#47304 (C++11) No.67 よくある棒を切る問題 (1)

提出ソース

結果

問題	No.67 よくある棒を切る問題 (1)
ユーザー	anta
提出日時	2015-09-04 16:13:49
言語	C++11 (gcc 11.4.0)
結果	RE
実行時間	-
コード長	4,885 bytes
コンパイル時間	621 ms
コンパイル使用メモリ	83,252 KB
実行使用メモリ	6,948 KB
最終ジャッジ日時	2024-07-18 23:43:19
合計ジャッジ時間	5,341 ms
ジャッジサーバーID （参考情報）	judge5 / judge3

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	RE	-
testcase_01	AC	2 ms 6,944 KB
testcase_02	RE	-
testcase_03	RE	-
testcase_04	RE	-
testcase_05	RE	-
testcase_06	RE	-
testcase_07	RE	-
testcase_08	RE	-
testcase_09	RE	-
testcase_10	RE	-
testcase_11	RE	-
testcase_12	RE	-
testcase_13	RE	-
testcase_14	RE	-
testcase_15	RE	-
testcase_16	RE	-
testcase_17	RE	-
testcase_18	RE	-
testcase_19	RE	-
testcase_20	RE	-
testcase_21	RE	-
testcase_22	RE	-
testcase_23	RE	-
testcase_24	AC	1 ms 6,940 KB
testcase_25	AC	2 ms 6,944 KB
testcase_26	AC	2 ms 6,940 KB
testcase_27	AC	1 ms 6,944 KB
testcase_28	RE	-
testcase_29	AC	5 ms 6,944 KB
testcase_30	AC	3 ms 6,944 KB

権限があれば一括ダウンロードができます

コンパイルメッセージ

main.cpp: In function ‘int main()’:
main.cpp:187:30: warning: ignoring return value of ‘int scanf(const char*, ...)’ declared with attribute ‘warn_unused_result’ [-Wunused-result]
  187 |                         scanf("%d", &A);
      |                         ~~~~~^~~~~~~~~~
main.cpp:191:22: warning: ignoring return value of ‘int scanf(const char*, ...)’ declared with attribute ‘warn_unused_result’ [-Wunused-result]
  191 |                 scanf("%lld", &K);
      |                 ~~~~~^~~~~~~~~~~~

ソースコード

raw source code

#include <string>
#include <vector>
#include <algorithm>
#include <numeric>
#include <set>
#include <map>
#include <queue>
#include <iostream>
#include <sstream>
#include <cstdio>
#include <cmath>
#include <ctime>
#include <cstring>
#include <cctype>
#include <cassert>
#include <limits>
#include <functional>

#ifdef MY_LOCAL_RUN
#include <immintrin.h>
#endif

#define rep(i,n) for(int (i)=0;(i)<(int)(n);++(i))
#define rer(i,l,u) for(int (i)=(int)(l);(i)<=(int)(u);++(i))
#define reu(i,l,u) for(int (i)=(int)(l);(i)<(int)(u);++(i))
#if defined(_MSC_VER) || __cplusplus > 199711L
#define aut(r,v) auto r = (v)
#else
#define aut(r,v) __typeof(v) r = (v)
#endif
#define each(it,o) for(aut(it, (o).begin()); it != (o).end(); ++ it)
#define all(o) (o).begin(), (o).end()
#define pb(x) push_back(x)
#define mp(x,y) make_pair((x),(y))
#define mset(m,v) memset(m,v,sizeof(m))
#define INF 0x3f3f3f3f
#define INFL 0x3f3f3f3f3f3f3f3fLL
using namespace std;
typedef vector<int> vi; typedef pair<int,int> pii; typedef vector<pair<int,int> > vpii; typedef long long ll;
template<typename T, typename U> inline void amin(T &x, U y) { if(y < x) x = y; }
template<typename T, typename U> inline void amax(T &x, U y) { if(x < y) x = y; }

const double *g_A;
int g_N;
double g_s_inv;
long long g_res;

#ifdef MY_LOCAL_RUN
extern "C" void sum_trunc_mul();
__declspec(noinline) void sum_trunc_mul() {
	const double *A = g_A;
	int N = g_N;
	double s_inv = g_s_inv;

	__m256d inv = _mm256_set1_pd(s_inv);
	int i = 0;
	__m256d sum = _mm256_setzero_pd();
	for(; i + 3 < N; i += 4) {
		__m256d a_d = _mm256_load_pd(A + i);
		__m256d prod = _mm256_mul_pd(a_d, inv);
		__m256d truncated = _mm256_round_pd(prod, (_MM_FROUND_TO_ZERO |_MM_FROUND_NO_EXC));
		sum = _mm256_add_pd(sum, truncated);
	}
	double sum4[4];
	_mm256_storeu_pd(sum4, sum);
	long long res = 0;
	rep(k, 4) res += (ll)sum4[k];
	for(; i < N; ++ i)
		res += (ll)(A[i] * s_inv);

