oj.uz

답안 #558606

# 제출 시각 아이디 문제 언어 결과 실행 시간 메모리
558606 2022-05-07T15:22:04 Z DanShaders Sprinkler (JOI22_sprinkler) C++17
41 / 100
 4000 ms 586004 KB 
#pragma GCC target("avx2")

#include <bits/stdc++.h>
#include <immintrin.h>
#include <ext/pb_ds/assoc_container.hpp>
using namespace std;

namespace x = __gnu_pbds;
template <typename T>
using ordered_set = x::tree<T, x::null_type, less<T>, x::rb_tree_tag, x::tree_order_statistics_node_update>;

template <typename T>
using normal_queue = priority_queue<T, vector<T>, greater<>>;

#define all(x) begin(x), end(x)
#define sz(x) ((int) (x).size())
#define x first
#define y second
using ll = long long;
using ld = long double;

const int N = 2e5 + 10, EULER = 2 * N, LOG = 19;
const int BUFF = 4096;

char buff[BUFF + 1];
int buff_it = 0, buff_len = 0;

char wbuff[BUFF];
int wbuff_len = 0;

char read_char() {
	if (buff_it == buff_len) {
		buff_len = (int) fread(buff, 1, BUFF, stdin);
		buff[buff_len] = 0;
		buff_it = 0;
	}
	return buff[buff_it++];
}

int read_int() {
	char c = ' ';
	while (!isdigit(c = read_char()));
	int res = 0;
	do {
		res *= 10;
		res += c - '0';
	} while (isdigit(c = read_char()));
	return res;
}

void wflush() {
	fwrite(wbuff, 1, wbuff_len, stdout);
	wbuff_len = 0;
}

void write_char(char c) {
	if (wbuff_len == BUFF) {
		wflush();
	}
	wbuff[wbuff_len++] = c;
}

void write_int(ll x) {
	static char cbuff[20];
	int i = 0;
	if (!x) {
		write_char('0');
		return;
	}
	for (; x; x /= 10) {
		cbuff[i++] = char(x % 10 + '0');
	}
	for (; i--; ) {
		write_char(cbuff[i]);
	}
}

vector<int> g[N];
int h[N], sz[N];
char used[N];

const int INT_MEM = 7600380;

struct Arr {
	int a[9] __attribute__((aligned(32)));
	ll i;
} int_mem[INT_MEM];

struct CentroidNode {
	int parent, depth, sz;
	vector<int> ob, pb;
	Arr *op, *pp;
} tc[N];

int next_free = 0;

Arr *allocate(int x) {
	Arr *res = int_mem + next_free;
	for (int i = next_free; i < next_free + x; ++i) {
		int_mem[i].i = 1;
	}
	next_free += x;
	assert(next_free < INT_MEM);
	return res;
}

int where[LOG][N], where2[LOG][N];

int dfs_sz(int u, int p = -1) {
	if (used[u]) {
		return 0;
	}
	sz[u] = 1;
	for (int v : g[u]) {
		if (v == p) {
			continue;
		}
		sz[u] += dfs_sz(v, u);
	}
	return sz[u];
}

int dfs_find_centroid(int u, int csz, int p = -1) {
	for (int v : g[u]) {
		if (v != p && !used[v] && 2 * sz[v] >= csz) {
			return dfs_find_centroid(v, csz, u);
		}
	}
	return u;
}

int croot;

queue<tuple<int, int, int>> bfs;

void dfs_centroid(int root, int parent = -1, int depth = 0) {
	int centroid = dfs_find_centroid(root, dfs_sz(root));
	auto &node = tc[centroid];
	node.parent = parent;
	node.depth = depth;
	node.sz = sz[root];
	if (parent == -1) {
		croot = centroid;
	}

