#352718 (C++17) No.502 階乗を計算するだけ

提出ソース

結果

問題	No.502 階乗を計算するだけ
ユーザー	ei1333333
提出日時	2019-06-18 01:13:38
言語	C++17 (gcc 12.3.0 + boost 1.83.0)
結果	AC
実行時間	34 ms / 1,000 ms
コード長	10,782 bytes
コンパイル時間	2,952 ms
コンパイル使用メモリ	225,484 KB
実行使用メモリ	6,000 KB
最終ジャッジ日時	2024-11-29 16:54:28
合計ジャッジ時間	4,255 ms
ジャッジサーバーID （参考情報）	judge3 / judge5

このコードへのチャレンジ
（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 5,248 KB
testcase_01	AC	2 ms 5,248 KB
testcase_02	AC	1 ms 5,248 KB
testcase_03	AC	2 ms 5,248 KB
testcase_04	AC	2 ms 5,248 KB
testcase_05	AC	1 ms 5,248 KB
testcase_06	AC	2 ms 5,248 KB
testcase_07	AC	2 ms 5,248 KB
testcase_08	AC	2 ms 5,248 KB
testcase_09	AC	2 ms 5,248 KB
testcase_10	AC	2 ms 5,248 KB
testcase_11	AC	2 ms 5,248 KB
testcase_12	AC	2 ms 5,248 KB
testcase_13	AC	1 ms 5,248 KB
testcase_14	AC	1 ms 5,248 KB
testcase_15	AC	2 ms 5,248 KB
testcase_16	AC	2 ms 5,248 KB
testcase_17	AC	2 ms 5,248 KB
testcase_18	AC	1 ms 5,248 KB
testcase_19	AC	2 ms 5,248 KB
testcase_20	AC	2 ms 5,248 KB
testcase_21	AC	2 ms 5,248 KB
testcase_22	AC	2 ms 5,248 KB
testcase_23	AC	2 ms 5,248 KB
testcase_24	AC	2 ms 5,248 KB
testcase_25	AC	2 ms 5,248 KB
testcase_26	AC	3 ms 5,248 KB
testcase_27	AC	3 ms 5,248 KB
testcase_28	AC	2 ms 5,248 KB
testcase_29	AC	2 ms 5,248 KB
testcase_30	AC	3 ms 5,248 KB
testcase_31	AC	3 ms 5,248 KB
testcase_32	AC	29 ms 5,852 KB
testcase_33	AC	32 ms 5,916 KB
testcase_34	AC	28 ms 5,784 KB
testcase_35	AC	15 ms 5,248 KB
testcase_36	AC	30 ms 5,708 KB
testcase_37	AC	29 ms 5,648 KB
testcase_38	AC	31 ms 5,804 KB
testcase_39	AC	31 ms 5,880 KB
testcase_40	AC	15 ms 5,248 KB
testcase_41	AC	34 ms 6,000 KB
testcase_42	AC	2 ms 5,248 KB
testcase_43	AC	2 ms 5,248 KB
testcase_44	AC	2 ms 5,248 KB
testcase_45	AC	2 ms 5,248 KB
testcase_46	AC	2 ms 5,248 KB
testcase_47	AC	2 ms 5,248 KB
testcase_48	AC	2 ms 5,248 KB
testcase_49	AC	1 ms 5,248 KB
testcase_50	AC	2 ms 5,248 KB
testcase_51	AC	2 ms 5,248 KB

権限があれば一括ダウンロードができます

ソースコード

raw source code

#include<bits/stdc++.h>

using namespace std;
using int64 = long long;
const int mod = 1e9 + 7;

const int64 infll = (1LL << 62) - 1;
const int inf = (1 << 30) - 1;

struct IoSetup {
  IoSetup() {
    cin.tie(nullptr);
    ios::sync_with_stdio(false);
    cout << fixed << setprecision(10);
    cerr << fixed << setprecision(10);
  }
} iosetup;


template< typename T1, typename T2 >
ostream &operator<<(ostream &os, const pair< T1, T2 > &p) {
  os << p.first << " " << p.second;
  return os;
}

template< typename T1, typename T2 >
istream &operator>>(istream &is, pair< T1, T2 > &p) {
  is >> p.first >> p.second;
  return is;
}

