結果
| 問題 |
No.3131 Twin Slide Puzzles
|
| コンテスト | |
| ユーザー |
 maspy
|
| 提出日時 | 2025-04-25 22:03:16 |
| 言語 | C++23 (gcc 13.3.0 + boost 1.87.0) |
| 結果 |
RE
|
| 実行時間 | - |
| コード長 | 28,503 bytes |
| コンパイル時間 | 8,253 ms |
| コンパイル使用メモリ | 366,140 KB |
| 実行使用メモリ | 665,624 KB |
| 最終ジャッジ日時 | 2025-04-25 22:04:12 |
| 合計ジャッジ時間 | 42,338 ms |
|
ジャッジサーバーID （参考情報） |
judge2 / judge4 |
（要ログイン）
| ファイルパターン | 結果 |
|---|---|
| sample | AC * 3 |
| other | AC * 54 RE * 2 MLE * 1 |
ソースコード
#line 1 "/home/maspy/compro/library/my_template.hpp"
#if defined(LOCAL)
#include <my_template_compiled.hpp>
#else
// https://codeforces.com/blog/entry/96344
// https://codeforces.com/blog/entry/126772?#comment-1154880
#include <bits/allocator.h>
#pragma GCC optimize("Ofast,unroll-loops")
#pragma GCC target("avx2,popcnt")
#include <bits/stdc++.h>
using namespace std;
using ll = long long;
using u8 = uint8_t;
using u16 = uint16_t;
using u32 = uint32_t;
using u64 = uint64_t;
using i128 = __int128;
using u128 = unsigned __int128;
using f128 = __float128;
template <class T>
constexpr T infty = 0;
template <>
constexpr int infty<int> = 1'010'000'000;
template <>
constexpr ll infty<ll> = 2'020'000'000'000'000'000;
template <>
constexpr u32 infty<u32> = infty<int>;
template <>
constexpr u64 infty<u64> = infty<ll>;
template <>
constexpr i128 infty<i128> = i128(infty<ll>) * 2'000'000'000'000'000'000;
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 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_sgn(int x) { return (__builtin_parity(unsigned(x)) & 1 ? -1 : 1); }
int popcnt_sgn(u32 x) { return (__builtin_parity(x) & 1 ? -1 : 1); }
int popcnt_sgn(ll x) { return (__builtin_parityll(x) & 1 ? -1 : 1); }
int popcnt_sgn(u64 x) { return (__builtin_parityll(x) & 1 ? -1 : 1); }
// (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 kth_bit(int k) {
return T(1) << k;
}
template <typename T>
bool has_kth_bit(T x, int k) {
return x >> k & 1;
}
template <typename UINT>
struct all_bit {
struct iter {
UINT s;
iter(UINT s) : s(s) {}
int operator*() const { return lowbit(s); }
iter &operator++() {
s &= s - 1;
return *this;
}
bool operator!=(const iter) const { return s != 0; }
};
UINT s;
all_bit(UINT s) : s(s) {}
iter begin() const { return iter(s); }
iter end() const { return iter(0); }
};
template <typename UINT>
struct all_subset {
static_assert(is_unsigned<UINT>::value);
struct iter {
UINT s, t;
bool ed;
iter(UINT s) : s(s), t(s), ed(0) {}
int operator*() const { return s ^ t; }
iter &operator++() {
(t == 0 ? ed = 1 : t = (t - 1) & s);
return *this;
}
bool operator!=(const iter) const { return !ed; }
};
UINT s;
all_subset(UINT s) : s(s) {}
iter begin() const { return iter(s); }
iter end() const { return iter(0); }
};
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;
}
template <typename T, typename... Vectors>
void concat(vc<T> &first, const Vectors &... others) {
vc<T> &res = first;
(res.insert(res.end(), others.begin(), others.end()), ...);
}
#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;
#if defined(LOCAL)
#define SHOW(...) SHOW_IMPL(__VA_ARGS__, SHOW6, SHOW5, SHOW4, SHOW3, SHOW2, SHOW1)(__VA_ARGS__)
#define SHOW_IMPL(_1, _2, _3, _4, _5, _6, NAME, ...) NAME
#define SHOW1(x) print(#x, "=", (x)), flush()
#define SHOW2(x, y) print(#x, "=", (x), #y, "=", (y)), flush()
#define SHOW3(x, y, z) print(#x, "=", (x), #y, "=", (y), #z, "=", (z)), flush()
#define SHOW4(x, y, z, w) print(#x, "=", (x), #y, "=", (y), #z, "=", (z), #w, "=", (w)), flush()
#define SHOW5(x, y, z, w, v) print(#x, "=", (x), #y, "=", (y), #z, "=", (z), #w, "=", (w), #v, "=", (v)), flush()
#define SHOW6(x, y, z, w, v, u) print(#x, "=", (x), #y, "=", (y), #z, "=", (z), #w, "=", (w), #v, "=", (v), #u, "=", (u)), flush()
#else
#define SHOW(...)