	bfs.push({1, root, -1});
	int prev = -1, at = 0;
	node.pb.push_back(0);
	while (sz(bfs)) {
		auto [d, u, p] = bfs.front();
		bfs.pop();
		where2[depth][u] = at;
		if (prev != d) {
			node.pb.push_back(at);
			prev = d;
		}
		++at;
		for (int v : g[u]) {
			if (!used[v] && v != p) {
				bfs.push({d + 1, v, u});
			}
		}
	}

	bfs.push({0, centroid, -1});
	prev = -1, at = 0;
	while (sz(bfs)) {
		auto [d, u, p] = bfs.front();
		bfs.pop();
		where[depth][u] = at;
		if (prev != d) {
			node.ob.push_back(at);
			prev = d;
		}
		++at;
		for (int v : g[u]) {
			if (!used[v] && v != p) {
				bfs.push({d + 1, v, u});
			}
		}
	}
	
	node.op = allocate(node.sz);
	node.pp = allocate(node.sz);

	used[centroid] = 1;
	for (int v : g[centroid]) {
		if (!used[v]) {
			dfs_centroid(v, centroid, depth + 1);
		}
	}
}

int ipow[EULER], depth[N];
pair<int, int> sp[LOG][EULER];
int order[N], timer = 0;

void dfs_euler(int u, int d = 0, int p = -1) {
	order[u] = timer;
	depth[u] = d;
	sp[0][timer++] = {d, u};
	for (int v : g[u]) {
		if (v != p) {
			dfs_euler(v, d + 1, u);
			sp[0][timer++] = {d, u};
		}
	}
}

int lca(int u, int v) {
	if (u == v) {
		return u;
	}
	u = order[u];
	v = order[v];
	if (u > v) {
		swap(u, v);
	}
	++v;
	int pw = ipow[v - u];
	return min(sp[pw][u], sp[pw][v - (1 << pw)]).y;
}

int dist(int u, int v) {
	return depth[u] + depth[v] - 2 * depth[lca(u, v)];
}

vector<pair<int, int>> factor(int x) {
	vector<pair<int, int>> res;
	for (int i = 2; i * i <= x; ++i) {
		if (x % i == 0) {
			res.push_back({i, 0});
			while (x % i == 0) {
				++res.back().y;
				x /= i;
			}
		}
	}
	if (x != 1) {
		res.push_back({x, 1});
	}
	return res;
}

pair<vector<int>, int> get_pw(int x, const vector<pair<int, int>> &fact) {
	vector<int> pw;
	for (auto [prime, _] : fact) {
		pw.push_back(0);
		while (x % prime == 0) {
			x /= prime;
			++pw.back();
		}
	}
	return {pw, x};
}

void exgcd(int a, int b, ll &x, ll &y) {
	if (b == 0) {
		x = 1;
		y = 0;
		return;
	}
	exgcd(b, a % b, x, y);
	ll nw = x - (a / b) * y;
	x = y;
	y = nw;
}

int diff;
ll l;

template <typename T>
void tdo(int, int r, int, T func) {
	for (; r >= 0; r &= r + 1, --r) {
		func(r);
	}
}

int part[12] __attribute__((aligned(32)));

void apply_for(int ineq, int inv, int u, int x, int d) {
	auto &node = tc[u];

	int dst = d - dist(u, x);
	int bound = dst < 0 ? 0 : (dst + 1 >= sz(node.ob) ? node.sz : node.ob[dst + 1]);

	__m256i part1 = _mm256_load_si256((__m256i*) (part));
	if (ineq != 1) {
		tdo(0, bound - 1, node.sz, [&](int j) {
			__m256i x1 = _mm256_load_si256((__m256i*) (node.op[j].a));
			_mm256_store_si256((__m256i*) (node.op[j].a), _mm256_add_epi32(x1, part1));
			node.op[j].a[8] += part[8];
 
