This submission is migrated from previous version of oj.uz, which used different machine for grading. This submission may have different result if resubmitted.
#include <bits/stdc++.h>
#define all(v) v.begin(), v.end()
#define gibon ios::sync_with_stdio(false); cin.tie(0);
#define fi first
#define se second
#define pdd pair<long double, long double>
#define pii pair<int, int>
#define pll pair<ll, ll>
#define ppi pair<pii, pii>
#pragma GCC optimize("O3")
#pragma GCC optimize("Ofast")
#pragma GCC optimize("unroll-loops")
typedef long long ll;
using namespace std;
const int mxN=15003;
const int mxM=10004;
const int MOD=1e9+7;
const ll INF=8e18;
int dx[4]={1, 0, -1, 0}, dy[4]={0, 1, 0, -1};
int N, M, K;
int A[mxN], B[mxN], c[mxN], ci[mxN];
int cnt[mxN], S[mxN];
bitset <15003> X[147000];
bitset <15003> tX, nX;
int ans;
void solv(vector <int> v)
{
    cout << v.size() << '\n';
    priority_queue <pii> pq;
    for(int i=1;i<=N;i++)   pq.emplace(A[i], i);
    for(int x : v)
    {
        cout << B[x] << " ";
        vector <pii> tmp;
        for(int i=0;i<B[x];i++)
        {
            tmp.push_back(pq.top());
            pq.pop();
        }
        for(auto [a, b] : tmp)  cout << b << " ";
        cout << '\n';
        for(auto [a, b] : tmp)  if(a!=1)    pq.emplace(a-1, b);
    }
}
int main()
{
    gibon
    cin >> N;
    for(int i=1;i<=N;i++)   cin >> A[i], K+=A[i];
    for(int i=1;i<=N;i++)   for(int j=1;j<=A[i];j++)    cnt[j]++;
    for(int i=1;i<=K;i++)   S[i]=S[i-1]+cnt[i];
    for(int i=1;i<=K;i++)   c[i]=c[i-1]+K/i;
    cin >> M;
    for(int i=1;i<=M;i++)   cin >> B[i];
    B[M+1]=K+1;
    for(int i=1;i<=M;i++)   if(B[i]<=S[1])  X[i][B[i]]=1;
    for(int i=1;i<=M;i++)   if(X[i][K]) ans=1;
    for(int i=1;i<K;i++)    if(ans==0)
    {
        tX.reset();
        nX.reset();
        for(int j=M;j>=1;j--)
        {
            for(int k=max(0, S[i+1]-B[j+1]+1);k<=S[i+1]-B[j];k++)   tX[k]=1;
            if(B[j]>K/i)    continue;
            nX|=X[c[i-1]+j];
            if(B[j]>K/(i+1))    continue;
            X[c[i]+j]=((nX&tX)<<B[j]);
        }
        //for(int j=0;j<=K;j++)   printf("dp[%d][%d]=(%d, %d)\n", i, j, dp[i][j].fi, dp[i][j].se);
        for(int j=1;j<=M;j++)
        {
            if(B[j]<=K/(i+1) && X[c[i]+j][K]==1)    ans=i+1;
        }
    }
    if(ans==0)
    {
        cout << -1;
        return 0;
    }
    vector <int> v;
    int cur=K;
    for(int i=ans;i>=1;i--)
    {
        int nv=0;
        for(int j=1;j<=M;j++)   if(B[j]<=K/i && X[c[i-1]+j][cur]) nv=j;
        v.push_back(nv);
        cur-=B[nv];
    }
    solv(v);
}
| # | Verdict  | Execution time | Memory | Grader output | 
|---|
| Fetching results... | 
| # | Verdict  | Execution time | Memory | Grader output | 
|---|
| Fetching results... | 
| # | Verdict  | Execution time | Memory | Grader output | 
|---|
| Fetching results... | 
| # | Verdict  | Execution time | Memory | Grader output | 
|---|
| Fetching results... | 
| # | Verdict  | Execution time | Memory | Grader output | 
|---|
| Fetching results... | 
| # | Verdict  | Execution time | Memory | Grader output | 
|---|
| Fetching results... |