oj.uz

답안 #644586

# 제출 시각 아이디 문제 언어 결과 실행 시간 메모리
644586 2022-09-25T03:30:31 Z ymm 운세 보기 2 (JOI14_fortune_telling2) C++17
35 / 100
 3000 ms 6856 KB 
#include <bits/stdc++.h>
#define Loop(x,l,r) for (ll x = (l); x < (r); ++x)
#define LoopR(x,l,r) for (ll x = (r)-1; x >= (l); --x)
typedef long long ll;
typedef std::pair<int, int> pii;
typedef std::pair<ll , ll > pll;
using namespace std;

const int N = 200'010;
int a[N], b[N];
int n;

/*
void up(int x)
{
	Loop (i,0,n)
		a[i] ^= a[i] <= x? b[i]: 0;
}
*/

void up(int);

asm("\n"
"	.text\n"
"	.p2align 4\n"
"	.globl	_Z2upi\n"
"	.type	_Z2upi, @function\n"
"_Z2upi:\n"
".myLFB9703:\n"
"	.cfi_startproc\n"
"	movl	%edi, %r8d\n"
"	movslq	n(%rip), %rdi\n"
"	testq	%rdi, %rdi\n"
"	jle	.myL53\n"
"	leaq	-1(%rdi), %rax\n"
"	cmpq	$6, %rax\n"
"	jbe	.myL14\n"
"	movq	%rdi, %rcx\n"
"	leaq	a(%rip), %rsi\n"
"	vmovd	%r8d, %xmm3\n"
"	shrq	$3, %rcx\n"
"	vpbroadcastd	%xmm3, %ymm3\n"
"	movq	%rsi, %rax\n"
"	salq	$5, %rcx\n"
"	leaq	b(%rip), %rdx\n"
"	leaq	(%rsi,%rcx), %r9\n"
"	subq	$32, %rcx\n"
"	shrq	$5, %rcx\n"
"	addq	$1, %rcx\n"
"	andl	$7, %ecx\n"
"	je	.myL4\n"
"	cmpq	$1, %rcx\n"
"	je	.myL37\n"
"	cmpq	$2, %rcx\n"
"	je	.myL38\n"
"	cmpq	$3, %rcx\n"
"	je	.myL39\n"
"	cmpq	$4, %rcx\n"
"	je	.myL40\n"
"	cmpq	$5, %rcx\n"
"	je	.myL41\n"
"	cmpq	$6, %rcx\n"
"	jne	.myL55\n"
".myL42:\n"
"	vmovdqa	(%rax), %ymm1\n"
"	vpxor	(%rdx), %ymm1, %ymm0\n"
"	addq	$32, %rax\n"
"	addq	$32, %rdx\n"
"	vpcmpgtd	%ymm3, %ymm1, %ymm2\n"
"	vpblendvb	%ymm2, %ymm1, %ymm0, %ymm0\n"
"	vmovdqa	%ymm0, -32(%rax)\n"
".myL41:\n"
"	vmovdqa	(%rax), %ymm1\n"
"	vpxor	(%rdx), %ymm1, %ymm0\n"
"	addq	$32, %rax\n"
"	addq	$32, %rdx\n"
"	vpcmpgtd	%ymm3, %ymm1, %ymm2\n"
"	vpblendvb	%ymm2, %ymm1, %ymm0, %ymm0\n"
"	vmovdqa	%ymm0, -32(%rax)\n"
".myL40:\n"
"	vmovdqa	(%rax), %ymm1\n"
"	vpxor	(%rdx), %ymm1, %ymm0\n"
"	addq	$32, %rax\n"
"	addq	$32, %rdx\n"
"	vpcmpgtd	%ymm3, %ymm1, %ymm2\n"
"	vpblendvb	%ymm2, %ymm1, %ymm0, %ymm0\n"
"	vmovdqa	%ymm0, -32(%rax)\n"
".myL39:\n"
"	vmovdqa	(%rax), %ymm1\n"
