【模板】矩阵快速幂

#include <cstdio>
#include <cmath>
#include <cstring>
#include <iostream>
#include <algorithm>

using namespace std;

typedef long long ll;

const int mod = 1e9 + 7;

ll n, k;
ll ans[110][110], a[110][110], b[110][110];

void mul2()
{
    memset(b, 0, sizeof(b));
    for (int i = 1; i <= n; i++)
        for (int j = 1; j <= n; j++)
            for (int k = 1; k <= n; k++)
                b[i][j] = (b[i][j] + ans[i][k] * a[k][j] % mod) % mod;
    memcpy(ans, b, sizeof(b));
}

void mul1()
{
    memset(b, 0, sizeof(b));
    for (int i = 1; i <= n; i++)
        for (int j = 1; j <= n; j++)
            for (int k = 1; k <= n; k++)
                b[i][j] = (b[i][j] + a[i][k] * a[k][j] % mod) % mod;
    memcpy(a, b, sizeof(b));
}

void qpow(ll b)
{
    for (int i = 1; i <= n; i++)
        ans[i][i] = 1;
    while (b)
    {
        if (b & 1)
            mul2();
        mul1();
        b >>= 1;
    }
}

int main()
{
    scanf("%lld%lld", &n, &k);
    for (int i = 1; i <= n; i++)
        for (int j = 1; j <= n; j++)
            scanf("%lld", &a[i][j]);
    qpow(k);
    for (int i = 1; i <= n; i++)
    {
        for (int j = 1; j <= n; j++)
            printf("%lld ", ans[i][j]);
        printf("\n");
    }

    return 0;
}