CF620E New Year Tree

CF620E New Year Tree
我爱卡常数~
首先一看：
哇！数颜色（普通莫队），带修（带修莫队），在树上做（树上莫队）
然后你会发现时间复杂度简直是天方夜谭
所以…
你要用DFS序+线段树
但是我总是TLE第51个点
怎么办？
呼叫卡常数国国王！
1.i++写成++i
2.循环里用register int
3.能不开LL就不开LL
4.程序压行
5.while比for好
6.cin优化比scanf快好多（ cin优化：ios::sync_with_stdio(false); ）
啊呀！还是TLE第51个点！
事实上要把dfs改改。
我的dfs是开两倍的
所以时间复杂度会*2

不得了啊！

然后只开一倍就AC了，还跑得不错
std:

#pragma GCC optimize(2)
#pragma GCC optimize(3)
#pragma GCC optimize("Ofast")
#pragma GCC optimize("inline")
#pragma GCC optimize("-fgcse")
#pragma GCC optimize("-fgcse-lm")
#pragma GCC optimize("-fipa-sra")
#pragma GCC optimize("-ftree-pre")
#pragma GCC optimize("-ftree-vrp")
#pragma GCC optimize("-fpeephole2")
#pragma GCC optimize("-ffast-math")
#pragma GCC optimize("-fsched-spec")
#pragma GCC optimize("unroll-loops")
#pragma GCC optimize("-falign-jumps")
#pragma GCC optimize("-falign-loops")
#pragma GCC optimize("-falign-labels")
#pragma GCC optimize("-fdevirtualize")
#pragma GCC optimize("-fcaller-saves")
#pragma GCC optimize("-fcrossjumping")
#pragma GCC optimize("-fthread-jumps")
#pragma GCC optimize("-funroll-loops")
#pragma GCC optimize("-fwhole-program")
#pragma GCC optimize("-freorder-blocks")
#pragma GCC optimize("-fschedule-insns")
#pragma GCC optimize("inline-functions")
#pragma GCC optimize("-ftree-tail-merge")
#pragma GCC optimize("-fschedule-insns2")
#pragma GCC optimize("-fstrict-aliasing")
#pragma GCC optimize("-fstrict-overflow")
#pragma GCC optimize("-falign-functions")
#pragma GCC optimize("-fcse-skip-blocks")
#pragma GCC optimize("-fcse-follow-jumps")
#pragma GCC optimize("-fsched-interblock")
#pragma GCC optimize("-fpartial-inlining")
#pragma GCC optimize("no-stack-protector")
#pragma GCC optimize("-freorder-functions")
#pragma GCC optimize("-findirect-inlining")
#pragma GCC optimize("-fhoist-adjacent-loads")
#pragma GCC optimize("-frerun-cse-after-loop")
#pragma GCC optimize("inline-small-functions")
#pragma GCC optimize("-finline-small-functions")
#pragma GCC optimize("-ftree-switch-conversion")
#pragma GCC optimize("-foptimize-sibling-calls")
#pragma GCC optimize("-fexpensive-optimizations")
#pragma GCC optimize("-funsafe-loop-optimizations")
#pragma GCC optimize("inline-functions-called-once")
#pragma GCC optimize("-fdelete-null-pointer-checks")
#include<iostream>
#include<cstdio>
using namespace std;
const int N=500005;
typedef long long lli;
#define re register
int n,m,col[N],hed[N*2],tal[N*2],nxt[N*2],cnt=0,c[N],ll[N],rr[N],opt=0,k[N];
lli t[N*8];//状压后的值 
bool LZT[N*8];
//root=1
void push_down(int num){
 if(!LZT[num]) return;
 LZT[num<<1]=1,LZT[num<<1|1]=1,t[num<<1]=t[num],t[num<<1|1]=t[num],LZT[num]=0;
}
void addege(int x,int y){
 ++cnt,tal[cnt]=y,nxt[cnt]=hed[x],hed[x]=cnt;
}
void dfs(int x,int father){
 ++opt,ll[x]=opt,k[opt]=x;
 for(int i=hed[x];i;i=nxt[i]){
  int v=tal[i];
  if(v==father) continue;
  dfs(v,x);
 }
 rr[x]=opt;
}
void build(int l,int r,int num){
 if(l==r){
  t[num]=1ll<<col[k[l]],LZT[num]=0;
  return;
 }
 int mid=(l+r)>>1;
 build(l,mid,num<<1);
 build(mid+1,r,num<<1|1);
 t[num]=(t[num<<1]|t[num<<1|1]);
 LZT[num]=0;
} 
void add(int l,int r,int num,int L,int R,int C){
 if(l>=L&&r<=R){
  LZT[num]=1,t[num]=(1ll<<C);
  return;
 }
 push_down(num);
 int mid=(l+r)>>1;
 if(mid>=R) add(l,mid,num<<1,L,R,C);
 else if(mid<L) add(mid+1,r,num<<1|1,L,R,C);
 else add(l,mid,num<<1,L,R,C),add(mid+1,r,num<<1|1,L,R,C);
 t[num]=(t[num<<1]|t[num<<1|1]);
}
lli ask(int l,int r,int num,int L,int R){
 if(l>=L&&r<=R) return t[num];
 push_down(num);
 int mid=(l+r)>>1;
 if(mid>=R) return ask(l,mid,num<<1,L,R);
 if(mid<L) return ask(mid+1,r,num<<1|1,L,R);
 return ask(l,mid,num<<1,L,R)|ask(mid+1,r,num<<1|1,L,R);
}
int nume(lli x){
 int ans=0;
 while(x) x-=(x&(-x)),++ans;
 return ans;
}
int sol(int L,int R){
 return nume(ask(1,n,1,L,R));
}
int main(){
 //Debug();
 scanf("%d%d",&n,&m);
 for(re int i=1;i<=n;++i) scanf("%d",&col[i]);
 for(re int i=1;i<n;++i){
  int a,b;
  scanf("%d%d",&a,&b),addege(a,b),addege(b,a);
 }
 dfs(1,0),n*=2,build(1,n,1);
 while(m--){
  int opt,a,b;
  scanf("%d%d",&opt,&a);
  if(opt==1){
   int L=ll[a],R=rr[a];
   scanf("%d",&b),add(1,n,1,L,R,b);
  }
  else{
   int L=ll[a],R=rr[a];
   printf("%d\n",sol(L,R));
  }
 }
 return 0;
}