#931883 (C++23) No.2473 Fraises dans une boîte

提出ソース

結果

問題	No.2473 Fraises dans une boîte
ユーザー	maspy
提出日時	2023-11-26 16:18:29
言語	C++23 (gcc 12.3.0 + boost 1.83.0)
結果	AC
実行時間	3,597 ms / 4,000 ms
コード長	16,542 bytes
コンパイル時間	6,439 ms
コンパイル使用メモリ	323,604 KB
実行使用メモリ	5,632 KB
最終ジャッジ日時	2024-09-26 11:49:20
合計ジャッジ時間	61,067 ms
ジャッジサーバーID （参考情報）	judge4 / 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 5,376 KB
testcase_02	AC	2 ms 5,376 KB
testcase_03	AC	2 ms 5,376 KB
testcase_04	AC	2 ms 5,376 KB
testcase_05	AC	2 ms 5,376 KB
testcase_06	AC	2 ms 5,376 KB
testcase_07	AC	2 ms 5,376 KB
testcase_08	AC	3 ms 5,376 KB
testcase_09	AC	2 ms 5,376 KB
testcase_10	AC	2 ms 5,376 KB
testcase_11	AC	2 ms 5,376 KB
testcase_12	AC	2 ms 5,376 KB
testcase_13	AC	1 ms 5,376 KB
testcase_14	AC	3 ms 5,376 KB
testcase_15	AC	2 ms 5,376 KB
testcase_16	AC	2 ms 5,376 KB
testcase_17	AC	1 ms 5,376 KB
testcase_18	AC	2 ms 5,376 KB
testcase_19	AC	3 ms 5,376 KB
testcase_20	AC	2 ms 5,376 KB
testcase_21	AC	2 ms 5,376 KB
testcase_22	AC	2 ms 5,376 KB
testcase_23	AC	2 ms 5,376 KB
testcase_24	AC	2 ms 5,376 KB
testcase_25	AC	2 ms 5,376 KB
testcase_26	AC	2 ms 5,376 KB
testcase_27	AC	2 ms 5,376 KB
testcase_28	AC	2 ms 5,376 KB
testcase_29	AC	2 ms 5,376 KB
testcase_30	AC	2 ms 5,376 KB
testcase_31	AC	2 ms 5,376 KB
testcase_32	AC	2 ms 5,376 KB
testcase_33	AC	2 ms 5,376 KB
testcase_34	AC	2 ms 5,376 KB
testcase_35	AC	2 ms 5,376 KB
testcase_36	AC	2 ms 5,376 KB
testcase_37	AC	2 ms 5,376 KB
testcase_38	AC	2 ms 5,376 KB
testcase_39	AC	2 ms 5,376 KB
testcase_40	AC	29 ms 5,376 KB
testcase_41	AC	41 ms 5,376 KB
testcase_42	AC	4 ms 5,376 KB
testcase_43	AC	671 ms 5,376 KB
testcase_44	AC	659 ms 5,376 KB
testcase_45	AC	169 ms 5,376 KB
testcase_46	AC	1,569 ms 5,376 KB
testcase_47	AC	926 ms 5,376 KB
testcase_48	AC	1,089 ms 5,376 KB
testcase_49	AC	1,986 ms 5,632 KB
testcase_50	AC	1,801 ms 5,632 KB
testcase_51	AC	2,760 ms 5,504 KB
testcase_52	AC	2,715 ms 5,504 KB
testcase_53	AC	1,840 ms 5,632 KB
testcase_54	AC	3,339 ms 5,504 KB
testcase_55	AC	2,028 ms 5,632 KB
testcase_56	AC	2,175 ms 5,504 KB
testcase_57	AC	3,355 ms 5,504 KB
testcase_58	AC	1,948 ms 5,504 KB
testcase_59	AC	1,710 ms 5,504 KB
testcase_60	AC	2,551 ms 5,632 KB
testcase_61	AC	3,510 ms 5,504 KB
testcase_62	AC	3,597 ms 5,632 KB
testcase_63	AC	2,801 ms 5,632 KB
testcase_64	AC	2,354 ms 5,504 KB
testcase_65	AC	2,824 ms 5,504 KB
testcase_66	AC	2,058 ms 5,632 KB
testcase_67	AC	4 ms 5,376 KB
testcase_68	AC	1,569 ms 5,504 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

