Getting TLE'd with O(nlogn) (2-sec)

#	User	Rating
1	tourist	4009
2	jiangly	3823
3	Benq	3738
4	Radewoosh	3633
5	jqdai0815	3620
6	orzdevinwang	3529
7	ecnerwala	3446
8	Um_nik	3396
9	ksun48	3390
10	gamegame	3386

#	User	Contrib.
1	cry	166
2	maomao90	163
2	Um_nik	163
4	atcoder_official	161
5	adamant	159
6	-is-this-fft-	158
7	awoo	157
8	TheScrasse	154
9	nor	153
9	Dominater069	153

I cannot figure out why this code is getting TLE'd despite of everything being under order and constraint. I knew those mod operations were costly so I optimized them but still no luck.

Problem : https://codeforces.net/contest/1466/problem/E

Code

//Think simple yet elegant.
#include <bits/stdc++.h>
using namespace std;
#define fast ios::sync_with_stdio(0); cin.tie(0); cout.tie(0);
#define ll  long long
#define all(v) v.begin(),v.end()
#define F first
#define S second
#define pb push_back
#define mp make_pair
#define pi pair<int,int>
#define REP(i,n) for(int i=0;i<n;i++)
const int N = 3e4+10;
const ll mod = 1e9+7;
const int BLOCK_SIZE = 200;


ll mul(ll a,ll b){
	if(a>=mod)
		a%=mod;
	if(b>=mod)
		b%=mod;
	ll xt = a*b;
	if(xt>=mod)
		return (xt)%mod;
	return (xt);
}
ll add(ll a,ll b){
	if((a+b)>=mod)
		return (a+b)%mod;
	return (a+b);
}

void run_case(){
	ll n,i,j,k;

	//<i,j> -> {<j,1>+<j,2>+<j,3>,...............,<j,n>}
	//{<1,1> + <2,1> + .... + <n,1>}-> {1,..|{1,2,...n}}
	cin >> n;
	ll x[n];
	ll C[n][60];
	REP(i,n)
		REP(j,60)
			C[i][j]=0;
	ll col[60];
	memset(col,0,sizeof(col));

	for(i=0;i<n;i++){
		cin >> x[i];
		ll tt = x[i];
		vector<ll> bin;
		while(tt>0){
			bin.pb(tt%2);
			tt/=2;
		}
		for(j=0;j<bin.size();++j){
			C[i][j] = bin[j];
		}

	}
	for(i=0;i<60;i++){
		ll cnt=0;
		for(j=0;j<n;j++)
			cnt+=C[j][i];
		col[i]=cnt;
	}
	ll ans=0;
	for(i=0;i<n;i++){
		ll tt = x[i];
		vector<ll> bin;
		ll O=0,A=0;
		while(tt>0){
			bin.pb(tt%2);
			tt/=2;
		}
		while(bin.size()<60)
			bin.pb(0);
		for(j=0;j<bin.size();++j){
			if(bin[j]==1){
				O = add(O,mul(n,(1LL<<j)));
				A = add(A,mul(col[j],(1LL<<j)));
			}
			else
				O = add(O,mul(col[j],(1LL<<j)));
		}
		ans = add(ans,mul(O,A));
	}
	cout<<ans<<"\n";
}
int main(){
	fast;
	int t;
	cin >> t;
	while(t--){
		run_case();
	}
}

Update-1 : Resolved, It barely passed(1996 ms) after I changed some ll's to ints. Would still like to hear some advice or a good solution though!

Update-2 : The comments are absolute gold thanks guys! Made the necessary changes and made code more concise.

New Code

//Think simple yet elegant.
#include <bits/stdc++.h>
using namespace std;
#define fast ios::sync_with_stdio(0); cin.tie(0); cout.tie(0);
#define ll  long long
#define all(v) v.begin(),v.end()
#define F first
#define S second
#define pb push_back
#define mp make_pair
#define pi pair<int,int>
#define REP(i,n) for(int i=0;i<n;i++)
const int N = 3e4+10;
const ll mod = 1e9+7;
const int BLOCK_SIZE = 200;


ll mul(ll a,ll b){
	if(a>=mod)
		a%=mod;
	if(b>=mod)
		b%=mod;
	if(a*b>=mod)
		return (a*b)%mod;
	return (a*b);
}
ll add(ll a,ll b){
	ll xt = a+b;
	if(xt>=mod)
		return xt-=mod;
	return xt;
}

void run_case(){
	int n,i,j,k;

	//<i,j> -> {<j,1>+<j,2>+<j,3>,...............,<j,n>}
	//{<1,1> + <2,1> + .... + <n,1>}-> {1,..|{1,2,...n}}
	
	cin >> n;
	ll x[n];

	int col[60];
	memset(col,0,sizeof(col));

	for(i=0;i<n;i++){
		cin >> x[i];
		for(j=0;j<60;++j){
			if(x[i]&(1LL<<j))
				++col[j];
		}
	}
	ll ans=0;
	for(i=0;i<n;i++){
		ll O=0,A=0;
		for(j=0;j<60;++j){
			if(x[i]&(1LL<<j)){
				O = add(O,mul(1LL*n,(1LL<<j)));
				A = add(A,mul(1LL*col[j],(1LL<<j)));
			}
			else
				O = add(O,mul(1LL*col[j],(1LL<<j)));
		}
		ans = add(ans,mul(O,A));
	}
	cout<<ans<<"\n";
}
int main(){
	fast;
	int t;
	cin >> t;
	while(t--){
		run_case();
	}
}

GNU C++17(64 bit) -> 453 ms

GNU C++17 ->1263 ms

Would still like to know more on the difference in time on the above 2 compilers.

Thanks!

Rev.	By	When	Δ	Comment
en5	Codeforcer	2021-05-02 15:17:07	1655	Tiny change: '263 ms\n\n<spoil' -> '263 ms\n\n\n\n<spoil'
en4	Codeforcer	2021-05-02 13:45:19	9	Tiny change: 'ely passed after I c' -> 'ely passed(1996 ms) after I c'
en3	Codeforcer	2021-05-02 13:44:38	145	Tiny change: 'oiler>\n\nUpdate : Resolve' -> 'oiler>\n\nUpdate : Resolve'
en2	Codeforcer	2021-05-02 13:28:53	0	(published)
en1	Codeforcer	2021-05-02 13:28:36	2013	Initial revision (saved to drafts)

History