oj.uz

Submission #650416

# Submission time Handle Problem Language Result Execution time Memory
650416 2022-10-13T17:11:49 Z ymm Bubble Sort 2 (JOI18_bubblesort2) C++17
60 / 100
 9000 ms 34244 KB 
#include "bubblesort2.h"
#include <bits/stdc++.h>
#define Loop(x,l,r) for (ll x = (l); x < (ll)(r); ++x)
#define LoopR(x,l,r) for (ll x = (r)-1; x >= (ll)(l); --x)
typedef long long ll;
typedef std::pair<int, int> pii;
typedef std::pair<ll , ll > pll;
using namespace std;

#pragma GCC optimize("O3,unroll-loops")
#pragma GCC target("avx2")

const int S = 2048 + 512;
const int N = 500'032 + S;
int seg_mx[N/S][S*2];
int seg_cnt[N/S][S*2];
int val[N], cnt[N], val_srt[N], srt_ind[N];
int n;

void add_seg(int l, int r, int x, int t)
{
	#define MAX(x, y) ((x)>(y)?(x):(y))
	#define UP(i) seg_mx[t][i] =   MAX(seg_mx[t][2*(i)],\
	                                   seg_mx[t][2*(i)+1])\
	                             + seg_cnt[t][i];
	l += S; r += S;
	for (;;) {
		if (l != r && (l&1)) {
			seg_mx[t][l] += x;
			seg_cnt[t][l] += x;
			++l;
		}
		if (l != r && (r&1)) {
			--r;
			seg_mx[t][r] += x;
			seg_cnt[t][r] += x;
		}
		l /= 2; r /= 2;
		if (l == 0) break;
		if (l > 1) UP(l-1);
		if (r < S) UP(r);
	}
}

void build_seg(int t)
{
	Loop (i,S,2*S) {
		seg_cnt[t][i] = cnt[srt_ind[S*t + i-S]];
		seg_mx[t][i] = seg_cnt[t][i];
	}
	LoopR (i,1,S) {
		seg_mx[t][i] = max(seg_mx[t][2*i], seg_mx[t][2*i+1]);
		seg_cnt[t][i] = 0;
	}
}

void flush_seg(int t)
{
	Loop (i,1,S) {
		seg_cnt[t][2*i] += seg_cnt[t][i];
		seg_cnt[t][2*i+1] += seg_cnt[t][i];
	}
	Loop (i,S,2*S)
		cnt[srt_ind[t*S + i-S]] = seg_cnt[t][i];
}

int get_gt(int l, int x)
{
	return S - (  upper_bound(val_srt + l, val_srt + l + S, x)
	            - (val_srt + l));
}

void up_range(int l, int xl, int xr, int val)
{
	xl = lower_bound(val_srt + l, val_srt + l + S, xl) - val_srt - l;
	xr = lower_bound(val_srt + l, val_srt + l + S, xr) - val_srt - l;
	if (xl < xr)
		add_seg(xl, xr, val, l/S);
}

void mov_right(int i, int j)
{
	typedef int ymma __attribute__((vector_size(32),aligned(32)));
	typedef int ymmu __attribute__((vector_size(32),aligned(4)));
	if (j-i < 16) {
		Loop (k,i,j) {
			val_srt[k] = val_srt[k+1];
			srt_ind[k] = srt_ind[k+1];
		}
		return;
	}
	while (i%8) {
		val_srt[i] = val_srt[i+1];
		srt_ind[i] = srt_ind[i+1];
		++i;
	}
	Loop (k,i/8,j/8) {
		((ymma *)val_srt)[k] = ((ymmu *)(val_srt+1))[k];
		((ymma *)srt_ind)[k] = ((ymmu *)(srt_ind+1))[k];
	}
	Loop (k,j-j%8,j) {
		val_srt[k] = val_srt[k+1];
		srt_ind[k] = srt_ind[k+1];
	}
}

void mov(int i, int x)
{
	int j = i - i%S;
	for (; srt_ind[j] != i; ++j);
	int dst =   lower_bound(val_srt + i-i%S, val_srt + i-i%S + S, x)
	          - val_srt;
	if (j < dst) {
		mov_right(j, --dst);
	} else {
		LoopR (k, dst, j) {
			val_srt[k+1] = val_srt[k];
			srt_ind[k+1] = srt_ind[k];
		}
	}
	val_srt[dst] = x;
	srt_ind[dst] = i;
}