#endif
#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); }
void YA(bool t = 1) { print(t ? "YA" : "TIDAK"); }
void TIDAK(bool t = 1) { YA(!t); }
#line 3 "main.cpp"
#line 2 "/home/maspy/compro/library/ds/fenwicktree/fenwicktree_01.hpp"
#line 2 "/home/maspy/compro/library/alg/monoid/add.hpp"
template <typename E>
struct Monoid_Add {
using X = E;
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 3 "/home/maspy/compro/library/ds/fenwicktree/fenwicktree.hpp"
template <typename Monoid>
struct FenwickTree {
using G = Monoid;
using MX = Monoid;
using E = typename G::value_type;
int n;
vector<E> dat;
E total;
FenwickTree() {}
FenwickTree(int n) { build(n); }
template <typename F>
FenwickTree(int n, F f) {
build(n, f);
}
FenwickTree(const vc<E>& v) { build(v); }
void build(int m) {
n = m;
dat.assign(m, G::unit());
total = G::unit();
}
void build(const vc<E>& v) {
build(len(v), [&](int i) -> E { return v[i]; });
}
template <typename F>
void build(int m, F f) {
n = m;
dat.clear();
dat.reserve(n);
total = G::unit();
FOR(i, n) { dat.eb(f(i)); }
for (int i = 1; i <= n; ++i) {
int j = i + (i & -i);
if (j <= n) dat[j - 1] = G::op(dat[i - 1], dat[j - 1]);
}
total = prefix_sum(m);
}
E prod_all() { return total; }
E sum_all() { return total; }
E sum(int k) { return prefix_sum(k); }
E prod(int k) { return prefix_prod(k); }
E prefix_sum(int k) { return prefix_prod(k); }
E prefix_prod(int k) {
chmin(k, n);
E ret = G::unit();
for (; k > 0; k -= k & -k) ret = G::op(ret, dat[k - 1]);
return ret;
}
E sum(int L, int R) { return prod(L, R); }
E prod(int L, int R) {
chmax(L, 0), chmin(R, n);
if (L == 0) return prefix_prod(R);
assert(0 <= L && L <= R && R <= n);
E pos = G::unit(), neg = G::unit();
while (L < R) { pos = G::op(pos, dat[R - 1]), R -= R & -R; }
while (R < L) { neg = G::op(neg, dat[L - 1]), L -= L & -L; }
return G::op(pos, G::inverse(neg));
}
vc<E> get_all() {
vc<E> res(n);
FOR(i, n) res[i] = prod(i, i + 1);
return res;
}
void add(int k, E x) { multiply(k, x); }
void multiply(int k, E x) {
static_assert(G::commute);
total = G::op(total, x);
for (++k; k <= n; k += k & -k) dat[k - 1] = G::op(dat[k - 1], x);
}
void set(int k, E x) { add(k, G::op(G::inverse(prod(k, k + 1)), x)); }
template <class F>
int max_right(const F check, int L = 0) {
assert(check(G::unit()));
E s = G::unit();
int i = L;
// 2^k 進むとダメ
int k = [&]() {
while (1) {
if (i % 2 == 1) { s = G::op(s, G::inverse(dat[i - 1])), i -= 1; }
if (i == 0) { return topbit(n) + 1; }
int k = lowbit(i) - 1;
if (i + (1 << k) > n) return k;
E t = G::op(s, dat[i + (1 << k) - 1]);
if (!check(t)) { return k; }
s = G::op(s, G::inverse(dat[i - 1])), i -= i & -i;
}
}();
while (k) {
--k;
if (i + (1 << k) - 1 < len(dat)) {
E t = G::op(s, dat[i + (1 << k) - 1]);
if (check(t)) { i += (1 << k), s = t; }
}
}
return i;
}
// check(i, x)
template <class F>
int max_right_with_index(const F check, int L = 0) {
assert(check(L, G::unit()));
E s = G::unit();
int i = L;
// 2^k 進むとダメ
int k = [&]() {
while (1) {
if (i % 2 == 1) { s = G::op(s, G::inverse(dat[i - 1])), i -= 1; }
