#include<bits/stdc++.h>
#include<atcoder/all>
using namespace std;
using namespace atcoder;
typedef long long int ll;
typedef long double ld;
typedef vector<ll> vi;
typedef vector<vi> vvi;
typedef vector<vvi> vvvi;
typedef vector<vvvi> vvvvi;
typedef vector<bool> vb;
typedef vector<vb> vvb;
typedef vector<vvb> vvvb;
typedef vector<vvvb> vvvvb;
typedef pair<ll,ll> pi;
typedef pair<ll,pi> ppi;
typedef pair<ll,ppi> pppi;
typedef pair<ll,pppi> ppppi;
#define FOR(i,l,r) for(ll i=l;i<r;i++)
#define REP(i,n) FOR(i,0,n)
#define RFOR(i,l,r) for(ll i=r-1;i>=l;i--)
#define RREP(i,n) RFOR(i,0,n)
#define ALL(x) x.begin(),x.end()
#define F first
#define S second
#define BS(A,x) binary_search(ALL(A),x)
#define LB(A,x) (ll)(lower_bound(ALL(A),x)-A.begin())
#define UB(A,x) (ll)(upper_bound(ALL(A),x)-A.begin())
#define COU(A,x) (UB(A,x)-LB(A,x))
#define sz(c) ((ll)(c).size())
/*
#include<boost/multiprecision/cpp_int.hpp>
namespace mp=boost::multiprecision;
using Bint=mp::cpp_int;
*/
template<typename T>using min_priority_queue=priority_queue<T,vector<T>,greater<T>>;
template<typename T1,typename T2>ostream&operator<<(ostream&os,pair<T1,T2>p){os<<p.F<<" "<<p.S;return os;}
template<typename T1,typename T2>istream&operator>>(istream&is,pair<T1,T2>&p){is>>p.F>>p.S;return is;}
template<typename T>ostream&operator<<(ostream&os,vector<T>v){REP(i,sz(v))os<<v[i]<<(i+1!=sz(v)?" ":"");return os;}
template<typename T>istream&operator>>(istream&is,vector<T>&v){for(T&in:v)is>>in;return is;}
template<class T>bool chmax(T&a,T b){if(a<b){a=b;return 1;}return 0;}
template<class T>bool chmin(T&a,T b){if(b<a){a=b;return 1;}return 0;}
ld dist(ld x1,ld y1,ld x2,ld y2){return sqrtl((x1-x2)*(x1-x2)+(y1-y2)*(y1-y2));}
vi fast_mod_convolution(vi&a,vi&b,ll mod){
  const ll m1=167772161,m2=469762049,m3=1224736769;
  const ll m1_inv_m2=inv_mod(m1,m2);
  const ll m12_inv_m3=inv_mod(m1*m2,m3);
  const ll m12_mod=m1*m2%mod;
  auto x=convolution<m1>(a,b);
  auto y=convolution<m2>(a,b);
  auto z=convolution<m3>(a,b);
  vector<ll>ret(sz(a)+sz(b)-1);
  REP(i,sz(ret)){
    ll v1=(y[i]-x[i])*m1_inv_m2%m2;if(v1<0)v1+=m2;
    ll v2=(z[i]-(x[i]+m1*v1)%m3)*m12_inv_m3%m3;if(v2<0)v2+=m3;
  	ret[i]=(x[i]+m1*v1+m12_mod*v2)%mod;
  }
  return ret;
}
const ld EPS=1e-8;
/*
using mint=modint998244353;
const ll mod=998244353;
//*/
/*
using mint=modint1000000007;
const ll mod=1000000007;
//*/
using mint=modint;
//*
typedef vector<mint> vm;
typedef vector<vm> vvm;
typedef vector<vvm> vvvm;
typedef vector<vvvm> vvvvm;
ostream&operator<<(ostream&os,mint a){os<<a.val();return os;}
istream&operator>>(istream&is,mint&a){int x;is>>x;a=mint(x);return is;}
//*/
int main(){
  ll N,P;cin>>N>>P;
  mint::set_mod(P);
  vm ex(2e6,1),re(N);
  FOR(i,1,2e6)ex[i]=ex[i-1]*i;
  REP(i,N)re[i]=1/ex[i];
  vvm DP(N+10,vm(N+10));
  DP[1][0]=1;
  FOR(j,1,N){
  	vi X(N),Y(N);
  	REP(i,N)X[i]=(DP[i][j-1]/j).val();
  	FOR(i,1,N)Y[i]=(pow_mod(i,i-1,P)*re[i]).val();
  	auto Z=fast_mod_convolution(X,Y,P);
  	REP(i,N+1)DP[i][j]=Z[i];
  }
  FOR(i,1,N+1)REP(j,N+1)DP[i][j]*=ex[i-1];
  mint ans=0,s=1;
  FOR(i,1,N+1){
  	s*=N+1-i;
  	if(i<N)s/=i;
  	else s=1;
  	REP(j,N+1)ans+=s*(i==1?pow_mod(i,j,P):pow_mod(i,i+j-2,P))*DP[N+1-i][j];
  }
  cout<<ans<<endl;
  return 0;
}