			(node.op[j].i *= ineq) %= l;
		});
	} else {
		tdo(0, bound - 1, node.sz, [&](int j) {
			__m256i x1 = _mm256_load_si256((__m256i*) (node.op[j].a));
			_mm256_store_si256((__m256i*) (node.op[j].a), _mm256_add_epi32(x1, part1));
			node.op[j].a[8] += part[8];
		});
	}

	if (node.parent == -1) {
		return;
	}

	dst = d - dist(node.parent, x);
	bound = dst < 0 ? 0 : (dst + 1 >= sz(node.pb) ? node.sz : node.pb[dst + 1]);
	if (inv != 1) {
		tdo(0, bound - 1, node.sz, [&](int j) {
			__m256i x1 = _mm256_load_si256((__m256i*) (node.pp[j].a));
			_mm256_store_si256((__m256i*) (node.pp[j].a), _mm256_sub_epi32(x1, part1));
			node.pp[j].a[8] -= part[8];

			(node.pp[j].i *= inv) %= l;
		});
	} else {
		tdo(0, bound - 1, node.sz, [&](int j) {
			__m256i x1 = _mm256_load_si256((__m256i*) (node.pp[j].a));
			_mm256_store_si256((__m256i*) (node.pp[j].a), _mm256_sub_epi32(x1, part1));
			node.pp[j].a[8] -= part[8];
		});
	}
}

void count_for(ll &ineq, int u, int x) {
	const auto &node = tc[u];

	__m256i lpart{};
	int lpart8 = 0;

	int i = where[node.depth][x];
	for (; i < node.sz; i |= i + 1) {
		__m256i x1 = _mm256_load_si256((__m256i*) (node.op[i].a));
		lpart = _mm256_add_epi32(x1, lpart);
		lpart8 += node.op[i].a[8];

// #pragma GCC ivdep
// 		for (int j = 0; j < 9; ++j) {
// 			part[j] += node.op[i].a[j];
// 		}
		(ineq *= node.op[i].i) %= l;
	}

	if (node.parent != -1) {

	i = where2[node.depth][x];
	for (; i < node.sz; i |= i + 1) {
		__m256i x1 = _mm256_load_si256((__m256i*) (node.pp[i].a));
		lpart = _mm256_add_epi32(x1, lpart);
		lpart8 += node.pp[i].a[8];

		(ineq *= node.pp[i].i) %= l;
	}
	}

	int rpart[8] __attribute__((aligned(32)));
	_mm256_store_si256((__m256i *) rpart, lpart);
	
	part[8] += lpart8;
	for (int i = 0; i < 8; ++i) {
		part[i] += rpart[i];
	}
}

ll fpow(ll a, ll b) {
	ll c = 1;
	for (int i = 1; i <= b; i *= 2) {
		if (b & i) {
			(c *= a) %= l;
		}
		(a *= a) %= l;
	}
	return c;
}

signed main() {
#ifdef DEBUG
	freopen("output.txt", "w", stdout);
#endif
	int n = read_int();
	l = read_int();

	for (int i = 1; i < n; ++i) {
		int u = read_int(), v = read_int();
		g[--u].push_back(--v);
		g[v].push_back(u);
	}
	for (int i = 0; i < n; ++i) {
		h[i] = read_int();
	}
	dfs_euler(0);
	for (int i = 1; i < LOG; ++i) {
		for (int j = 0; j <= timer - (1 << i); ++j) {
			sp[i][j] = min(sp[i - 1][j], sp[i - 1][j + (1 << (i - 1))]);
		}
	}
	for (int i = 2; i <= timer; ++i) {
		ipow[i] = ipow[i / 2] + 1;
	}
	dfs_centroid(0);
	int queries = read_int();
	auto fact = factor(int(l));
	diff = sz(fact);

	while (queries--) {
		int type = read_int();
		if (type == 1) {
			int x = read_int(), d = read_int(), w = read_int();
			--x;
			if (!w) {
				w = int(l);
			}
			auto [partr, ineq] = get_pw(w, fact);
			fill(all(part), 0);
			copy_n(begin(partr), sz(partr), begin(part));
			ll inv, tmp;
			exgcd(ineq, int(l), inv, tmp);
			inv = (inv % l + l) % l;

