FWT模板（洛谷P4717）

Fast Walsh-Hadamard Transform，即FWT，用来解决形如一类的卷积，其中⊕表示位运算（xor/or/and）。

参考博客：https://www.cnblogs.com/cjyyb/p/9065615.html

大体结构和FFT、NTT差不多。

代码：

#pragma GCC optimize(2)
#pragma GCC optimize(3)
#pragma GCC optimize(4)
#pragma comment(linker, "/STACK:102400000,102400000")
#include<unordered_map>
#include<unordered_set>
#include<algorithm>
#include<iostream>
#include<fstream>
#include<complex>
#include<cstdlib>
#include<cstring>
#include<cassert>
#include<iomanip>
#include<string>
#include<cstdio>
#include<bitset>
#include<vector>
#include<cctype>
#include<cmath>
#include<ctime>
#include<stack>
#include<queue>
#include<deque>
#include<list>
#include<set>
#include<map>
using namespace std;
#define pt(a) cout<<a<<endl
#define debug test
#define mst(ss,b) memset((ss),(b),sizeof(ss))
#define rep(i,a,n) for (int i=a;i<=n;i++)
#define per(i,a,n) for (int i=n-1;i>=a;i--)
#define all(x) (x).begin(),(x).end()
#define fi first
#define se second
#define SZ(x) ((int)(x).size())
#define ll long long
#define ull unsigned long long
#define pb push_back
#define mp make_pair
#define inf 0x3f3f3f3f
#define eps 1e-10
#define PI acos(-1.0)
typedef pair<int,int> PII;
const ll mod = 998244353;
const int N = 1e6+10;

ll gcd(ll p,ll q){return q==0?p:gcd(q,p%q);}
ll qp(ll a,ll b) {ll res=1;a%=mod; assert(b>=0); for(;b;b>>=1){if(b&1)res=res*a%mod;a=a*a%mod;}return res;}
int to[4][2]={{-1,0},{1,0},{0,-1},{0,1}};

ll n,a[3][N],b[3][N],c[3][N],inv[3];

void FWT(ll *a,int kd,int f){
    for (int k=1;k<n;k<<=1)
        for (int i=0;i<n;i+=(k<<1))
            for (int j=0;j<k;j++){
                ll x=a[i+j],y=a[i+j+k];
                if (kd==0) (a[i+j+k]+=f*x)%=mod;
                else if (kd==1) (a[i+j]+=f*y)%=mod;
                else a[i+j]=(x+y)*inv[3-f>>1]%mod,a[i+j+k]=(x-y)*inv[3-f>>1]%mod;
            }
}

int main() {
    ios::sync_with_stdio(0),cin.tie(0),cout.tie(0);
    cin>>n;
    n=1<<n;
    inv[1]=1,inv[2]=mod>>1|1;
    ll tp;
    for (int i=0; i<n; i++)
        cin>>tp,a[0][i]=a[1][i]=a[2][i]=tp;
    for (int i=0; i<n; i++)
        cin>>tp,b[0][i]=b[1][i]=b[2][i]=tp;
    for (int i=0; i<3; i++)
    {
        FWT(a[i],i,1),FWT(b[i],i,1);
        for (int j=0; j<n; j++)
            c[i][j]=a[i][j]*b[i][j]%mod;
        FWT(c[i],i,-1);
    }
    for (int i=0; i<3; i++)
    {
        for (int j=0; j<n; j++)
            cout<<((c[i][j]+mod)%mod)<<" ";
        cout<<endl;
    }
    return 0;
}