = int(a.size()), m = int(b.size());
if (!n || !m) return {};
using mint = static_modint<mod>;
std::vector<mint> a2(n), b2(m);
for (int i = 0; i < n; i++) {
a2[i] = mint(a[i]);
}
for (int i = 0; i < m; i++) {
b2[i] = mint(b[i]);
}
auto c2 = convolution(move(a2), move(b2));
std::vector<T> c(n + m - 1);
for (int i = 0; i < n + m - 1; i++) {
c[i] = c2[i].val();
}
return c;
}
std::vector<long long> convolution_ll(const std::vector<long long>& a,
const std::vector<long long>& b) {
int n = int(a.size()), m = int(b.size());
if (!n || !m) return {};
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 constexpr unsigned long long i1 =
internal::inv_gcd(MOD2 * MOD3, MOD1).second;
static constexpr unsigned long long i2 =
internal::inv_gcd(MOD1 * MOD3, MOD2).second;
static constexpr unsigned long long i3 =
internal::inv_gcd(MOD1 * MOD2, MOD3).second;
auto c1 = convolution<MOD1>(a, b);
auto c2 = convolution<MOD2>(a, b);
auto c3 = convolution<MOD3>(a, b);
std::vector<long long> c(n + m - 1);
for (int i = 0; i < n + m - 1; i++) {
unsigned long long x = 0;
x += (c1[i] * i1) % MOD1 * M2M3;
x += (c2[i] * i2) % MOD2 * M1M3;
x += (c3[i] * i3) % MOD3 * M1M2;
// B = 2^63, -B <= x, r(real value) < B
// (x, x - M, x - 2M, or x - 3M) = r (mod 2B)
// r = c1[i] (mod MOD1)
// focus on MOD1
// r = x, x - M', x - 2M', x - 3M' (M' = M % 2^64) (mod 2B)
// r = x,
// x - M' + (0 or 2B),
// x - 2M' + (0, 2B or 4B),
// x - 3M' + (0, 2B, 4B or 6B) (without mod!)
// (r - x) = 0, (0)
// - M' + (0 or 2B), (1)
// -2M' + (0 or 2B or 4B), (2)
// -3M' + (0 or 2B or 4B or 6B) (3) (mod MOD1)
// we checked that
// ((1) mod MOD1) mod 5 = 2
// ((2) mod MOD1) mod 5 = 3
// ((3) mod MOD1) mod 5 = 4
long long diff =
c1[i] - internal::safe_mod((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;
}
} // namespace atcoder
using namespace atcoder;
// input and output of modint
istream &operator>>(istream &is, modint998244353 &a) { long long v; is >> v; a = v; return is; }
ostream &operator<<(ostream &os, const modint998244353 &a) { return os << a.val(); }
istream &operator>>(istream &is, modint1000000007 &a) { long long v; is >> v; a = v; return is; }
ostream &operator<<(ostream &os, const modint1000000007 &a) { return os << a.val(); }
template<int m> istream &operator>>(istream &is, static_modint<m> &a) { long long v; is >> v; a = v; return is; }
template<int m> ostream &operator<<(ostream &os, const static_modint<m> &a) { return os << a.val(); }
template<int m> istream &operator>>(istream &is, dynamic_modint<m> &a) { long long v; is >> v; a = v; return is; }
template<int m> ostream &operator<<(ostream &os, const dynamic_modint<m> &a) { return os << a.val(); }
#define rep2(i, m, n) for (int i = (m); i < (n); ++i)
#define rep(i, n) rep2(i, 0, n)
#define drep2(i, m, n) for (int i = (m)-1; i >= (n); --i)
#define drep(i, n) drep2(i, n, 0)
#define all(x) (x).begin(), (x).end()
#define rall(x) (x).rbegin(), (x).rend()
#ifdef LOCAL
void debug_out() { cerr << endl; }
template <class Head, class... Tail> void debug_out(Head H, Tail... T) { cerr << ' ' << H; debug_out(T...); }
#define debug(...) cerr << 'L' << __LINE__ << " [" << #__VA_ARGS__ << "]:", debug_out(__VA_ARGS__)
#define dump(x) cerr << 'L' << __LINE__ << " " << #x << " = " << (x) << endl
#else
#define debug(...) (void(0))
#define dump(x) (void(0))
#endif
template<class T> using V = vector<T>;
using ll = long long;
using ld = long double;
using Vi = V<int>; using VVi = V<Vi>;
using Vl = V<ll>; using VVl = V<Vl>;