if (i == 0) { return topbit(n) + 1; }
int k = lowbit(i) - 1;
if (i + (1 << k) > n) return k;
E t = G::op(s, dat[i + (1 << k) - 1]);
if (!check(i + (1 << k), t)) { return k; }
s = G::op(s, G::inverse(dat[i - 1])), i -= i & -i;
}
}();
while (k) {
--k;
if (i + (1 << k) - 1 < len(dat)) {
E t = G::op(s, dat[i + (1 << k) - 1]);
if (check(i + (1 << k), t)) { i += (1 << k), s = t; }
}
}
return i;
}
template <class F>
int min_left(const F check, int R) {
assert(check(G::unit()));
E s = G::unit();
int i = R;
// false になるところまで戻る
int k = 0;
while (i > 0 && check(s)) {
s = G::op(s, dat[i - 1]);
k = lowbit(i);
i -= i & -i;
}
if (check(s)) {
assert(i == 0);
return 0;
}
// 2^k 進むと ok になる
// false を維持して進む
while (k) {
--k;
E t = G::op(s, G::inverse(dat[i + (1 << k) - 1]));
if (!check(t)) { i += (1 << k), s = t; }
}
return i + 1;
}
int kth(E k, int L = 0) {
return max_right([&k](E x) -> bool { return x <= k; }, L);
}
};
#line 4 "/home/maspy/compro/library/ds/fenwicktree/fenwicktree_01.hpp"
struct FenwickTree_01 {
using MX = Monoid_Add<int>;
int N, n;
vc<u64> dat;
FenwickTree<Monoid_Add<int>> bit;
FenwickTree_01() {}
FenwickTree_01(int n) { build(n); }
template <typename F>
FenwickTree_01(int n, F f) {
build(n, f);
}
void build(int m) {
N = m;
n = ceil<int>(N + 1, 64);
dat.assign(n, u64(0));
bit.build(n);
}
void build(vc<int> dat) {
build(len(dat), [&](int i) -> int { return dat[i]; });
}
template <typename F>
void build(int m, F f) {
N = m;
n = ceil<int>(N + 1, 64);
dat.assign(n, u64(0));
FOR(i, N) { dat[i / 64] |= u64(f(i)) << (i % 64); }
bit.build(n, [&](int i) -> int { return popcnt(dat[i]); });
}
int sum_all() { return bit.sum_all(); }
int sum(int k) { return prefix_sum(k); }
int prefix_sum(int k) {
int ans = bit.sum(k / 64);
ans += popcnt(dat[k / 64] & ((u64(1) << (k % 64)) - 1));
return ans;
}
int sum(int L, int R) {
if (L == 0) return prefix_sum(R);
int ans = 0;
ans -= popcnt(dat[L / 64] & ((u64(1) << (L % 64)) - 1));
ans += popcnt(dat[R / 64] & ((u64(1) << (R % 64)) - 1));
ans += bit.sum(L / 64, R / 64);
return ans;
}
int prod(int L, int R) { return sum(L, R); }
void add(int k, int x) {
if (x == 1) add(k);
elif (x == -1) remove(k);
else assert(0);
}
void multiply(int k, int x) { add(k, x); }
void add(int k) {
dat[k / 64] |= u64(1) << (k % 64);
bit.add(k / 64, 1);
}
void remove(int k) {
dat[k / 64] &= ~(u64(1) << (k % 64));
bit.add(k / 64, -1);
}
int kth(int k, int L = 0) {
if (k >= sum_all()) return N;
k += popcnt(dat[L / 64] & ((u64(1) << (L % 64)) - 1));
L /= 64;
int mid = 0;
auto check = [&](auto e) -> bool {
if (e <= k) chmax(mid, e);
return e <= k;
};
int idx = bit.max_right(check, L);
if (idx == n) return N;
k -= mid;
u64 x = dat[idx];
int p = popcnt(x);
if (p <= k) return N;
k = binary_search([&](int n) -> bool { return (p - popcnt(x >> n)) <= k; }, 0, 64, 0);
return 64 * idx + k;
}
int next(int k) {
int idx = k / 64;
k %= 64;
u64 x = dat[idx] & ~((u64(1) << k) - 1);
if (x) return 64 * idx + lowbit(x);
idx = bit.kth(0, idx + 1);
if (idx == n || !dat[idx]) return N;