	g_res = res;
}
#else
extern "C" void sum_trunc_mul();
__asm(
"\n"
".text\n"
"sum_trunc_mul:\n"
".L_FB3893:\n"
"	pushq	%rbp\n"
"	movq	%rsp, %rbp\n"
"	subq	$112, %rsp\n"
"	subq	$352, %rsp\n"
"	movq	%rsp, %rax\n"
"	addq	$31, %rax\n"
"	shrq	$5, %rax\n"
"	salq	$5, %rax\n"
"	movq	g_A(%rip), %rdx\n"
"	movq	%rdx, -32(%rbp)\n"
"	movl	g_N(%rip), %edx\n"
"	movl	%edx, -36(%rbp)\n"
"	movq	g_s_inv(%rip), %rdx\n"
"	movq	%rdx, -48(%rbp)\n"
"	movq	-48(%rbp), %rdx\n"
"	movq	%rdx, -56(%rbp)\n"
"	vbroadcastsd	-56(%rbp), %ymm0\n"
"	vmovapd	%ymm0, 256(%rax)\n"
"	movl	$0, -4(%rbp)\n"
"	vxorpd	%xmm0, %xmm0, %xmm0\n"
"	vmovapd	%ymm0, 288(%rax)\n"
"	jmp	.L_6\n"
".L_10:\n"
"	movl	-4(%rbp), %edx\n"
"	movslq	%edx, %rdx\n"
"	leaq	0(,%rdx,8), %rcx\n"
"	movq	-32(%rbp), %rdx\n"
"	addq	%rcx, %rdx\n"
"	movq	%rdx, -64(%rbp)\n"
"	movq	-64(%rbp), %rdx\n"
"	vmovapd	(%rdx), %ymm0\n"
"	vmovapd	%ymm0, 224(%rax)\n"
"	vmovapd	224(%rax), %ymm0\n"
"	vmovapd	%ymm0, 128(%rax)\n"
"	vmovapd	256(%rax), %ymm0\n"
"	vmovapd	%ymm0, 96(%rax)\n"
"	vmovapd	128(%rax), %ymm0\n"
"	vmulpd	96(%rax), %ymm0, %ymm0\n"
"	vmovapd	%ymm0, 192(%rax)\n"
"	vroundpd	$11, 192(%rax), %ymm0\n"
"	vmovapd	%ymm0, 160(%rax)\n"
"	vmovapd	288(%rax), %ymm0\n"
"	vmovapd	%ymm0, 64(%rax)\n"
"	vmovapd	160(%rax), %ymm0\n"
"	vmovapd	%ymm0, 32(%rax)\n"
"	vmovapd	64(%rax), %ymm0\n"
"	vaddpd	32(%rax), %ymm0, %ymm0\n"
"	vmovapd	%ymm0, 288(%rax)\n"
"	addl	$4, -4(%rbp)\n"
".L_6:\n"
"	movl	-4(%rbp), %edx\n"
"	addl	$3, %edx\n"
"	cmpl	-36(%rbp), %edx\n"
"	jl	.L_10\n"
"	leaq	-112(%rbp), %rdx\n"
"	movq	%rdx, -72(%rbp)\n"
"	vmovapd	288(%rax), %ymm0\n"
"	vmovapd	%ymm0, (%rax)\n"
"	movq	-72(%rbp), %rdx\n"
"	vmovapd	(%rax), %ymm0\n"
"	vmovupd	%ymm0, (%rdx)\n"
"	movq	$0, -16(%rbp)\n"
"	movl	$0, -20(%rbp)\n"
"	jmp	.L_11\n"
".L_12:\n"
"	movl	-20(%rbp), %eax\n"
"	cltq\n"
"	movq	-112(%rbp,%rax,8), %rax\n"
"	vmovq	%rax, %xmm1\n"
"	vcvttsd2siq	%xmm1, %rax\n"
"	addq	%rax, -16(%rbp)\n"
"	addl	$1, -20(%rbp)\n"
".L_11:\n"
"	cmpl	$3, -20(%rbp)\n"
"	jle	.L_12\n"
"	jmp	.L_13\n"
".L_14:\n"
"	movl	-4(%rbp), %eax\n"
"	cltq\n"
"	leaq	0(,%rax,8), %rdx\n"
"	movq	-32(%rbp), %rax\n"
"	addq	%rdx, %rax\n"
"	movq	(%rax), %rax\n"
"	vmovq	%rax, %xmm2\n"
"	vmulsd	-48(%rbp), %xmm2, %xmm0\n"
"	vcvttsd2siq	%xmm0, %rax\n"
"	addq	%rax, -16(%rbp)\n"
"	addl	$1, -4(%rbp)\n"
".L_13:\n"
"	movl	-4(%rbp), %eax\n"
"	cmpl	-36(%rbp), %eax\n"
"	jl	.L_14\n"
"	movq	-16(%rbp), %rax\n"
"	movq	%rax, g_res(%rip)\n"
"	movq	%rbp, %rsp\n"
"	popq	%rbp\n"
"	ret\n"
);

#endif

int main() {
	int N;
	while(~scanf("%d", &N)) {
		vector<double> A_d(N);
		rep(i, N) {
			int A;
			scanf("%d", &A);
			A_d[i] = A;
		}
		long long K;
		scanf("%lld", &K);
		const double EPS = 1e-9;
		double l = 0, u = 1e9;
		while(l + EPS < u && l * (1 + EPS) < u) {
			double mid = (l + u) / 2;
			double inv = 1. / mid;
			g_A = &A_d[0], g_N = N, g_s_inv = inv;
			sum_trunc_mul();
			long long sum = g_res;
			if(sum >= K) l = mid; else u = mid;
		}
		printf("%.10f\n", (l + u) / 2);
	}
	return 0;
}

yukicoder

結果

テストケース

コンパイルメッセージ

ソースコード