using Vd = V<ld>; using VVd = V<Vd>;
using Vb = V<bool>; using VVb = V<Vb>;
template<class T> using priority_queue_rev = priority_queue<T, vector<T>, greater<T>>;
template<class T> vector<T> make_vec(size_t n, T a) { return vector<T>(n, a); }
template<class... Ts> auto make_vec(size_t n, Ts... ts) { return vector<decltype(make_vec(ts...))>(n, make_vec(ts...)); }
template<class T> inline int sz(const T &x) { return size(x); }
template<class T> inline bool chmin(T &a, const T b) { if (a > b) { a = b; return true; } return false; }
template<class T> inline bool chmax(T &a, const T b) { if (a < b) { a = b; return true; } return false; }
template<class T1, class T2> istream &operator>>(istream &is, pair<T1, T2> &p) { is >> p.first >> p.second; return is; }
template<class T1, class T2> ostream &operator<<(ostream &os, const pair<T1, T2> &p) { os << '(' << p.first << ", " << p.second << ')'; return os; }
template<class T, size_t n> istream &operator>>(istream &is, array<T, n> &v) { for (auto &e : v) is >> e; return is; }
template<class T, size_t n> ostream &operator<<(ostream &os, const array<T, n> &v) { for (auto &e : v) os << e << ' '; return os; }
template<class T> istream &operator>>(istream &is, vector<T> &v) { for (auto &e : v) is >> e; return is; }
template<class T> ostream &operator<<(ostream &os, const vector<T> &v) { for (auto &e : v) os << e << ' '; return os; }
template<class T> inline void deduplicate(vector<T> &a) { sort(all(a)); a.erase(unique(all(a)), a.end()); }
template<class T> inline int count_between(const vector<T> &a, T l, T r) { return lower_bound(all(a), r) - lower_bound(all(a), l); } // [l, r)
inline ll cDiv(const ll x, const ll y) { return (x+y-1) / y; } // ceil(x/y)
inline int fLog2(const ll x) { assert(x > 0); return 63-__builtin_clzll(x); } // floor(log2(x))
inline int cLog2(const ll x) { assert(x > 0); return (x == 1) ? 0 : 64-__builtin_clzll(x-1); } // ceil(log2(x))
inline int popcount(const ll x) { return __builtin_popcountll(x); }
inline void fail() { cout << -1 << '\n'; exit(0); }
struct fast_ios { fast_ios(){ cin.tie(nullptr); ios::sync_with_stdio(false); cout << fixed << setprecision(20); }; } fast_ios_;
// const int INF = (1<<30) - 1;
// const ll INFll = (1ll<<60) - 1;
// const ld EPS = 1e-10;
// const ld PI = acos(-1.0);
// using mint = modint998244353;
// using mint = modint1000000007;
// using mint = modint;
// using Vm = V<mint>; using VVm = V<Vm>;
template<class T>
struct FormalPowerSeries : vector<T> {
using vector<T>::vector;
using vector<T>::operator=;
using F = FormalPowerSeries;
F operator-() const {
F res(*this);
for (auto &e : res) e = -e;
return res;
}
F &operator*=(const T &g) {
for (auto &e : *this) e *= g;
return *this;
}
F &operator/=(const T &g) {
assert(g != T(0));
*this *= g.inv();
return *this;
}
F &operator+=(const F &g) {
int n = this->size(), m = g.size();
rep(i, min(n, m)) (*this)[i] += g[i];
return *this;
}
F &operator-=(const F &g) {
int n = this->size(), m = g.size();
rep(i, min(n, m)) (*this)[i] -= g[i];
return *this;
}
F &operator<<=(const int d) {
int n = this->size();
this->insert(this->begin(), d, 0);
this->resize(n);
return *this;
}
F &operator>>=(const int d) {
int n = this->size();
this->erase(this->begin(), this->begin() + min(n, d));
this->resize(n);
return *this;
}
// O(n log n)
F inv(int d = -1) const {
int n = this->size();
assert(n != 0 && (*this)[0] != 0);
if (d == -1) d = n;
assert(d >= 0);
F res{(*this)[0].inv()};
for (int m = 1; m < d; m *= 2) {