template< typename T >
ostream &operator<<(ostream &os, const vector< T > &v) {
  for(int i = 0; i < (int) v.size(); i++) {
    os << v[i] << (i + 1 != v.size() ? " " : "");
  }
  return os;
}

template< typename T >
istream &operator>>(istream &is, vector< T > &v) {
  for(T &in : v) is >> in;
  return is;
}

template< typename T1, typename T2 >
inline bool chmax(T1 &a, T2 b) { return a < b && (a = b, true); }

template< typename T1, typename T2 >
inline bool chmin(T1 &a, T2 b) { return a > b && (a = b, true); }

template< typename T = int64 >
vector< T > make_v(size_t a) {
  return vector< T >(a);
}

template< typename T, typename... Ts >
auto make_v(size_t a, Ts... ts) {
  return vector< decltype(make_v< T >(ts...)) >(a, make_v< T >(ts...));
}

template< typename T, typename V >
typename enable_if< is_class< T >::value == 0 >::type fill_v(T &t, const V &v) {
  t = v;
}

template< typename T, typename V >
typename enable_if< is_class< T >::value != 0 >::type fill_v(T &t, const V &v) {
  for(auto &e : t) fill_v(e, v);
}

namespace FastFourierTransform {
  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;
        }
      }
    }
  }

  vector< int64_t > multiply(const vector< int > &a, const vector< int > &b) {
    int need = (int) a.size() + (int) b.size() - 1;
    int nbase = 1;
    while((1 << nbase) < need) nbase++;
    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);
    }
    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 * rts[(sz >> 1) + i];
      fa[i] = A0 + A1 * s;
    }
    fft(fa, sz >> 1);
    vector< int64_t > ret(need);
    for(int i = 0; i < need; i++) {
      ret[i] = llround(i & 1 ? fa[i >> 1].y : fa[i >> 1].x);
    }
    return ret;
  }


};

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); }

  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 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;
  }

  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 int get_mod() { return mod; }
};

using modint = ModInt< mod >;


template< typename T >
struct ArbitraryModConvolution {
  using real = FastFourierTransform::real;
  using C = FastFourierTransform::C;

  ArbitraryModConvolution() = default;

  vector< T > multiply(const vector< T > &a, const vector< T > &b, int need = -1) {
    if(need == -1) need = a.size() + b.size() - 1;
    int nbase = 0;
    while((1 << nbase) < need) nbase++;
    FastFourierTransform::ensure_base(nbase);
    int sz = 1 << nbase;
    vector< C > fa(sz);
    for(int i = 0; i < a.size(); i++) {
      fa[i] = C(a[i].x & ((1 << 15) - 1), a[i].x >> 15);
    }
    fft(fa, sz);
    vector< C > fb(sz);
    for(int i = 0; i < b.size(); i++) {
      fb[i] = C(b[i].x & ((1 << 15) - 1), b[i].x >> 15);
    }
    fft(fb, sz);
    real ratio = 0.25 / sz;
    C r2(0, -1), r3(ratio, 0), r4(0, -ratio), r5(0, 1);
    for(int i = 0; i <= (sz >> 1); i++) {
      int j = (sz - i) & (sz - 1);
      C a1 = (fa[i] + fa[j].conj());
      C a2 = (fa[i] - fa[j].conj()) * r2;
      C b1 = (fb[i] + fb[j].conj()) * r3;
      C b2 = (fb[i] - fb[j].conj()) * r4;
      if(i != j) {
        C c1 = (fa[j] + fa[i].conj());
        C c2 = (fa[j] - fa[i].conj()) * r2;
        C d1 = (fb[j] + fb[i].conj()) * r3;
        C d2 = (fb[j] - fb[i].conj()) * r4;
        fa[i] = c1 * d1 + c2 * d2 * r5;
        fb[i] = c1 * d2 + c2 * d1;
      }
      fa[j] = a1 * b1 + a2 * b2 * r5;
      fb[j] = a1 * b2 + a2 * b1;
    }
    fft(fa, sz);
    fft(fb, sz);
    vector< T > ret(need);
    for(int i = 0; i < need; i++) {
      int64_t aa = llround(fa[i].x);
      int64_t bb = llround(fb[i].x);
      int64_t cc = llround(fa[i].y);
      aa = T(aa).x, bb = T(bb).x, cc = T(cc).x;
      ret[i] = aa + (bb << 15) + (cc << 30);
    }
    return ret;
  }
};

template< typename T >
struct Combination {
  vector< T > _fact, _rfact, _inv;