"	vpxor	(%rdx), %ymm1, %ymm0\n"
"	addq	$32, %rax\n"
"	addq	$32, %rdx\n"
"	vpcmpgtd	%ymm3, %ymm1, %ymm2\n"
"	vpblendvb	%ymm2, %ymm1, %ymm0, %ymm0\n"
"	vmovdqa	%ymm0, -32(%rax)\n"
".myL38:\n"
"	vmovdqa	(%rax), %ymm1\n"
"	vpxor	(%rdx), %ymm1, %ymm0\n"
"	addq	$32, %rax\n"
"	addq	$32, %rdx\n"
"	vpcmpgtd	%ymm3, %ymm1, %ymm2\n"
"	vpblendvb	%ymm2, %ymm1, %ymm0, %ymm0\n"
"	vmovdqa	%ymm0, -32(%rax)\n"
".myL37:\n"
"	vmovdqa	(%rax), %ymm1\n"
"	vpxor	(%rdx), %ymm1, %ymm0\n"
"	addq	$32, %rax\n"
"	addq	$32, %rdx\n"
"	vpcmpgtd	%ymm3, %ymm1, %ymm2\n"
"	vpblendvb	%ymm2, %ymm1, %ymm0, %ymm0\n"
"	vmovdqa	%ymm0, -32(%rax)\n"
"	cmpq	%r9, %rax\n"
"	je	.myL51\n"
".myL4:\n"
"	vmovdqa	(%rax), %ymm1\n"
"	vpxor	(%rdx), %ymm1, %ymm0\n"
"	leaq	32(%rax), %rcx\n"
"	addq	$256, %rdx\n"
"	vpcmpgtd	%ymm3, %ymm1, %ymm2\n"
"	vpblendvb	%ymm2, %ymm1, %ymm0, %ymm0\n"
"	vmovdqa	32(%rax), %ymm1\n"
"	vmovdqa	%ymm0, (%rax)\n"
"	vpxor	-224(%rdx), %ymm1, %ymm0\n"
"	vpcmpgtd	%ymm3, %ymm1, %ymm2\n"
"	vpblendvb	%ymm2, %ymm1, %ymm0, %ymm0\n"
"	vmovdqa	64(%rax), %ymm1\n"
"	vmovdqa	%ymm0, 32(%rax)\n"
"	vpxor	-192(%rdx), %ymm1, %ymm0\n"
"	vpcmpgtd	%ymm3, %ymm1, %ymm2\n"
"	vpblendvb	%ymm2, %ymm1, %ymm0, %ymm0\n"
"	vmovdqa	%ymm0, 64(%rax)\n"
"	vmovdqa	64(%rcx), %ymm1\n"
"	vpxor	-160(%rdx), %ymm1, %ymm0\n"
"	leaq	224(%rcx), %rax\n"
"	vpcmpgtd	%ymm3, %ymm1, %ymm2\n"
"	vpblendvb	%ymm2, %ymm1, %ymm0, %ymm0\n"
"	vmovdqa	96(%rcx), %ymm1\n"
"	vmovdqa	%ymm0, 64(%rcx)\n"
"	vpxor	-128(%rdx), %ymm1, %ymm0\n"
"	vpcmpgtd	%ymm3, %ymm1, %ymm2\n"
"	vpblendvb	%ymm2, %ymm1, %ymm0, %ymm0\n"
"	vmovdqa	128(%rcx), %ymm1\n"
"	vmovdqa	%ymm0, 96(%rcx)\n"
"	vpxor	-96(%rdx), %ymm1, %ymm0\n"
"	vpcmpgtd	%ymm3, %ymm1, %ymm2\n"
"	vpblendvb	%ymm2, %ymm1, %ymm0, %ymm0\n"
"	vmovdqa	160(%rcx), %ymm1\n"
"	vmovdqa	%ymm0, 128(%rcx)\n"
"	vpxor	-64(%rdx), %ymm1, %ymm0\n"
"	vpcmpgtd	%ymm3, %ymm1, %ymm2\n"
"	vpblendvb	%ymm2, %ymm1, %ymm0, %ymm0\n"
"	vmovdqa	192(%rcx), %ymm1\n"
"	vmovdqa	%ymm0, 160(%rcx)\n"
"	vpxor	-32(%rdx), %ymm1, %ymm0\n"