return 64 * idx + lowbit(dat[idx]);
}
int prev(int k) {
if (k == N) --k;
int idx = k / 64;
k %= 64;
u64 x = dat[idx];
if (k < 63) x &= (u64(1) << (k + 1)) - 1;
if (x) return 64 * idx + topbit(x);
idx = bit.min_left([&](auto e) -> bool { return e <= 0; }, idx) - 1;
if (idx == -1) return -1;
return 64 * idx + topbit(dat[idx]);
}
};
#line 3 "/home/maspy/compro/library/seq/inversion.hpp"
template <typename T>
ll inversion(vc<T> A) {
int N = len(A);
if (A.empty()) return 0;
ll ANS = 0;
FenwickTree_01 bit(N);
auto I = argsort(A);
for (auto& i: I) {
ANS += bit.sum_all() - bit.sum(i);
bit.add(i, 1);
}
return ANS;
}
// i 番目：A_i が先頭になるように rotate したときの転倒数
template <typename T, bool SMALL = false>
vi inversion_rotate(vc<T>& A) {
const int N = len(A);
if (!SMALL) {
auto key = A;
UNIQUE(key);
for (auto&& x: A) x = LB(key, x);
}
ll K = MAX(A) + 1;
ll ANS = 0;
FenwickTree<Monoid_Add<int>> bit(K);
for (auto&& x: A) {
ANS += bit.sum(x + 1, K);
bit.add(x, 1);
}
vi res(N);
FOR(i, N) {
res[i] = ANS;
ll x = A[i];
ANS = ANS + bit.sum(x + 1, K) - bit.prefix_sum(x);
}
return res;
}
// inv[i][j] = inversion A[i:j) であるような (N+1, N+1) テーブル
template <typename T>
vvc<int> all_range_inversion(vc<T>& A) {
int N = len(A);
vv(int, dp, N + 1, N + 1);
FOR_R(L, N + 1) FOR(R, L + 2, N + 1) {
dp[L][R] = dp[L][R - 1] + dp[L + 1][R] - dp[L + 1][R - 1];
if (A[L] > A[R - 1]) ++dp[L][R];
}
return dp;
}
template <typename T>
ll inversion_between(vc<T> A, vc<T> B) {
int N = len(A);
map<T, vc<int>> MP;
FOR(i, N) MP[B[i]].eb(i);
vc<int> TO(N);
FOR_R(i, N) {
auto& I = MP[A[i]];
if (I.empty()) return -1;
TO[i] = POP(I);
}
return inversion(TO);
}
#line 2 "/home/maspy/compro/library/ds/hashmap.hpp"
// u64 -> Val
template <typename Val>
struct HashMap {
// n は入れたいものの個数で ok
HashMap(u32 n = 0) { build(n); }
void build(u32 n) {
u32 k = 8;
while (k < n * 2) k *= 2;
cap = k / 2, mask = k - 1;
key.resize(k), val.resize(k), used.assign(k, 0);
}
// size を保ったまま. size=0 にするときは build すること.
void clear() {
used.assign(len(used), 0);
cap = (mask + 1) / 2;
}
int size() { return len(used) / 2 - cap; }
int index(const u64& k) {
int i = 0;
for (i = hash(k); used[i] && key[i] != k; i = (i + 1) & mask) {}
return i;
}
Val& operator[](const u64& k) {
if (cap == 0) extend();
int i = index(k);
if (!used[i]) { used[i] = 1, key[i] = k, val[i] = Val{}, --cap; }
return val[i];
}
Val get(const u64& k, Val default_value) {
int i = index(k);
return (used[i] ? val[i] : default_value);
}
bool count(const u64& k) {
int i = index(k);
return used[i] && key[i] == k;
}
// f(key, val)
template <typename F>
void enumerate_all(F f) {
FOR(i, len(used)) if (used[i]) f(key[i], val[i]);
}
private:
u32 cap, mask;
vc<u64> key;
vc<Val> val;
vc<bool> used;
u64 hash(u64 x) {
static const u64 FIXED_RANDOM = std::chrono::steady_clock::now().time_since_epoch().count();
x += FIXED_RANDOM;
x = (x ^ (x >> 30)) * 0xbf58476d1ce4e5b9;
x = (x ^ (x >> 27)) * 0x94d049bb133111eb;
return (x ^ (x >> 31)) & mask;
}
void extend() {
vc<pair<u64, Val>> dat;
dat.reserve(len(used) / 2 - cap);
