深度优先搜索加char缓存｜只需26ms

使用char数组加快输出，达到超快26ms的速度，远远快于平均的100ms以上

#include <iostream>
#include <cstring>  
using namespace std;

int n;
int g[10];
bool flag[10];
char buf[1024]; 
char* p;   


void put_num(int x) {

    for (int i = 0; i < 5; ++i) {
        *p++ = ' ';
    }

    char tmp[6];
    int len = 0;
    if (x == 0) tmp[len++] = '0';
    else {
        while (x > 0) {
            tmp[len++] = x % 10 + '0';
            x /= 10;
        }
    }

    for (int i = 0; i < len; ++i) {
        p[-1 - i] = tmp[len - 1 - i];
    }
}

void dfs(int u) {
    if (u == n + 1) {
        p = buf;
        for (int i = 1; i <= n; ++i) {
            put_num(g[i]);
        }
        *p++ = '\n';

        cout.write(buf, p - buf);
        return;
    }
    for (int i = 1; i <= n; ++i) {
        if (!flag[i]) {
            flag[i] = true;
            g[u] = i;
            dfs(u + 1);
            flag[i] = false;
        }
    }
}

int main() {
    ios::sync_with_stdio(false);
    cin.tie(0);
    cout.tie(0);
    

    char cout_buf[1 << 20];
    cout.rdbuf()->pubsetbuf(cout_buf, sizeof(cout_buf));
    
    cin >> n;
    dfs(1);
    return 0;
}