"	vpcmpgtd	%ymm3, %ymm1, %ymm2\n"
"	vpblendvb	%ymm2, %ymm1, %ymm0, %ymm0\n"
"	vmovdqa	%ymm0, 192(%rcx)\n"
"	cmpq	%r9, %rax\n"
"	jne	.myL4\n"
".myL51:\n"
"	movq	%rdi, %rdx\n"
"	andq	$-8, %rdx\n"
"	movq	%rdx, %rax\n"
"	cmpq	%rdx, %rdi\n"
"	je	.myL56\n"
"	vzeroupper\n"
".myL3:\n"
"	movq	%rdi, %rcx\n"
"	subq	%rdx, %rcx\n"
"	leaq	-1(%rcx), %r9\n"
"	cmpq	$2, %r9\n"
"	jbe	.myL8\n"
"	leaq	(%rsi,%rdx,4), %r9\n"
"	vmovd	%r8d, %xmm4\n"
"	leaq	b(%rip), %r10\n"
"	vmovdqa	(%r9), %xmm2\n"
"	vpshufd	$0, %xmm4, %xmm0\n"
"	vpxor	(%r10,%rdx,4), %xmm2, %xmm1\n"
"	movq	%rcx, %rdx\n"
"	andq	$-4, %rdx\n"
"	vpcmpgtd	%xmm0, %xmm2, %xmm0\n"
"	addq	%rdx, %rax\n"
"	vpblendvb	%xmm0, %xmm2, %xmm1, %xmm0\n"
"	vmovdqa	%xmm0, (%r9)\n"
"	cmpq	%rdx, %rcx\n"
"	je	.myL53\n"
".myL8:\n"
"	movl	(%rsi,%rax,4), %edx\n"
"	cmpl	%r8d, %edx\n"
"	jle	.myL57\n"
".myL10:\n"
"	movl	%edx, (%rsi,%rax,4)\n"
"	leaq	1(%rax), %rdx\n"
"	cmpq	%rdx, %rdi\n"
"	jle	.myL53\n"
"	movl	(%rsi,%rdx,4), %ecx\n"
"	cmpl	%ecx, %r8d\n"
"	jl	.myL11\n"
"	leaq	b(%rip), %r9\n"
"	xorl	(%r9,%rdx,4), %ecx\n"
".myL11:\n"
"	addq	$2, %rax\n"
"	movl	%ecx, (%rsi,%rdx,4)\n"
"	cmpq	%rax, %rdi\n"
"	jle	.myL53\n"
"	movl	(%rsi,%rax,4), %edx\n"
"	cmpl	%edx, %r8d\n"
"	jl	.myL13\n"
"	leaq	b(%rip), %rcx\n"
"	xorl	(%rcx,%rax,4), %edx\n"
".myL13:\n"
"	movl	%edx, (%rsi,%rax,4)\n"
"	ret\n"
"	.p2align 4,,10\n"
"	.p2align 3\n"
".myL53:\n"
"	ret\n"
"	.p2align 4,,10\n"
"	.p2align 3\n"
".myL57:\n"
"	leaq	b(%rip), %rcx\n"
"	xorl	(%rcx,%rax,4), %edx\n"
"	jmp	.myL10\n"
"	.p2align 4,,10\n"
"	.p2align 3\n"
".myL55:\n"
"	vmovdqa	(%rsi), %ymm1\n"
"	vpxor	(%rdx), %ymm1, %ymm0\n"
"	leaq	32+a(%rip), %rax\n"
"	leaq	32+b(%rip), %rdx\n"
"	vpcmpgtd	%ymm3, %ymm1, %ymm2\n"
"	vpblendvb	%ymm2, %ymm1, %ymm0, %ymm0\n"
"	vmovdqa	%ymm0, (%rsi)\n"
"	jmp	.myL42\n"
"	.p2align 4,,10\n"
"	.p2align 3\n"
".myL56:\n"
"	vzeroupper\n"
"	ret\n"
".myL14:\n"
"	xorl	%edx, %edx\n"
"	xorl	%eax, %eax\n"
"	leaq	a(%rip), %rsi\n"
"	jmp	.myL3\n"
"	.cfi_endproc\n"
".myLFE9703:\n"
"	.size	_Z2upi, .-_Z2upi\n"
);

