HDU 2971 Tower (矩阵快速幂)

对于一个数列

求前n相的平方和

设

可得到

对于前n相和 

可以发现重复项和

可得

根据得到的不变项可得

需要注意将负数加mod取模之后处理成正数

数据很大  连续取mod可能超时

#include <cstdio>
#include <iostream>
#include <algorithm>
#include <cstdlib>
#include <cmath>
#include <string>
#include <cstring>
#include <string.h>
#include <vector>
#include <set>
#include <map>
#include <queue>
#include <stack>

using namespace std;
#define sp system("pause")

typedef long long ll;
typedef pair<int, int> pii;

ll mod;

struct Matrix
{
	ll m[5][5];
	int size;
	void E()
	{
		for (int i = 0; i < 5; i++)for (int j = 0; j < 5; j++)m[i][j] = (i == j ? 1 : 0);
	}
	void clear()
	{
		for (int i = 0; i < 5; i++)for (int j = 0; j < 5; j++)m[i][j] = 0;
	}
	Matrix operator*(Matrix &x)
	{
		Matrix res;
		res.size = x.size;
		res.clear();
		for (int i = 0; i < x.size; i++)
		{
			for (int j = 0; j < x.size; j++)
			{
				res.m[i][j] = 0;
				for (int k = 0; k < x.size; k++)
				{
					res.m[i][j] += (m[i][k] * x.m[k][j]) % mod;
				}
				res.m[i][j] %= mod;
			}
		}
		return res;
	}
	Matrix operator^(ll plus)
	{
		Matrix res;
		res.E();
		res.size = size;
		Matrix a = *this;
		while (plus)
		{
			if (plus & 1)res = res*a;
			a = a*a;
			plus >>= 1;
		}
		return res;
	}
	void to()
	{
		for (int i = 0; i < 5; i++)for (int j = 0; j < 5; j++)m[i][j] = (m[i][j] + mod) % mod;
	}
};

int main()
{
	int T;
	cin >> T;
	while (T--)
	{
		ll p, n;
		scanf("%lld%lld%lld", &p, &n, &mod);
		ll to2 = p;
		Matrix b;
		p <<= 1;
		p %= mod;
		b.size = 4;
		b.clear();
		b.m[0][0] = 1;
		b.m[0][1] = p*p%mod;
		b.m[0][2] = 1;
		b.m[0][3] = ((-p + mod) % mod) * 2 % mod;
		b.m[1][0] = 0;
		b.m[1][1] = b.m[0][1];
		b.m[1][2] = b.m[0][2];
		b.m[1][3] = b.m[0][3];
		b.m[2][0] = b.m[2][2] = b.m[2][3] = 0;
		b.m[2][1] = 1;
		b.m[3][0] = b.m[3][2]=0;
		b.m[3][1] = p;
		b.m[3][3] = (-1 + mod) % mod;
		Matrix ans;
		ans.size = 4;
		ans.clear();
		if (n <= 2)
		{
			ll aa = 0;
			if (n == 1)
			{
				puts("1");
			}
			else if (n == 2)
			{
				printf("%lld\n", (1 + (to2)*(to2)) % mod);
			}
		}
		else
		{
			n -= 2;
			ans.m[0][0] = (1 + to2*to2) % mod;
			ans.m[1][0] = (to2*to2) % mod;
			ans.m[2][0] = 1;
			ans.m[3][0] = (to2);
			b = b^n;
			ans = b*ans;
			printf("%lld\n", ans.m[0][0]);
		}
	}
}