#line 1 "/home/maspy/compro/library/my_template.hpp"
#if defined(LOCAL)
#include <my_template_compiled.hpp>
#else
#pragma GCC optimize("Ofast")
#pragma GCC optimize("unroll-loops")

#include <bits/stdc++.h>

using namespace std;

using ll = long long;
using u32 = unsigned int;
using u64 = unsigned long long;
using i128 = __int128;
using u128 = unsigned __int128;
using f128 = __float128;

template <class T>
constexpr T infty = 0;
template <>
constexpr int infty<int> = 1'000'000'000;
template <>
constexpr ll infty<ll> = ll(infty<int>) * infty<int> * 2;
template <>
constexpr u32 infty<u32> = infty<int>;
template <>
constexpr u64 infty<u64> = infty<ll>;
template <>
constexpr i128 infty<i128> = i128(infty<ll>) * infty<ll>;
template <>
constexpr double infty<double> = infty<ll>;
template <>
constexpr long double infty<long double> = infty<ll>;

using pi = pair<ll, ll>;
using vi = vector<ll>;
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 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 overload4(a, b, c, d, e, ...) e
#define overload3(a, b, c, d, ...) d
#define FOR(...) overload4(__VA_ARGS__, FOR4, FOR3, FOR2, FOR1)(__VA_ARGS__)
#define FOR_R(...) overload3(__VA_ARGS__, 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

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); }
int popcnt_mod_2(int x) { return __builtin_parity(x); }
int popcnt_mod_2(u32 x) { return __builtin_parity(x); }
int popcnt_mod_2(ll x) { return __builtin_parityll(x); }
int popcnt_mod_2(u64 x) { return __builtin_parityll(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 floor(T a, T b) {
  return a / b - (a % b && (a ^ b) < 0);
}
template <typename T>
T ceil(T x, T y) {
  return floor(x + y - 1, y);
}
template <typename T>
T bmod(T x, T y) {
  return x - y * floor(x, y);
}
template <typename T>
pair<T, T> divmod(T x, T y) {
  T q = floor(x, y);
  return {q, x - q * y};
}

template <typename T, typename U>
T SUM(const vector<U> &A) {
  T sm = 0;
  for (auto &&a: A) sm += a;
  return sm;
}

#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()), x.shrink_to_fit()

template <typename T>
T POP(deque<T> &que) {
  T a = que.front();
  que.pop_front();
  return a;
}
template <typename T>
T POP(pq<T> &que) {
  T a = que.top();
  que.pop();
  return a;
}
template <typename T>
T POP(pqg<T> &que) {
  T a = que.top();
  que.pop();
  return a;
}
template <typename T>
T POP(vc<T> &que) {
  T a = que.back();
  que.pop_back();
  return a;
}

template <typename F>
ll binary_search(F check, ll ok, ll ng, bool check_ok = true) {
  if (check_ok) assert(check(ok));
  while (abs(ok - ng) > 1) {
    auto x = (ng + ok) / 2;
    (check(x) ? ok : ng) = 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;
    (check(x) ? ok : ng) = 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);
}

// ? は -1
vc<int> s_to_vi(const string &S, char first_char) {
  vc<int> A(S.size());
  FOR(i, S.size()) { A[i] = (S[i] != '?' ? S[i] - first_char : -1); }
  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;
}

// stable sort
template <typename T>
vector<int> argsort(const vector<T> &A) {
  vector<int> ids(len(A));
  iota(all(ids), 0);
  sort(all(ids),
       [&](int i, int j) { return (A[i] == A[j] ? i < j : A[i] < A[j]); });
  return ids;
}

// A[I[0]], A[I[1]], ...
template <typename T>
vc<T> rearrange(const vc<T> &A, const vc<int> &I) {
  vc<T> B(len(I));
  FOR(i, len(I)) B[i] = A[I[i]];
  return B;
}
#endif
#line 1 "/home/maspy/compro/library/other/io.hpp"
#define FASTIO
#include <unistd.h>

