#include <bits/stdc++.h>
using namespace std;
const int N = 5e2 + 5;
int n,P;
inline void Plus(int &x,const int &y) { x += y;if(x >= P) x -= P;}
int fac[N * N],ifac[N * N];
inline void init(int n) {
	fac[0] = 1;
	for(int i = 1;i <= n;i++) fac[i] = 1ll * fac[i - 1] * i % P;
	ifac[1] = 1;
	for(int i = 2;i <= n;i++) ifac[i] = 1ll * ifac[P % i] * (P - P / i) % P;
	ifac[0] = 1;
	for(int i = 1;i <= n;i++) ifac[i] = 1ll * ifac[i - 1] * ifac[i] % P;
}
inline int C(int n,int m) { if(n < 0 || m < 0 || n < m) return 0; return 1ll * fac[n] * ifac[m] % P * ifac[n - m] % P;}
inline int E(int n,int m) { return C(n + m - 1,m - 1);}
int Binom[N][N];
int A[N][N],B[N][N];
int main() {
	// freopen("tmp.in","r",stdin);
	// freopen("tmp.out","w",stdout);
	cin >> n >> P;
	init(N * N - 1);
	Binom[0][0] = 1;
	for(int i = 1;i <= n;i++) {
		Binom[i][0] = Binom[i][i] = 1;
		for(int j = 1;j < i;j++)
			Binom[i][j] = (Binom[i - 1][j] + Binom[i - 1][j - 1]) % P;
	}
	for(int i = 1;i <= n;i++)
		for(int j = 1;j <= n;j++)
			A[i][j] = E(n,i * j); // 两维分别有 i,j 个上升段
	for(int i = 1;i <= n;i++)
		for(int j = n;j >= 1;j--)
			for(int k = 1;k < j;k++)
				if((j - k) & 1)
				Plus(A[i][j],P - 1ll * A[i][k] * Binom[j][k] % P);
				else Plus(A[i][j],1ll * A[i][k] * Binom[j][k] % P);
	for(int j = 1;j <= n;j++)
		for(int i = n;i >= 1;i--)
			for(int k = 1;k < i;k++)
				if((i - k) & 1)
				Plus(A[i][j],P - 1ll * A[k][j] * Binom[i][k] % P);
				else Plus(A[i][j],1ll * A[k][j] * Binom[i][k] % P);
	for(int i = 1;i <= n;i++)
		for(int j = 1;j <= n;j++)
			B[n - i][n - j] = A[i][j];
	for(int i = 0;i < n;i++)
		for(int j = 0;j < n;j++)
			for(int k = j + 1;k < n;k++)
				if((k - j) & 1) Plus(B[i][j],P - 1ll * B[i][k] * Binom[k][j] % P);
				else Plus(B[i][j],1ll * B[i][k] * Binom[k][j] % P);
	for(int j = 0;j < n;j++)
		for(int i = 0;i < n;i++)
			for(int k = i + 1;k < n;k++)
				if((k - i) & 1) Plus(B[i][j],P - 1ll * B[k][j] * Binom[k][i] % P);
				else Plus(B[i][j],1ll * B[k][j] * Binom[k][i] % P);
	for(int i = 0;i < n;i++,cout << endl)
		for(int j = 0;j < n;j++)
			cout << B[i][j] << ' ';
	cerr << 1.0 * clock() / CLOCKS_PER_SEC << endl;
	return 0;
}