hdu 6057 Kanade's convolution（子集卷积）

#include <iostream>
#include <vector>
#include <cstdio>
using namespace std;
const int MOD = 998244353;
typedef long long LL;
LL mypow(LL a, LL b){
    LL ans = 1; for(; b; b >>= 1) { if(b&1) (ans *= a) %= MOD; (a *= a) %= MOD; } return ans;
}
LL I2 = mypow(2, MOD-2);
const int maxn = (1<<19) + 100;
LL a[maxn], b[maxn], A[21][maxn*4], B[21][maxn*4], C[21][maxn*4];
vector<int> Bit[21];
int m;

class FWT{
public:
    void fwt(LL *a, int n){
        for(int d = 1; d < n; d <<= 1){
            for(int m = d<<1, i = 0; i < n; i += m){
                for(int j = 0; j < d; j++){
                    LL x = a[i+j], y = a[i+j+d];
                    a[i+j] = x+y; if(a[i+j] >= MOD) a[i+j] -= MOD;
                    a[i+j+d] = x-y;   if(a[i+j+d] < 0) a[i+j+d] += MOD;
                }
            }
        }
    }
    void ufwt(LL *a, int n){
        for(int d = 1; d < n; d <<= 1){
            for(int m = d<<1, i = 0; i < n; i += m){
                for(int j = 0; j < d; j++){
                    LL x = a[i+j], y = a[i+j+d];
                    a[i+j] = (x+y)*I2%MOD; a[i+j+d] = (x-y+MOD)*I2%MOD;
                }
            }
        }
    }
    void work(LL *a, LL *b, int n){
        fwt(a, n);
        fwt(b, n);
        for(int i = 0; i < n; i++) a[i] *= b[i];
        ufwt(a, n);
    }
}myfwt;

int bit(int x){
    int ans = 0;
    for(int i = 0; i < 19; i++)
        ans += ((x&(1<<i)) > 0);
    return ans;
}

int main()
{
    for(int i = 0; i < (1<<19); i++) Bit[bit(i)].push_back(i);
    cin>>m;
    for(int i = 0; i < (1<<m); i++) scanf("%d", &a[i]);
    for(int i = 0; i < (1<<m); i++) scanf("%d", &b[i]);
    int L = (1<<m);
    for(int i = 0; i <= m; i++){
        for(auto x : Bit[i]){
            if(x >= L) break;
            A[i][x] = (a[x]*(1<<i))%MOD;
            B[i][x] = b[x];
        }
        myfwt.fwt(A[i], L);
        myfwt.fwt(B[i], L);
    }
    for(int x = 0; x <= m; x++)
        for(int y = 0; y <= x; y++)
            for(int i = 0; i < L; i++)
                (C[x-y][i] += A[y][i]*B[x][i]) %= MOD;
    for(int i = 0; i <= m; i++) myfwt.ufwt(C[i], L);
    LL ans = 0, t = 1;
    for(int i = 0; i < (1<<m); i++){
        (ans += C[bit(i)][i]*t) %= MOD;
        (t *= 1526) %= MOD;
    }
    cout<<ans<<endl;
    return 0;
}