// https://judge.yosupo.jp/submission/21623
namespace fastio {
static constexpr uint32_t SZ = 1 << 17;
char ibuf[SZ];
char obuf[SZ];
char out[100];
// pointer of ibuf, obuf
uint32_t pil = 0, pir = 0, por = 0;

struct Pre {
  char num[10000][4];
  constexpr Pre() : num() {
    for (int i = 0; i < 10000; i++) {
      int n = i;
      for (int j = 3; j >= 0; j--) {
        num[i][j] = n % 10 | '0';
        n /= 10;
      }
    }
  }
} constexpr pre;

inline void load() {
  memcpy(ibuf, ibuf + pil, pir - pil);
  pir = pir - pil + fread(ibuf + pir - pil, 1, SZ - pir + pil, stdin);
  pil = 0;
  if (pir < SZ) ibuf[pir++] = '\n';
}

inline void flush() {
  fwrite(obuf, 1, por, stdout);
  por = 0;
}

void rd(char &c) {
  do {
    if (pil + 1 > pir) load();
    c = ibuf[pil++];
  } while (isspace(c));
}

void rd(string &x) {
  x.clear();
  char c;
  do {
    if (pil + 1 > pir) load();
    c = ibuf[pil++];
  } while (isspace(c));
  do {
    x += c;
    if (pil == pir) load();
    c = ibuf[pil++];
  } while (!isspace(c));
}

template <typename T>
void rd_real(T &x) {
  string s;
  rd(s);
  x = stod(s);
}

template <typename T>
void rd_integer(T &x) {
  if (pil + 100 > pir) load();
  char c;
  do
    c = ibuf[pil++];
  while (c < '-');
  bool minus = 0;
  if constexpr (is_signed<T>::value || is_same_v<T, i128>) {
    if (c == '-') { minus = 1, c = ibuf[pil++]; }
  }
  x = 0;
  while ('0' <= c) { x = x * 10 + (c & 15), c = ibuf[pil++]; }
  if constexpr (is_signed<T>::value || is_same_v<T, i128>) {
    if (minus) x = -x;
  }
}

void rd(int &x) { rd_integer(x); }
void rd(ll &x) { rd_integer(x); }
void rd(i128 &x) { rd_integer(x); }
void rd(u32 &x) { rd_integer(x); }
void rd(u64 &x) { rd_integer(x); }
void rd(u128 &x) { rd_integer(x); }
void rd(double &x) { rd_real(x); }
void rd(long double &x) { rd_real(x); }
void rd(f128 &x) { rd_real(x); }

template <class T, class U>
void rd(pair<T, U> &p) {
  return rd(p.first), rd(p.second);
}
template <size_t N = 0, typename T>
void rd_tuple(T &t) {
  if constexpr (N < std::tuple_size<T>::value) {
    auto &x = std::get<N>(t);
    rd(x);
    rd_tuple<N + 1>(t);
  }
}
template <class... T>
void rd(tuple<T...> &tpl) {
  rd_tuple(tpl);
}

template <size_t N = 0, typename T>
void rd(array<T, N> &x) {
  for (auto &d: x) rd(d);
}
template <class T>
void rd(vc<T> &x) {
  for (auto &d: x) rd(d);
}

void read() {}
template <class H, class... T>
void read(H &h, T &... t) {
  rd(h), read(t...);
}

void wt(const char c) {
  if (por == SZ) flush();
  obuf[por++] = c;
}
void wt(const string s) {
  for (char c: s) wt(c);
}
void wt(const char *s) {
  size_t len = strlen(s);
  for (size_t i = 0; i < len; i++) wt(s[i]);
}

template <typename T>
void wt_integer(T x) {
  if (por > SZ - 100) flush();
  if (x < 0) { obuf[por++] = '-', x = -x; }
  int outi;
  for (outi = 96; x >= 10000; outi -= 4) {
    memcpy(out + outi, pre.num[x % 10000], 4);
    x /= 10000;
  }
  if (x >= 1000) {
    memcpy(obuf + por, pre.num[x], 4);
    por += 4;
  } else if (x >= 100) {
    memcpy(obuf + por, pre.num[x] + 1, 3);
    por += 3;
  } else if (x >= 10) {
    int q = (x * 103) >> 10;
    obuf[por] = q | '0';
    obuf[por + 1] = (x - q * 10) | '0';
    por += 2;
  } else
    obuf[por++] = x | '0';
  memcpy(obuf + por, out + outi + 4, 96 - outi);
  por += 96 - outi;
}

template <typename T>
void wt_real(T x) {
  ostringstream oss;
  oss << fixed << setprecision(15) << double(x);
  string s = oss.str();
  wt(s);
}