F f(this->begin(), this->begin() + min(n, 2*m));
F g(res);
f.resize(2*m), internal::butterfly(f);
g.resize(2*m), internal::butterfly(g);
rep(i, 2*m) f[i] *= g[i];
internal::butterfly_inv(f);
f.erase(f.begin(), f.begin() + m);
f.resize(2*m), internal::butterfly(f);
rep(i, 2*m) f[i] *= g[i];
internal::butterfly_inv(f);
T iz = T(2*m).inv(); iz *= -iz;
rep(i, m) f[i] *= iz;
res.insert(res.end(), f.begin(), f.begin() + m);
}
return {res.begin(), res.begin() + d};
}
// fast: FMT-friendly modulus only
// O(n log n)
F &multiply_inplace(const F &g, int d = -1) {
int n = this->size();
if (d == -1) d = n;
assert(d >= 0);
*this = convolution(move(*this), g);
this->resize(d);
return *this;
}
F multiply(const F &g, int d = -1) const { return F(*this).multiply_inplace(g); }
// O(n log n)
F ÷_inplace(const F &g, int d = -1) {
int n = this->size();
if (d == -1) d = n;
assert(d >= 0);
*this = convolution(move(*this), g.inv(d));
this->resize(d);
return *this;
}
F divide(const F &g, int d = -1) const { return F(*this).divide_inplace(g); }
// // naive
// // O(n^2)
// F &operator*=(const F &g) {
// int n = this->size(), m = g.size();
// drep(i, n) {
// (*this)[i] *= g[0];
// rep2(j, 1, min(i+1, m)) (*this)[i] += (*this)[i-j] * g[j];
// }
// return *this;
// }
// // O(n^2)
// F &operator/=(const F &g) {
// assert(g[0] != T(0));
// T ig0 = g[0].inv();
// int n = this->size(), m = g.size();
// rep(i, n) {
// rep2(j, 1, min(i+1, m)) (*this)[i] -= (*this)[i-j] * g[j];
// (*this)[i] *= ig0;
// }
// return *this;
// }
// sparse
// O(nk)
F &operator*=(vector<pair<int, T>> g) {
int n = this->size();
auto [d, c] = g.front();
if (d == 0) g.erase(g.begin());
else c = 0;
drep(i, n) {
(*this)[i] *= c;
for (auto &[j, b] : g) {
if (j > i) break;
(*this)[i] += (*this)[i-j] * b;
}
}
return *this;
}
// O(nk)
F &operator/=(vector<pair<int, T>> g) {
int n = this->size();
auto [d, c] = g.front();
assert(d == 0 && c != T(0));
T ic = c.inv();
g.erase(g.begin());
rep(i, n) {
for (auto &[j, b] : g) {
if (j > i) break;
(*this)[i] -= (*this)[i-j] * b;
}
(*this)[i] *= ic;
}
return *this;
}
// multiply and divide (1 + cz^d)
// O(n)
void multiply(const int d, const T c) {
int n = this->size();
if (c == T(1)) drep(i, n-d) (*this)[i+d] += (*this)[i];
else if (c == T(-1)) drep(i, n-d) (*this)[i+d] -= (*this)[i];
else drep(i, n-d) (*this)[i+d] += (*this)[i] * c;
}
// O(n)
void divide(const int d, const T c) {
int n = this->size();
if (c == T(1)) rep(i, n-d) (*this)[i+d] -= (*this)[i];
else if (c == T(-1)) rep(i, n-d) (*this)[i+d] += (*this)[i];
else rep(i, n-d) (*this)[i+d] -= (*this)[i] * c;
}
// O(n)
T eval(const T &a) const {
T x(1), res(0);
for (auto e : *this) res += e * x, x *= a;
return res;
}
// O(n)
F &integrate_inplace() {
int n = this->size();
assert(n > 0);
if (n == 1) return *this = F{0};
this->insert(this->begin(), 0);
this->pop_back();
vector<T> inv(n);
inv[1] = 1;
int p = T::mod();
rep2(i, 2, n) inv[i] = - inv[p%i] * (p/i);
rep2(i, 2, n) (*this)[i] *= inv[i];
return *this;
}
F integrate() const { return F(*this).integrate_inplace(); }
// O(n)
F &differentiate_inplace() {
int n = this->size();
assert(n > 0);
rep2(i, 2, n) (*this)[i] *= i;
this->erase(this->begin());
this->push_back(0);
return *this;
}
F differentiate() const { return F(*this).differentiate_inplace(); }
// O(n log n)
F log(int d = -1) const {
int n = this->size();
assert(n > 0 && (*this)[0] == 1);
if (d == -1) d = n;
assert(d > 0);
F res(this->differentiate());
res.divide_inplace(*this, d);
res.integrate_inplace();