			int curr = x;
			while (curr != -1) {
				apply_for(ineq, int(inv), curr, x, d);
				curr = tc[curr].parent;
			}
		} else {
			int x = read_int() - 1;
			fill(all(part), 0);
			ll ineq = 1;
			int curr = x;
			while (curr != -1) {
				count_for(ineq, curr, x);
				curr = tc[curr].parent;
			}

			ll res = 1;
			for (int i = 0; i < diff; ++i) {
				(res *= fpow(fact[i].x, part[i])) %= l;
			}
			(res *= ineq) %= l;
			write_int((h[x] * res) % l);
			write_char('\n');
			// for (int u : part) {
			// 	cout << u << " ";
			// }
			// cout << ineq << "\n";
		}
	}
	wflush();
	cerr << clock() << endl;
}

Subtask #1
3.0 / 3.0

# 결과 실행 시간 메모리 Grader output
1 Correct 12 ms 20692 KB Output is correct
2 Correct 12 ms 20692 KB Output is correct
3 Correct 11 ms 20692 KB Output is correct
4 Correct 13 ms 22484 KB Output is correct
5 Correct 13 ms 22172 KB Output is correct
6 Correct 13 ms 21900 KB Output is correct
7 Correct 13 ms 21844 KB Output is correct
8 Correct 12 ms 21332 KB Output is correct
9 Correct 12 ms 20692 KB Output is correct
10 Correct 12 ms 20692 KB Output is correct
11 Correct 12 ms 20692 KB Output is correct
12 Correct 13 ms 20692 KB Output is correct
13 Correct 12 ms 20820 KB Output is correct
14 Correct 11 ms 20692 KB Output is correct
15 Correct 12 ms 20692 KB Output is correct
16 Correct 14 ms 20772 KB Output is correct
17 Correct 11 ms 20692 KB Output is correct
18 Correct 12 ms 20828 KB Output is correct
19 Correct 11 ms 20652 KB Output is correct
20 Correct 13 ms 20740 KB Output is correct
21 Correct 11 ms 20692 KB Output is correct
22 Correct 12 ms 20692 KB Output is correct
23 Correct 11 ms 20692 KB Output is correct
24 Correct 11 ms 20756 KB Output is correct
25 Correct 12 ms 20692 KB Output is correct
26 Correct 13 ms 20764 KB Output is correct
27 Correct 13 ms 20820 KB Output is correct
28 Correct 13 ms 20816 KB Output is correct

Subtask #2
9.0 / 9.0

# 결과 실행 시간 메모리 Grader output
1 Correct 11 ms 20692 KB Output is correct
2 Correct 2998 ms 452948 KB Output is correct
3 Correct 1924 ms 440804 KB Output is correct
4 Correct 3449 ms 578960 KB Output is correct
5 Correct 2326 ms 442312 KB Output is correct
6 Correct 1753 ms 365764 KB Output is correct
7 Correct 1581 ms 330604 KB Output is correct
8 Correct 488 ms 155844 KB Output is correct
9 Correct 3979 ms 586004 KB Output is correct
10 Correct 2523 ms 583592 KB Output is correct
11 Correct 2792 ms 452712 KB Output is correct
12 Correct 1824 ms 447252 KB Output is correct
13 Correct 451 ms 161460 KB Output is correct
14 Correct 522 ms 179476 KB Output is correct
15 Correct 581 ms 202932 KB Output is correct
16 Correct 651 ms 224748 KB Output is correct
17 Correct 735 ms 250192 KB Output is correct
18 Correct 13 ms 20692 KB Output is correct
19 Correct 12 ms 20692 KB Output is correct
20 Correct 12 ms 20820 KB Output is correct
21 Correct 12 ms 20820 KB Output is correct
22 Correct 13 ms 20820 KB Output is correct