int main()
{
	cin.tie(0) -> sync_with_stdio(false);
	int q;
	cin >> n >> q;
	Loop (i,0,n) {
		cin >> a[i] >> b[i];
		b[i] ^= a[i];
	}
	while (q--) {
		int t;
		cin >> t;
		up(t);
	}
	ll ans = 0;
	Loop (i,0,n)
		ans += a[i];
	cout << ans << '\n';
}

Subtask #1
4.0 / 4.0

# 결과 실행 시간 메모리 Grader output
1 Correct 0 ms 212 KB Output is correct
2 Correct 1 ms 212 KB Output is correct
3 Correct 1 ms 212 KB Output is correct
4 Correct 1 ms 340 KB Output is correct
5 Correct 1 ms 212 KB Output is correct
6 Correct 1 ms 340 KB Output is correct
7 Correct 1 ms 212 KB Output is correct
8 Correct 1 ms 340 KB Output is correct
9 Correct 1 ms 340 KB Output is correct
10 Correct 1 ms 212 KB Output is correct
11 Correct 1 ms 340 KB Output is correct
12 Correct 1 ms 340 KB Output is correct
13 Correct 1 ms 340 KB Output is correct

Subtask #2
31.0 / 31.0

# 결과 실행 시간 메모리 Grader output
1 Correct 0 ms 212 KB Output is correct
2 Correct 1 ms 212 KB Output is correct
3 Correct 1 ms 212 KB Output is correct
4 Correct 1 ms 340 KB Output is correct
5 Correct 1 ms 212 KB Output is correct
6 Correct 1 ms 340 KB Output is correct
7 Correct 1 ms 212 KB Output is correct
8 Correct 1 ms 340 KB Output is correct
9 Correct 1 ms 340 KB Output is correct
10 Correct 1 ms 212 KB Output is correct
11 Correct 1 ms 340 KB Output is correct
12 Correct 1 ms 340 KB Output is correct
13 Correct 1 ms 340 KB Output is correct
14 Correct 17 ms 412 KB Output is correct
15 Correct 67 ms 484 KB Output is correct
16 Correct 141 ms 548 KB Output is correct
17 Correct 244 ms 620 KB Output is correct
18 Correct 233 ms 596 KB Output is correct
19 Correct 267 ms 656 KB Output is correct
20 Correct 233 ms 624 KB Output is correct
21 Correct 255 ms 624 KB Output is correct
22 Correct 247 ms 628 KB Output is correct
23 Correct 234 ms 596 KB Output is correct
24 Correct 231 ms 524 KB Output is correct
25 Correct 246 ms 620 KB Output is correct
26 Correct 201 ms 468 KB Output is correct
27 Correct 236 ms 624 KB Output is correct
28 Correct 239 ms 620 KB Output is correct
29 Correct 237 ms 620 KB Output is correct

Subtask #3
0 / 65.0

# 결과 실행 시간 메모리 Grader output
1 Correct 0 ms 212 KB Output is correct
2 Correct 1 ms 212 KB Output is correct
3 Correct 1 ms 212 KB Output is correct
4 Correct 1 ms 340 KB Output is correct
5 Correct 1 ms 212 KB Output is correct
6 Correct 1 ms 340 KB Output is correct
7 Correct 1 ms 212 KB Output is correct
8 Correct 1 ms 340 KB Output is correct
9 Correct 1 ms 340 KB Output is correct
10 Correct 1 ms 212 KB Output is correct
11 Correct 1 ms 340 KB Output is correct
12 Correct 1 ms 340 KB Output is correct
13 Correct 1 ms 340 KB Output is correct
14 Correct 17 ms 412 KB Output is correct
15 Correct 67 ms 484 KB Output is correct
16 Correct 141 ms 548 KB Output is correct
17 Correct 244 ms 620 KB Output is correct
18 Correct 233 ms 596 KB Output is correct
19 Correct 267 ms 656 KB Output is correct
20 Correct 233 ms 624 KB Output is correct
21 Correct 255 ms 624 KB Output is correct
22 Correct 247 ms 628 KB Output is correct
23 Correct 234 ms 596 KB Output is correct
24 Correct 231 ms 524 KB Output is correct
25 Correct 246 ms 620 KB Output is correct
26 Correct 201 ms 468 KB Output is correct
27 Correct 236 ms 624 KB Output is correct
28 Correct 239 ms 620 KB Output is correct
29 Correct 237 ms 620 KB Output is correct
30 Correct 302 ms 340 KB Output is correct
31 Correct 1444 ms 708 KB Output is correct
32 Correct 2956 ms 1108 KB Output is correct
33 Execution timed out 3057 ms 6856 KB Time limit exceeded
34 Halted 0 ms 0 KB -