I expected 10 mins to solve this problem but it took 7 mins for the first submission and 8 mins for debugging.

Consider a naive brute force approach, maintaining a priority queue. Each time take out the monster with the highest health, attack, then put it back into the queue. This will lead to a TLE.

We are only concerned about the time when the monster be killed, so the time a monster is killed depends on its health at the last attack. Preprocess each monster’s health: h = (h % k == 0) ? k : h % k

Then do a stable sort on the health array.

// compile: make data
// run: ./data < data.in
#include <bits/stdc++.h>
using namespace std;
#pragma GCC optimize("O3,unroll-loops")
#pragma GCC target("avx2,bmi,bmi2,lzcnt,popcnt")
#ifdef LOCAL
#include <debug/codeforces.h>
#define debug(x...) _debug_print(#x, x);
#define Debug(x...) _debug_print_format(#x, x);
ifstream terminal("/dev/tty");
#define PP cerr<<"\033[1;30mpause...\e[0m",terminal.ignore();
#else
#define debug(x...)
#define Debug(x...)
#define PP
#endif
template<typename...Args> void print_(Args...args){((cout<<args<<" "),...)<<endl;}
#define rep(i,a,b) for(int i=(a);i<(int)(b);++i)
#define sz(v) ((int)(v).size())
#define print(...) print_(__VA_ARGS__);
#define FIND(a, x) ((find(a.begin(),a.end(),(x))!=a.end())?1:0)
#define cmin(x,...) x=min({(x),__VA_ARGS__})
#define cmax(x,...) x=max({(x),__VA_ARGS__})
#define INTMAX (int)(9223372036854775807)
#define INF (int)(1152921504606846976)
#define NaN (int)(0x8b88e1d0595d51d1)
#define double long double
#define int long long
#define uint unsigned long long
#define MAXN 200010

bool cmp(pair<int, int> a, pair<int, int> b) {
    if (a.first == b.first) return a.second < b.second;
    return a.first > b.first;
}

void solve() {
    int n, k; cin >> n >> k;
    vector<pair<int, int>> a;
    rep(i, 0, n) {
        int x; cin >> x;
        a.push_back({((x % k) ? (x % k) : k), i+1});
    }
    sort(a.begin(), a.end(), cmp);
    for (auto [h, id]: a) cout << id << " ";
    cout << endl;
}

int32_t main() {
    ios::sync_with_stdio(false); cin.tie(nullptr); cout.tie(nullptr);

    int _; cin >> _;
    while (_--) solve();

    return 0;
}