void wt(int x) { wt_integer(x); }
void wt(ll x) { wt_integer(x); }
void wt(i128 x) { wt_integer(x); }
void wt(u32 x) { wt_integer(x); }
void wt(u64 x) { wt_integer(x); }
void wt(u128 x) { wt_integer(x); }
void wt(double x) { wt_real(x); }
void wt(long double x) { wt_real(x); }
void wt(f128 x) { wt_real(x); }

template <class T, class U>
void wt(const pair<T, U> val) {
  wt(val.first);
  wt(' ');
  wt(val.second);
}
template <size_t N = 0, typename T>
void wt_tuple(const T t) {
  if constexpr (N < std::tuple_size<T>::value) {
    if constexpr (N > 0) { wt(' '); }
    const auto x = std::get<N>(t);
    wt(x);
    wt_tuple<N + 1>(t);
  }
}
template <class... T>
void wt(tuple<T...> tpl) {
  wt_tuple(tpl);
}
template <class T, size_t S>
void wt(const array<T, S> val) {
  auto n = val.size();
  for (size_t i = 0; i < n; i++) {
    if (i) wt(' ');
    wt(val[i]);
  }
}
template <class T>
void wt(const vector<T> val) {
  auto n = val.size();
  for (size_t i = 0; i < n; i++) {
    if (i) wt(' ');
    wt(val[i]);
  }
}

void print() { wt('\n'); }
template <class Head, class... Tail>
void print(Head &&head, Tail &&... tail) {
  wt(head);
  if (sizeof...(Tail)) wt(' ');
  print(forward<Tail>(tail)...);
}

// gcc expansion. called automaticall after main.
void __attribute__((destructor)) _d() { flush(); }
} // namespace fastio
using fastio::read;
using fastio::print;
using fastio::flush;

#define INT(...)   \
  int __VA_ARGS__; \
  read(__VA_ARGS__)
#define LL(...)   \
  ll __VA_ARGS__; \
  read(__VA_ARGS__)
#define U32(...)   \
  u32 __VA_ARGS__; \
  read(__VA_ARGS__)
#define U64(...)   \
  u64 __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 3 "main.cpp"

#line 2 "/home/maspy/compro/library/ds/cumsum_2d.hpp"

#line 2 "/home/maspy/compro/library/alg/monoid/add.hpp"

template <typename X>
struct Monoid_Add {
  using value_type = X;
  static constexpr X op(const X &x, const X &y) noexcept { return x + y; }
  static constexpr X inverse(const X &x) noexcept { return -x; }
  static constexpr X power(const X &x, ll n) noexcept { return X(n) * x; }
  static constexpr X unit() { return X(0); }
  static constexpr bool commute = true;
};
#line 4 "/home/maspy/compro/library/ds/cumsum_2d.hpp"

template <typename Monoid>
struct Cumsum_2D {
  using MX = Monoid;
  static_assert(MX::commute);
  using X = typename MX::value_type;
  int H, W;
  vc<X> dat;

  Cumsum_2D() {}
  Cumsum_2D(vvc<X> &A) { build(A); }

  void build(vvc<X> &A) {
    H = len(A);
    W = (H == 0 ? 0 : len(A[0]));
    dat.assign(H * W, MX::unit());
    FOR(x, H) FOR(y, W) {
      int k = W * x + y;
      dat[k] = (y == 0 ? A[x][y] : MX::op(dat[k - 1], A[x][y]));
    }
    FOR(i, W, H * W) dat[i] = MX::op(dat[i - W], dat[i]);
  }

  // [x1,x2) x [y1,y2)
  X sum(int x1, int x2, int y1, int y2) {
    if (x2 == 0 || y2 == 0) return MX::unit();
    assert(0 <= x1 && x1 <= x2 && x2 <= H);
    assert(0 <= y1 && y1 <= y2 && y2 <= W);
    --x1, --y1, --x2, --y2;
    X a = (x1 >= 0 && y1 >= 0 ? dat[W * x1 + y1] : MX::unit());
    X b = (x1 >= 0 && y2 >= 0 ? dat[W * x1 + y2] : MX::unit());
    X c = (x2 >= 0 && y1 >= 0 ? dat[W * x2 + y1] : MX::unit());
    X d = (x2 >= 0 && y2 >= 0 ? dat[W * x2 + y2] : MX::unit());
    return MX::op(MX::op(a, d), MX::inverse(MX::op(b, c)));
  }

