代码

const int bucket = 256;
const int maxn = 100000005;
unsigned cnt[bucket];
void sort(unsigned *a, int n) {
	unsigned *b = new unsigned[maxn], *tmp;
	for (int move = 0; move < 32; move += 8) {
		//memset(cnt, 0, sizeof cnt);
		for (int j = 0; j < bucket; ++j) cnt[j] = 0;
		for (int j = 0; j < n; ++j) ++cnt[(a[j] >> move) & 0xffu];
		for (int j = 1; j < bucket; ++j) cnt[j] += cnt[j - 1];
		for (int j = n - 1; ~j; --j) b[--cnt[(a[j] >> move) & 0xffu]] = a[j];
		//std::swap(a, b);
		tmp = a, a = b, b = tmp;
	}
}

评测结果