Subtask #3
29.0 / 29.0

# 결과 실행 시간 메모리 Grader output
1 Correct 11 ms 20692 KB Output is correct
2 Correct 2998 ms 452948 KB Output is correct
3 Correct 1924 ms 440804 KB Output is correct
4 Correct 3449 ms 578960 KB Output is correct
5 Correct 2326 ms 442312 KB Output is correct
6 Correct 1753 ms 365764 KB Output is correct
7 Correct 1581 ms 330604 KB Output is correct
8 Correct 488 ms 155844 KB Output is correct
9 Correct 3979 ms 586004 KB Output is correct
10 Correct 2523 ms 583592 KB Output is correct
11 Correct 2792 ms 452712 KB Output is correct
12 Correct 1824 ms 447252 KB Output is correct
13 Correct 451 ms 161460 KB Output is correct
14 Correct 522 ms 179476 KB Output is correct
15 Correct 581 ms 202932 KB Output is correct
16 Correct 651 ms 224748 KB Output is correct
17 Correct 735 ms 250192 KB Output is correct
18 Correct 13 ms 20692 KB Output is correct
19 Correct 12 ms 20692 KB Output is correct
20 Correct 12 ms 20820 KB Output is correct
21 Correct 12 ms 20820 KB Output is correct
22 Correct 13 ms 20820 KB Output is correct
23 Correct 12 ms 20764 KB Output is correct
24 Correct 2846 ms 453952 KB Output is correct
25 Correct 1937 ms 443964 KB Output is correct
26 Correct 3302 ms 585508 KB Output is correct
27 Correct 2321 ms 446864 KB Output is correct
28 Correct 1908 ms 377588 KB Output is correct
29 Correct 1532 ms 330696 KB Output is correct
30 Correct 600 ms 158108 KB Output is correct
31 Correct 3935 ms 583608 KB Output is correct
32 Correct 2566 ms 584084 KB Output is correct
33 Correct 2769 ms 448888 KB Output is correct
34 Correct 1839 ms 441700 KB Output is correct
35 Correct 12 ms 20692 KB Output is correct
36 Correct 13 ms 20684 KB Output is correct
37 Correct 12 ms 20692 KB Output is correct
38 Correct 12 ms 20820 KB Output is correct
39 Correct 13 ms 20812 KB Output is correct
40 Correct 13 ms 20692 KB Output is correct
41 Correct 13 ms 20768 KB Output is correct
42 Correct 13 ms 20684 KB Output is correct
43 Correct 11 ms 20692 KB Output is correct
44 Correct 12 ms 20740 KB Output is correct
45 Correct 14 ms 20728 KB Output is correct
46 Correct 13 ms 20796 KB Output is correct
47 Correct 12 ms 20740 KB Output is correct
48 Correct 12 ms 20820 KB Output is correct
49 Correct 11 ms 20820 KB Output is correct

Subtask #4
0 / 12.0

# 결과 실행 시간 메모리 Grader output
1 Correct 12 ms 20724 KB Output is correct
2 Execution timed out 4067 ms 582908 KB Time limit exceeded
3 Halted 0 ms 0 KB -

Subtask #5
0 / 30.0

# 결과 실행 시간 메모리 Grader output
1 Correct 14 ms 20692 KB Output is correct
2 Execution timed out 4108 ms 580124 KB Time limit exceeded
3 Halted 0 ms 0 KB -

