P3803 【模板】多项式乘法（NTT）

传送门

NTT好像是比FFT快了不少

然而感觉不是很看得懂……主要是点值转化为系数表示那里……

upd：大概已经搞明白是个什么玩意儿了……吧……

//minamoto
#include<bits/stdc++.h>
#define R register
#define fp(i,a,b) for(R int i=a,I=b+1;i<I;++i)
#define fd(i,a,b) for(R int i=a,I=b-1;i>I;--i)
#define go(u) for(int i=head[u],v=e[i].v;i;i=e[i].nx,v=e[i].v)
using namespace std;
char buf[1<<21],*p1=buf,*p2=buf;
inline char getc(){return p1==p2&&(p2=(p1=buf)+fread(buf,1,1<<21,stdin),p1==p2)?EOF:*p1++;}
int read(){
    R int res,f=1;R char ch;
    while((ch=getc())>'9'||ch<'0')(ch=='-')&&(f=-1);
    for(res=ch-'0';(ch=getc())>='0'&&ch<='9';res=res*10+ch-'0');
    return res*f;
}
char sr[1<<21],z[20];int C=-1,Z=0;
inline void Ot(){fwrite(sr,1,C+1,stdout),C=-1;}
void print(R int x){
    if(C>1<<20)Ot();if(x<0)sr[++C]='-',x=-x;
    while(z[++Z]=x%10+48,x/=10);
    while(sr[++C]=z[Z],--Z);sr[++C]=' ';
}
const int N=3e6+5,P=998244353,Gi=332748118;
inline int add(R int x,R int y){return x+y>=P?x+y-P:x+y;}
inline int dec(R int x,R int y){return x-y<0?x-y+P:x-y;}
inline int mul(R int x,R int y){return 1ll*x*y-1ll*x*y/P*P;}
int ksm(int x,int y){
    R int res=1;
    for(;y;y>>=1,x=mul(x,x))if(y&1)res=mul(res,x);
    return res;
}
int A[N],B[N],O[N],r[N],lim=1,n,m,l;
void NTT(int *A,int ty){
    fp(i,0,lim-1)if(i<r[i])swap(A[i],A[r[i]]);
    for(R int mid=1;mid<lim;mid<<=1){
        int D=(mid<<1),Wn=ksm(ty==1?3:Gi,(P-1)/D);O[0]=1;
        fp(i,1,mid-1)O[i]=mul(O[i-1],Wn);
        for(R int j=0;j<lim;j+=D){
            for(R int k=0;k<mid;++k){
                int x=A[j+k],y=mul(O[k],A[j+k+mid]);
                A[j+k]=add(x,y),A[j+k+mid]=dec(x,y);
            }
        }
    }
    if(ty==-1)for(R int i=0,inv=ksm(lim,P-2);i<lim;++i)A[i]=mul(A[i],inv);
}
int main(){
//    freopen("testdata.in","r",stdin);
    n=read(),m=read();while(lim<=n+m)lim<<=1,++l;
    fp(i,0,lim-1)r[i]=(r[i>>1]>>1)|((i&1)<<(l-1));
    fp(i,0,n)A[i]=read();fp(i,0,m)B[i]=read();
    NTT(A,1),NTT(B,1);
    fp(i,0,lim-1)A[i]=mul(A[i],B[i]);
    NTT(A,-1);
    fp(i,0,n+m)print(A[i]);return Ot(),0;
}