void up(int i, int x)
{
	int pre = val[i];
	int cnt_gt = 0;
	for (int l = 0; l < i - i%S; l += S)
		cnt_gt += get_gt(l, x);
	flush_seg(i/S);
	val[i] = x;
	for (int j = i - i%S; j < i; ++j)
		cnt_gt += val[j] > x;
	cnt[i] = cnt_gt;
	for (int j = i + 1; j < i - i%S + S; ++j)
		cnt[j] += (x > val[j]) - (pre > val[j]);
	mov(i, x);
	build_seg(i/S);
	int val = pre < x? 1: -1;
	int xl = pre < x? pre: x;
	int xr = pre < x? x: pre;
	for (int l = i - i%S + S; l < n; l += S)
		up_range(l, xl, xr, val);
}

int get()
{
	int mx = 0;
	for (int l = 0; l < n; l += S)
		mx = max(seg_mx[l/S][1], mx);
	return mx;
}

namespace init {
int fen[N];
void fen_add(int i, int x)
{
	++i;
	while (i < N) {
		fen[i] += x;
		i += i & -i;
	}
}
int fen_get(int r)
{
	int ans = 0;
	while (r > 0) {
		ans += fen[r];
		r -= r & -r;
	}
	return ans;
}
 
void init(vector<int> A)
{
	static pii pii_srt[N];
	n = A.size();
	Loop (i,0,n) {
		val[i] = A[i];
		pii_srt[i] = {val[i], i};
	}
	Loop (i,n,N) {
		val[i] = 1e9+10;
		pii_srt[i] = {val[i], i};
	}
	for (int l = 0; l < n; l += S) {
		sort(pii_srt+l, pii_srt+l+S);
		Loop (i,l,l+S) {
			val_srt[i] = pii_srt[i].first;
			srt_ind[i] = pii_srt[i].second;
		}
	}
	vector<int> cmp(val, val+N);
	sort(cmp.begin(), cmp.end());
	cmp.resize(unique(cmp.begin(), cmp.end()) - cmp.begin());
	int mx = cmp.size() - 1;
	Loop (i,0,n) {
		int j =   lower_bound(cmp.begin(), cmp.end(), val[i])
		        - cmp.begin();
		cnt[i] = fen_get(mx-j);
		fen_add(mx-j, 1);
	}
	for (int l = 0; l < n; l += S)
		build_seg(l/S);
}
}

vector<int> countScans(vector<int> A, vector<int> X, vector<int> V)
{
	init::init(A);
	vector<int> ans;
	Loop (i,0,X.size()) {
		up(X[i], V[i]);
		ans.push_back(get());
	}
	return ans;
}

Subtask #1
17.0 / 17.0

# Verdict Execution time Memory Grader output
1 Correct 21 ms 8244 KB Output is correct
2 Correct 25 ms 8264 KB Output is correct
3 Correct 42 ms 8288 KB Output is correct
4 Correct 40 ms 8292 KB Output is correct
5 Correct 44 ms 8276 KB Output is correct
6 Correct 46 ms 8276 KB Output is correct
7 Correct 45 ms 8276 KB Output is correct
8 Correct 41 ms 8284 KB Output is correct
9 Correct 45 ms 8280 KB Output is correct
10 Correct 39 ms 8276 KB Output is correct
11 Correct 41 ms 8288 KB Output is correct
12 Correct 47 ms 8324 KB Output is correct
13 Correct 43 ms 8276 KB Output is correct
14 Correct 40 ms 8288 KB Output is correct
15 Correct 41 ms 8288 KB Output is correct
16 Correct 39 ms 8284 KB Output is correct
17 Correct 42 ms 8284 KB Output is correct
18 Correct 47 ms 8276 KB Output is correct

Subtask #2
21.0 / 21.0

# Verdict Execution time Memory Grader output
1 Correct 21 ms 8244 KB Output is correct
2 Correct 25 ms 8264 KB Output is correct
3 Correct 42 ms 8288 KB Output is correct
4 Correct 40 ms 8292 KB Output is correct
5 Correct 44 ms 8276 KB Output is correct
6 Correct 46 ms 8276 KB Output is correct
7 Correct 45 ms 8276 KB Output is correct
8 Correct 41 ms 8284 KB Output is correct
9 Correct 45 ms 8280 KB Output is correct
10 Correct 39 ms 8276 KB Output is correct
11 Correct 41 ms 8288 KB Output is correct
12 Correct 47 ms 8324 KB Output is correct
13 Correct 43 ms 8276 KB Output is correct
14 Correct 40 ms 8288 KB Output is correct
15 Correct 41 ms 8288 KB Output is correct
16 Correct 39 ms 8284 KB Output is correct
17 Correct 42 ms 8284 KB Output is correct
18 Correct 47 ms 8276 KB Output is correct
19 Correct 121 ms 8660 KB Output is correct
20 Correct 134 ms 8772 KB Output is correct
21 Correct 143 ms 8660 KB Output is correct
22 Correct 131 ms 8636 KB Output is correct
23 Correct 137 ms 8660 KB Output is correct
24 Correct 142 ms 8660 KB Output is correct
25 Correct 143 ms 8660 KB Output is correct
26 Correct 134 ms 8708 KB Output is correct
27 Correct 139 ms 8628 KB Output is correct
28 Correct 145 ms 8660 KB Output is correct

