代码

#pragma GCC optimize("Ofast")
#pragma GCC target("sse,sse2,sse3,ssse3,sse4")

#include <cstdio>
#include <cmath>
#include <cstring>
#include <cstdlib>
#include <algorithm>
// #include "interactor.h"

const int MAXN = 1e8 + 10;
int n;
unsigned int a[MAXN], b[MAXN];
int bin0[256], bin1[256], bin2[256],bin3[256];

void sort(unsigned int *a, int n) {
	for (int i = 0; i < n; ++i) {
		++bin0[a[i] & 255];
		++bin1[a[i] >> 8 & 255];
		++bin2[a[i] >> 16 & 255];
		++bin3[a[i] >> 24 & 255];
	}

	for (int i = 1; i < 256; ++i) bin0[i] += bin0[i - 1];
	for (int i = 1; i < 256; ++i) bin1[i] += bin1[i - 1];
	for (int i = 1; i < 256; ++i) bin2[i] += bin2[i - 1];
	for (int i = 1; i < 256; ++i) bin3[i] += bin3[i - 1];

	for (int i = n - 1; ~i; --i) b[--bin0[a[i] & 255]] = a[i];
	for (int i = n - 1; ~i; --i) a[--bin1[b[i] >> 8 & 255]] = b[i];
	for (int i = n - 1; ~i; --i) b[--bin2[a[i] >> 16 & 255]] = a[i];
	for (int i = n - 1; ~i; --i) a[--bin3[b[i] >> 24 & 255]] = b[i];
	return;
}

评测结果