  Combination(int sz) : _fact(sz + 1), _rfact(sz + 1), _inv(sz + 1) {
    _fact[0] = _rfact[sz] = _inv[0] = 1;
    for(int i = 1; i <= sz; i++) _fact[i] = _fact[i - 1] * i;
    _rfact[sz] /= _fact[sz];
    for(int i = sz - 1; i >= 0; i--) _rfact[i] = _rfact[i + 1] * (i + 1);
    for(int i = 1; i <= sz; i++) _inv[i] = _rfact[i] * _fact[i - 1];
  }

  inline T fact(int k) const { return _fact[k]; }

  inline T rfact(int k) const { return _rfact[k]; }

  inline T inv(int k) const { return _inv[k]; }

  T P(int n, int r) const {
    if(r < 0 || n < r) return 0;
    return fact(n) * rfact(n - r);
  }

  T C(int p, int q) const {
    if(q < 0 || p < q) return 0;
    return fact(p) * rfact(q) * rfact(p - q);
  }

  T H(int n, int r) const {
    if(n < 0 || r < 0) return (0);
    return r == 0 ? 1 : C(n + r - 1, r);
  }
};

template< typename T >
T factorial(int64_t n) {
  if(n >= T::get_mod()) return 0;
  if(n == 0) return 1;

  const int sn = sqrt(n);
  const T sn_inv = T(1) / sn;

  Combination< modint > comb(sn);
  using P = vector< T >;
  ArbitraryModConvolution< modint > fft;

  auto shift = [&](const P &f, T dx) {
    int n = (int) f.size();
    T a = dx * sn_inv;
    auto p1 = P(f);
    for(int i = 0; i < n; i++) {
      T d = comb.rfact(i) * comb.rfact((n - 1) - i);
      if(((n - 1 - i) & 1)) d = -d;
      p1[i] *= d;
    }
    auto p2 = P(2 * n);
    for(int i = 0; i < p2.size(); i++) {
      p2[i] = (a.x + i - n) <= 0 ? 1 : a + i - n;
    }
    for(int i = 1; i < p2.size(); i++) {
      p2[i] *= p2[i - 1];
    }
    T prod = p2[2 * n - 1];
    T prod_inv = T(1) / prod;
    for(int i = 2 * n - 1; i > 0; --i) {
      p2[i] = prod_inv * p2[i - 1];
      prod_inv *= a + i - n;
    }
    p2[0] = prod_inv;
    auto p3 = fft.multiply(p1, p2, (int) p2.size());
    p1 = P(p3.begin() + p1.size(), p3.begin() + p2.size());
    prod = 1;
    for(int i = 0; i < n; i++) {
      prod *= a + n - 1 - i;
    }
    for(int i = n - 1; i >= 0; --i) {
      p1[i] *= prod;
      prod *= p2[n + i] * (a + i - n);
    }
    return p1;
  };
  function< P(int) > rec = [&](int64_t n) {
    if(n == 1) return P({1, 1 + sn});
    int nh = n >> 1;
    auto a1 = rec(nh);
    auto a2 = shift(a1, nh);
    auto b1 = shift(a1, sn * nh);
    auto b2 = shift(a1, sn * nh + nh);
    for(int i = 0; i <= nh; i++) a1[i] *= a2[i];
    for(int i = 1; i <= nh; i++) a1.emplace_back(b1[i] * b2[i]);
    if(n & 1) {
      for(int64_t i = 0; i < n; i++) {
        a1[i] *= n + 1LL * sn * i;
      }
      T prod = 1;
      for(int64_t i = 1LL * n * sn; i < 1LL * n * sn + n; i++) {
        prod *= (i + 1);
      }
      a1.push_back(prod);
    }
    return a1;
  };
  auto vs = rec(sn);
  T ret = 1;
  for(int64_t i = 0; i < sn; i++) ret *= vs[i];
  for(int64_t i = 1LL * sn * sn + 1; i <= n; i++) ret *= i;
  return ret;
}


int main() {
  int64 X;
  cin >> X;
  cout << factorial< modint >(X) << endl;
}

yukicoder

結果

テストケース

ソースコード