Fast intersection of sets: C++ vs C#

Question

On my machine (Quad core, 8gb ram), running Vista x64 Business, with Visual Studio 2008 SP1, I am trying to intersect two sets of numbers very quickly.

I\'ve impleme

Answer 1

Update:

I modified the set_intersection code to use vectors, and to sort them (instead of using the sorted set class), and its MUCH faster now:

Found the intersection of 319 values (using unordered_map) 1000 times, in 22187.5ms
Found the intersection of 315 values (using set_intersection) 1000 times, in 2401.62ms

Keep in mind: the larger set is created sorted, so sorting it might not take much time in this example.

C++ Code:

// MapPerformance.cpp : Defines the entry point for the console application.
//

#include "stdafx.h"
#include 
#include 
#include 
#include 
#include 
#include 

#include 

#include "timer.h"

using namespace std;
using namespace stdext;
using namespace boost;

int runIntersectionTest(vector set1, vector set2)
{
    // hash_map theMap;
    // map theMap;
    unordered_map theMap;

    // Now intersect the two sets by populating the map
    for ( vector::iterator iterator = set1.begin(); iterator != set1.end(); iterator++ )
    {
        int value = *iterator;

        theMap[value] = 1;
    }

    int intersectionSize = 0;

    for ( vector::iterator iterator = set2.begin(); iterator != set2.end(); iterator++ )
    {
        int value = *iterator;

        unordered_map::iterator foundValue = theMap.find(value);

        if ( foundValue != theMap.end() )
        {
            theMap[value] = 2;

            intersectionSize++;
        }
    }

    return intersectionSize;

}

int runSetIntersection(vector set1, vector set2)
{   
    sort(set1.begin(),set1.end());
    sort(set2.begin(),set2.end());

    set intersection;

    set_intersection(set1.begin(),set1.end(), set2.begin(), set2.end(), inserter(intersection, intersection.end()));

    return intersection.size(); 
}



int _tmain(int argc, _TCHAR* argv[])
{
    srand ( time(NULL) );

    vector set1;
    vector set2;

    set1.reserve(10000);
    set2.reserve(1000);

    // Create 100,000 values for set1
    for ( int i = 0; i < 100000; i++ )
    {
        int value = 1000000000 + i;
        set1.push_back(value);
    }

    // Create 1,000 values for set2
    for ( int i = 0; i < 1000; i++ )
    {
        int random = rand() % 200000 + 1;
        random *= 10;

        int value = 1000000000 + random;
        set2.push_back(value);
    }

    int intersectionSize = 0;


    Timer timer;
    for ( int i = 0; i < 1000; i++ )
    {
        intersectionSize = runIntersectionTest(set1, set2);
    }
    timer.Stop();

    cout << "Found the intersection of " << intersectionSize << " values (using unordered_map) 1000 times, in " << timer.GetMilliseconds() << "ms" << endl;

    timer.Reset();
    for ( int i = 0; i < 1000; i++ )
    {
        intersectionSize = runSetIntersection(set1,set2);
    }
    timer.Stop();

    cout << "Found the intersection of " << intersectionSize << " values (using set_intersection) 1000 times, in " << timer.GetMilliseconds() << "ms" << endl;

    getchar();

    return 0;
}