FOR(i, len(used)) {
if (used[i]) dat.eb(key[i], val[i]);
}
build(2 * len(dat));
for (auto& [a, b]: dat) (*this)[a] = b;
}
};
#line 2 "/home/maspy/compro/library/random/base.hpp"
u64 RNG_64() {
static u64 x_ = u64(chrono::duration_cast<chrono::nanoseconds>(chrono::high_resolution_clock::now().time_since_epoch()).count()) * 10150724397891781847ULL;
x_ ^= x_ << 7;
return x_ ^= x_ >> 9;
}
u64 RNG(u64 lim) { return RNG_64() % lim; }
ll RNG(ll l, ll r) { return l + RNG_64() % (r - l); }
#line 7 "main.cpp"
/*
0 の移動距離 == 転倒数
で？
まあ順列めっちゃたくさんあって、楽しさの種類は少ないので、基本的に存在します
N が大きいとき
それこそスライド操作をランダムにやりまくってお誕生日でよさそうだね
N が小さいとき
大きい、小さいとは？
たぶん 5*5 はよゆうでおおきい
4*4 も大丈夫説
*/
void out(int N, vc<int> X, vc<int> Y) {
Yes();
FOR(2) {
swap(X, Y);
FOR(i, N) {
vc<int> row;
FOR(j, N * i, N * i + N) row.eb(X[j]);
print(row);
}
}
}
void solve_small(ll N) {
VEC(ll, A, N * N);
map<ll, vc<int>> MP;
vc<int> X(N * N);
FOR(i, N * N) X[i] = i;
do {
int pos = min_element(all(X)) - X.begin();
int inv = inversion(X);
if ((pos + inv) % 2 == 1) continue;
ll score = 0;
FOR(i, N * N) score += A[i] * X[i];
if (MP.count(score)) {
vc<int> Y = MP[score];
return out(N, X, Y);
}
MP[score] = X;
} while (next_permutation(all(X)));
No();
}
void solve() {
LL(N);
if (N <= 3) return solve_small(N);
assert(N >= 5);
vc<char> history;
ll LIM = 1 << 22;
HashMap<int> MP(LIM);
VV(u64, A, N, N);
vv(u32, X, N, N);
vv(u64, base, N, N);
FOR(i, N) FOR(j, N) base[i][j] = RNG_64();
FOR(i, N) FOR(j, N) X[i][j] = N * i + j;
u64 sm = 0, hash = 0;
FOR(i, N) FOR(j, N) sm += A[i][j] * X[i][j], hash += base[i][j] * X[i][j];
MP[sm] = 0;
vc<u64> H = {hash};
ll x = 0, y = 0;
auto isin = [&](int x, int y) -> bool { return (0 <= x && x < N && 0 <= y && y < N); };
int dx[] = {1, 0, -1, 0, 1, 1, -1, -1};
int dy[] = {0, 1, 0, -1, 1, -1, 1, -1};
auto [m, n] = [&]() -> pair<int, int> {
int prv = -1;
while (1) {
int d = RNG(0, 4);
if (d == (prv ^ 2)) continue;
int x1 = x + dx[d], y1 = y + dy[d];
if (!isin(x1, y1)) continue;
prv = d;
u64 v = X[x1][y1];
sm += v * (A[x][y] - A[x1][y1]);
hash += v * (base[x][y] - base[x1][y1]);
SHOW(len(MP), sm, hash);
swap(X[x][y], X[x1][y1]);
x = x1, y = y1;
#ifdef LOCAL
u64 mysm = 0;
FOR(i, N) FOR(j, N) mysm += A[i][j] * X[i][j];
assert(sm == mysm);
SHOW(sm, mysm);
#endif
history.eb(d);
H.eb(hash);
int m = MP.get(sm, -1);
if (m != -1 && H[m] != hash) { return {m, len(history)}; }
if (m == -1 && len(MP) < LIM) { MP[sm] = len(history); }
}
assert(0);
return {0, 0};
}();
SHOW(m, n);
FOR(i, N) FOR(j, N) X[i][j] = N * i + j;
x = 0, y = 0;
Yes();
FOR(i, m) {
int d = history[i];
int x1 = x + dx[d], y1 = y + dy[d];
swap(X[x][y], X[x1][y1]);
x = x1, y = y1;
}
vvc<u32> XX = X;
FOR(i, N) print(X[i]);
FOR(i, m, n) {
int d = history[i];
int x1 = x + dx[d], y1 = y + dy[d];
swap(X[x][y], X[x1][y1]);
x = x1, y = y1;
}
vvc<u32> YY = X;
FOR(i, N) print(X[i]);
// check
u64 xx = 0, yy = 0;
FOR(i, N) FOR(j, N) xx += XX[i][j] * A[i][j];
FOR(i, N) FOR(j, N) yy += YY[i][j] * A[i][j];
SHOW(xx, yy);
}
signed main() {
int T = 1;
// INT(T);
FOR(T) solve();
return 0;
}