  X prefix_sum(int x, int y) {
    return (x == 0 || y == 0) ? MX::unit() : dat[W * x + y - (W + 1)];
  }
};
#line 5 "main.cpp"

void test(int H, int W) {
  vv(int, A, H, W); // 盤面
  vv(int, appear, H, W);

  auto shrink = [&](vvc<int> A) -> vvc<int> {
    if (A.empty()) return A;
    int H = len(A), W = len(A[0]);
    vc<int> X(H), Y(W);
    FOR(x, H) FOR(y, W) X[x] += A[x][y], Y[y] += A[x][y];
    vc<int> I, J;
    FOR(i, H) if (X[i]) I.eb(i);
    FOR(j, W) if (Y[j]) J.eb(j);
    A = rearrange(A, I);
    FOR(i, len(A)) A[i] = rearrange(A[i], J);
    return A;
  };

  auto check = [&](vvc<int> A) -> bool {
    auto dfs = [&](auto& dfs, vvc<int> A) -> bool {
      A = shrink(A);
      if (A.empty()) return true;
      int H = len(A), W = len(A[0]);
      Cumsum_2D<Monoid_Add<int>> X(A);
      FOR(a, 1, H + 1) FOR(b, 1, W + 1) {
        if (X.sum(0, a, 0, b) != a * b) continue;
        if (X.sum(a, H, b, W) != 0) continue;
        vv(int, B, H - a, b);
        vv(int, C, a, W - b);
        FOR(x, H - a) FOR(y, b) B[x][y] = A[a + x][y];
        FOR(x, a) FOR(y, W - b) C[x][y] = A[x][b + y];
        return dfs(dfs, B) && dfs(dfs, C);
      }
      return 0;
    };
    return dfs(dfs, A);
  };

  auto dfs = [&](auto& dfs, int p) -> void {
    if (p == H * W) {
      if (!check(A)) {
        A = shrink(A);
        FOR(i, H) print(A[i]);
        print();
      }
      return;
    }
    dfs(dfs, p + 1);
    auto [x, y] = divmod(p, W);
    int a = 0, b = 0;
    FOR(i, x) a += A[i][y];
    FOR(j, y) b += A[x][j];
    if (appear[a][b]) return;
    A[x][y] = 1, appear[a][b] = 1;
    dfs(dfs, p + 1);
    A[x][y] = 0, appear[a][b] = 0;
  };
  dfs(dfs, 0);
}

void solve() {
  INT(H, W);
  VV(int, S, H, W);
  vv(int, R, H + 1, W + 1);
  vv(int, D, H + 1, W + 1);
  FOR_R(x, H) FOR_R(y, W) {
    D[x][y] = S[x][y] + D[x + 1][y];
    R[x][y] = S[x][y] + R[x][y + 1];
  }
  vvc<int> RD = R;
  FOR_R(x, H) FOR_R(y, W) {
    if (x + 1 < H) RD[x][y] += RD[x + 1][y];
  }

  // FOR(x, H + 1) print(RD[x]);
  // print();

  vv(int, dp, H + 1, W + 1, infty<int>);
  FOR_R(x, H + 1) {
    FOR_R(y, W + 1) {
      if (RD[x][y] == 0) {
        dp[x][y] = 0;
        continue;
      }
      // 1 がある行 / 列か
      vc<int> X(H - x), Y(W - y);
      FOR(i, H - x) X[i] = (R[x + i][y] > 0);
      FOR(j, W - y) Y[j] = (D[x][y + j] > 0);
      X = cumsum<int>(X);
      Y = cumsum<int>(Y);
      FOR(a, 1, H - x + 1) {
        FOR(b, 1, W - y + 1) {
          if (RD[x + a][y + b] > 0) continue;
          int cost = 0;
          int now = RD[x][y] - RD[x + a][y] - RD[x][y + b];
          cost += X[a] * Y[b] - now;
          cost += dp[x + a][y] + dp[x][y + b];
          chmin(dp[x][y], cost);
        }
      }
    }
  }

  // FOR(x, H) print(dp[x]);
  print(dp[0][0]);
}

signed main() {
  int T = 1;
  // INT(T);
  FOR(T) solve();
  return 0;
}

yukicoder

結果

テストケース

ソースコード