Subtask #6
0 / 17.0

# 결과 실행 시간 메모리 Grader output
1 Correct 12 ms 20692 KB Output is correct
2 Correct 12 ms 20692 KB Output is correct
3 Correct 11 ms 20692 KB Output is correct
4 Correct 13 ms 22484 KB Output is correct
5 Correct 13 ms 22172 KB Output is correct
6 Correct 13 ms 21900 KB Output is correct
7 Correct 13 ms 21844 KB Output is correct
8 Correct 12 ms 21332 KB Output is correct
9 Correct 12 ms 20692 KB Output is correct
10 Correct 12 ms 20692 KB Output is correct
11 Correct 12 ms 20692 KB Output is correct
12 Correct 13 ms 20692 KB Output is correct
13 Correct 12 ms 20820 KB Output is correct
14 Correct 11 ms 20692 KB Output is correct
15 Correct 12 ms 20692 KB Output is correct
16 Correct 14 ms 20772 KB Output is correct
17 Correct 11 ms 20692 KB Output is correct
18 Correct 12 ms 20828 KB Output is correct
19 Correct 11 ms 20652 KB Output is correct
20 Correct 13 ms 20740 KB Output is correct
21 Correct 11 ms 20692 KB Output is correct
22 Correct 12 ms 20692 KB Output is correct
23 Correct 11 ms 20692 KB Output is correct
24 Correct 11 ms 20756 KB Output is correct
25 Correct 12 ms 20692 KB Output is correct
26 Correct 13 ms 20764 KB Output is correct
27 Correct 13 ms 20820 KB Output is correct
28 Correct 13 ms 20816 KB Output is correct
29 Correct 11 ms 20692 KB Output is correct
30 Correct 2998 ms 452948 KB Output is correct
31 Correct 1924 ms 440804 KB Output is correct
32 Correct 3449 ms 578960 KB Output is correct
33 Correct 2326 ms 442312 KB Output is correct
34 Correct 1753 ms 365764 KB Output is correct
35 Correct 1581 ms 330604 KB Output is correct
36 Correct 488 ms 155844 KB Output is correct
37 Correct 3979 ms 586004 KB Output is correct
38 Correct 2523 ms 583592 KB Output is correct
39 Correct 2792 ms 452712 KB Output is correct
40 Correct 1824 ms 447252 KB Output is correct
41 Correct 451 ms 161460 KB Output is correct
42 Correct 522 ms 179476 KB Output is correct
43 Correct 581 ms 202932 KB Output is correct
44 Correct 651 ms 224748 KB Output is correct
45 Correct 735 ms 250192 KB Output is correct
46 Correct 13 ms 20692 KB Output is correct
47 Correct 12 ms 20692 KB Output is correct
48 Correct 12 ms 20820 KB Output is correct
49 Correct 12 ms 20820 KB Output is correct
50 Correct 13 ms 20820 KB Output is correct
51 Correct 12 ms 20764 KB Output is correct
52 Correct 2846 ms 453952 KB Output is correct
53 Correct 1937 ms 443964 KB Output is correct
54 Correct 3302 ms 585508 KB Output is correct
55 Correct 2321 ms 446864 KB Output is correct
56 Correct 1908 ms 377588 KB Output is correct
57 Correct 1532 ms 330696 KB Output is correct
58 Correct 600 ms 158108 KB Output is correct
59 Correct 3935 ms 583608 KB Output is correct
60 Correct 2566 ms 584084 KB Output is correct
61 Correct 2769 ms 448888 KB Output is correct
62 Correct 1839 ms 441700 KB Output is correct
63 Correct 12 ms 20692 KB Output is correct
64 Correct 13 ms 20684 KB Output is correct
65 Correct 12 ms 20692 KB Output is correct
66 Correct 12 ms 20820 KB Output is correct
67 Correct 13 ms 20812 KB Output is correct
68 Correct 13 ms 20692 KB Output is correct
69 Correct 13 ms 20768 KB Output is correct
70 Correct 13 ms 20684 KB Output is correct
71 Correct 11 ms 20692 KB Output is correct
72 Correct 12 ms 20740 KB Output is correct
73 Correct 14 ms 20728 KB Output is correct
74 Correct 13 ms 20796 KB Output is correct
75 Correct 12 ms 20740 KB Output is correct
76 Correct 12 ms 20820 KB Output is correct
77 Correct 11 ms 20820 KB Output is correct
78 Correct 12 ms 20724 KB Output is correct
79 Execution timed out 4067 ms 582908 KB Time limit exceeded
80 Halted 0 ms 0 KB -