C++ && Manjaro && Multithread, медленно работает

#include <bits/stdc++.h>
 
#define rep(i, n) for (long long i=0; i<n; i++)
#define eps 1e-9
 
using namespace std;
 
typedef long long ll;
 
 
ll POW(ll a, ll b){
    return (!b?1:b==1?a:b%2?POW(a,b>>1)*POW(a,b>>1)*a:POW(a,b>>1)*POW(a,b>>1));
}
 
 
void oneThread(ll N);
void fourThread(ll N);
void thrFoo(ll strt, ll end, ll &res);
 
set<ll> cubes;
 
int main(){
    ll N, start;
    cin >> N;
    ll cbt = pow(N, 1./3);
    for (ll i=1; i<=cbt; i++) 
        cubes.insert(POW(i, 3));
    start=clock();
    fourThread(N);
    cout << "Four Thread worked at "<< (clock()-start)/1e6 << " seconds" <<  endl;
    start=clock();
    oneThread(N);
    cout << "One Thread worked at "<< (clock()-start)/1e6 << " seconds" <<  endl;
 
    return 0;
}
void oneThread(ll N){
    ll count=0;
    for (ll i=1; i<=N; i++){
        for (auto&cube:cubes){
            if (cubes.find(i-cube)!=cubes.end()){
                count++;
                //cout << i << ' ' << cube << endl;
                break;
            }
        }
    }
    cout << "Result: " << count << endl;
}
void fourThread(ll N){
    ll count=0;
    ll tmpCount1=0, tmpCount2=0, tmpCount3=0, tmpCount4=0;
    ll center = N/2;
    thread thr1(thrFoo, 1, center/2, ref(tmpCount1));
    thread thr2(thrFoo, center/2, center, ref(tmpCount2));
    thread thr3(thrFoo, center, center*3/2, ref(tmpCount3));
    thread thr4(thrFoo, center*3/2, N+1, ref(tmpCount4));
    thr1.join();
    thr2.join();
    thr3.join();
    thr4.join();
    if (1){
        //cout << tmpCount1 << ' ' << tmpCount2 << ' ' << tmpCount3 << ' ' << tmpCount4 << endl;
        count+=tmpCount1+tmpCount2+tmpCount3+tmpCount4;
        cout << "Result: " << count << endl;
    }
}
void thrFoo(ll strt, ll end, ll &res){
    for (ll i=strt; i<end; i++){
        for (auto&cube:cubes){
            if (cubes.find(i-cube)!=cubes.end()){
                res++;
                break;
            }
        }
    }
}