Subtask #3
22.0 / 22.0

# Verdict Execution time Memory Grader output
1 Correct 53 ms 9296 KB Output is correct
2 Correct 453 ms 10148 KB Output is correct
3 Correct 975 ms 10956 KB Output is correct
4 Correct 934 ms 10948 KB Output is correct
5 Correct 914 ms 10992 KB Output is correct
6 Correct 895 ms 11016 KB Output is correct
7 Correct 905 ms 11008 KB Output is correct
8 Correct 876 ms 10956 KB Output is correct
9 Correct 868 ms 10956 KB Output is correct
10 Correct 750 ms 11004 KB Output is correct
11 Correct 782 ms 10964 KB Output is correct
12 Correct 808 ms 10964 KB Output is correct
13 Correct 804 ms 10956 KB Output is correct
14 Correct 762 ms 10964 KB Output is correct
15 Correct 732 ms 11008 KB Output is correct
16 Correct 705 ms 10984 KB Output is correct
17 Correct 705 ms 10964 KB Output is correct
18 Correct 712 ms 10956 KB Output is correct

Subtask #4
0 / 40.0

# Verdict Execution time Memory Grader output
1 Correct 21 ms 8244 KB Output is correct
2 Correct 25 ms 8264 KB Output is correct
3 Correct 42 ms 8288 KB Output is correct
4 Correct 40 ms 8292 KB Output is correct
5 Correct 44 ms 8276 KB Output is correct
6 Correct 46 ms 8276 KB Output is correct
7 Correct 45 ms 8276 KB Output is correct
8 Correct 41 ms 8284 KB Output is correct
9 Correct 45 ms 8280 KB Output is correct
10 Correct 39 ms 8276 KB Output is correct
11 Correct 41 ms 8288 KB Output is correct
12 Correct 47 ms 8324 KB Output is correct
13 Correct 43 ms 8276 KB Output is correct
14 Correct 40 ms 8288 KB Output is correct
15 Correct 41 ms 8288 KB Output is correct
16 Correct 39 ms 8284 KB Output is correct
17 Correct 42 ms 8284 KB Output is correct
18 Correct 47 ms 8276 KB Output is correct
19 Correct 121 ms 8660 KB Output is correct
20 Correct 134 ms 8772 KB Output is correct
21 Correct 143 ms 8660 KB Output is correct
22 Correct 131 ms 8636 KB Output is correct
23 Correct 137 ms 8660 KB Output is correct
24 Correct 142 ms 8660 KB Output is correct
25 Correct 143 ms 8660 KB Output is correct
26 Correct 134 ms 8708 KB Output is correct
27 Correct 139 ms 8628 KB Output is correct
28 Correct 145 ms 8660 KB Output is correct
29 Correct 53 ms 9296 KB Output is correct
30 Correct 453 ms 10148 KB Output is correct
31 Correct 975 ms 10956 KB Output is correct
32 Correct 934 ms 10948 KB Output is correct
33 Correct 914 ms 10992 KB Output is correct
34 Correct 895 ms 11016 KB Output is correct
35 Correct 905 ms 11008 KB Output is correct
36 Correct 876 ms 10956 KB Output is correct
37 Correct 868 ms 10956 KB Output is correct
38 Correct 750 ms 11004 KB Output is correct
39 Correct 782 ms 10964 KB Output is correct
40 Correct 808 ms 10964 KB Output is correct
41 Correct 804 ms 10956 KB Output is correct
42 Correct 762 ms 10964 KB Output is correct
43 Correct 732 ms 11008 KB Output is correct
44 Correct 705 ms 10984 KB Output is correct
45 Correct 705 ms 10964 KB Output is correct
46 Correct 712 ms 10956 KB Output is correct
47 Correct 3553 ms 17112 KB Output is correct
48 Execution timed out 9029 ms 34244 KB Time limit exceeded
49 Halted 0 ms 0 KB -