return res;
}
// O(n log n)
// https://arxiv.org/abs/1301.5804 (Figure 2, right)
F exp(int d = -1) const {
int n = this->size();
assert(n > 0 && (*this)[0] == 0);
if (d == -1) d = n;
assert(d >= 0);
F f{1}, g{1};
F h_drv(this->differentiate());
for (int m = 1; m < d; m *= 2) {
// update g
if (m > 1) {
F _f(f), _g(g);
internal::butterfly(_f);
_g.resize(m), internal::butterfly(_g);
rep(i, m) _f[i] *= _g[i];
internal::butterfly_inv(_f);
_f.erase(_f.begin(), _f.begin() + m/2);
_f.resize(m), internal::butterfly(_f);
rep(i, m) _f[i] *= _g[i];
internal::butterfly_inv(_f);
T iz = T(m).inv(); iz *= -iz;
rep(i, m) _f[i] *= iz;
g.insert(g.end(), _f.begin(), _f.begin() + m/2);
}
F _f(f);
_f.resize(2*m), internal::butterfly(_f);
auto mult_f = [&] (F &_g) {
_g.resize(2*m); internal::butterfly(_g);
rep(i, 2*m) _g[i] *= _f[i];
internal::butterfly_inv(_g);
T iz = T(2*m).inv();
rep(i, 2*m) _g[i] *= iz;
};
// update t
F t(f.differentiate());
{
F r{h_drv.begin(), h_drv.begin() + min(n, m-1)};
mult_f(r);
rep(i, m) t[i] -= r[i] + r[i+m];
}
t.insert(t.begin(), t.back()); t.pop_back();
t.multiply_inplace(g);
// update v
F v(this->begin() + m, this->begin() + min(n, 2*m)); v.resize(m);
t.insert(t.begin(), m-1, 0); t.push_back(0);
t.integrate_inplace();
rep(i, m) v[i] -= t[m+i];
mult_f(v);
// update f
f.insert(f.end(), v.begin(), v.begin() + m);
}
return {f.begin(), f.begin() + d};
}
// O(n log n)
F &pow_inplace(ll k, int d = -1) {
int n = this->size();
if (d == -1) d = n;
assert(d >= 0);
int l = 0;
while ((*this)[l] == 0) ++l;
if (l > d/k) return *this = F(d);
T ic = (*this)[l].inv();
T pc = (*this)[l].pow(k);
this->erase(this->begin(), this->begin() + l);
*this *= ic;
*this = this->log();
*this *= k;
*this = this->exp();
*this *= pc;
this->insert(this->begin(), l*k, 0);
this->resize(d);
return *this;
}
F pow(const ll k, const int d = -1) const { return F(*this).pow_inplace(k, d); }
F operator*(const T &g) const { return F(*this) *= g; }
F operator/(const T &g) const { return F(*this) /= g; }
F operator+(const F &g) const { return F(*this) += g; }
F operator-(const F &g) const { return F(*this) -= g; }
F operator<<(const int d) const { return F(*this) <<= d; }
F operator>>(const int d) const { return F(*this) >>= d; }
F operator*(const F &g) const { return F(*this) *= g; }
F operator/(const F &g) const { return F(*this) /= g; }
F operator*(const vector<pair<int, T>> &g) const { return F(*this) *= g; }
F operator/(const vector<pair<int, T>> &g) const { return F(*this) /= g; }
};
using mint = modint998244353;
// using mint = modint1000000007;
using fps = FormalPowerSeries<mint>;
using sfps = vector<pair<int, mint>>;
template<typename T> struct Factorial {
int MAX;
vector<T> fac, finv;
Factorial(int m = 0) : MAX(m), fac(m+1, 1), finv(m+1, 1) {
rep2(i, 2, MAX+1) fac[i] = fac[i-1] * i;
finv[MAX] /= fac[MAX];
drep2(i, MAX+1, 3) finv[i-1] = finv[i] * i;
}
T binom(int n, int k) {
if (k < 0 || n < k) return 0;
return fac[n] * finv[k] * finv[n-k];
}
T perm(int n, int k) {
if (k < 0 || n < k) return 0;
return fac[n] * finv[n-k];
}
};
Factorial<mint> fc;
// sum_{l=k}^n k! S(l, k) binom(n, l) binom(m, k) m^(n-l)
int main() {
int n, m, k; cin >> n >> m >> k;
fc = Factorial<mint>(n);
fps f(fc.finv.begin() + 1, fc.finv.begin() + n-k+2);
f.pow_inplace(k);
// f[i] = k! S(k+i, k) / (k+i)!
// k! S(l, k) = l! f[l-k]
mint ans = 0;
mint z = 1;
drep2(l, n+1, k) {
ans += f[l-k] * fc.fac[l] * fc.binom(n, l) * z;
z *= m;
}
ans *= fc.binom(m, k);
cout << ans << '\n';
}
opt