#include <bits/stdc++.h>

using namespace std;

typedef long long ll;
typedef vector<int> vi;
typedef vector<ll> vl;
typedef pair<int,int> pii;
typedef pair<ll,ll> pll;

typedef int _loop_int;
#define REP(i,n) for(_loop_int i=0;i<(_loop_int)(n);++i)
#define FOR(i,a,b) for(_loop_int i=(_loop_int)(a);i<(_loop_int)(b);++i)
#define FORR(i,a,b) for(_loop_int i=(_loop_int)(b)-1;i>=(_loop_int)(a);--i)

#define DEBUG(x) cout<<#x<<": "<<x<<endl
#define DEBUG_VEC(v) cout<<#v<<":";REP(i,v.size())cout<<" "<<v[i];cout<<endl
#define ALL(a) (a).begin(),(a).end()

#define CHMIN(a,b) a=min((a),(b))
#define CHMAX(a,b) a=max((a),(b))

#define rsh 31
#define r (1ll<<31)
#define rmsk (r-1ll)

ll n,m;
ll r2, mm;
ll m4;

ll calc_mm(){
  ll res = 0;
  ll t = 0;
  ll rr = r;
  ll i = 1;
  while(rr > 1){
    if(!(t%2)){
      t += m;
      res += i;
    }
    t /= 2;
    rr /= 2;
    i *= 2;
  }
  return res;
}

inline ll MR(ll x){
  ll t = (x + ((x * mm) & rmsk)*m) >> rsh;
  return t<m ? t : t-m;
}

#define f(x) ((x)*((x)+4ll)%m)

int floyd_cycle_algorithm(ll init){
  int mu = 0;
  init = MR(r2 * init);
  ll x = init;
  do {
    mu++;
    x = MR(x*(x+m4));
  }while(x!=init);
  return mu;
}

ll naive(ll x, ll n){
  x = MR(r2 * x);
  while(n--){
    x = MR(x*(x+m4));
  }
  return MR(x);
}

int main(){
  cin>>n>>m;
  if(m == 2){
    cout<<0<<endl;
    return 0;
  }
  // montgomery
  r2 = r*r%m;
  mm = calc_mm();
  m4 = MR(r2 * 4);

  // solve
  if(n < 100){
    cout<<naive(2,n)<<endl;
    return 0;
  }
  ll x = naive(2,100);
  n -= 100;
  int mu = floyd_cycle_algorithm(x);
  n %= mu;
  x = naive(x,n);
  cout<<x<<endl;
  return 0;
}