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

Latest benchmark:

Found the intersection of 504 values (using unordered_map) 1000 times, in 28827.6ms
Found the intersection of 495 values (using set_intersection) 1000 times, in 9817.69ms
Found the intersection of 504 values (using unordered_set) 1000 times, in 24769.1ms

I think the 504 - 495 difference happens because there are a couple dupe values.

Code:

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

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

#include 

#include "timer.h"

using namespace std;
using namespace stdext;
using namespace boost;
using namespace tr1;


int runIntersectionTest2(const vector& set1, const vector& set2)
{
    // hash_map theMap;
    // map theMap;
    unordered_set theSet;      

     theSet.insert( set1.begin(), set1.end() );

    int intersectionSize = 0;

    vector::const_iterator set2_end = set2.end();

    for ( vector::const_iterator iterator = set2.begin(); iterator != set2_end; ++iterator )
    {
        if ( theSet.find(*iterator) != theSet.end() )
        {
                intersectionSize++;
        }
    }

    return intersectionSize;
}

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

    vector::const_iterator set1_end = set1.end();

    // Now intersect the two sets by populating the map
    for ( vector::const_iterator iterator = set1.begin(); iterator != set1_end; ++iterator )
    {
        int value = *iterator;

        theMap[value] = 1;
    }

    int intersectionSize = 0;

    vector::const_iterator set2_end = set2.end();

    for ( vector::const_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(const vector& set1_unsorted, const vector& set2_unsorted)
{   
    // Create two vectors
    std::vector set1(set1_unsorted.size());
    std::vector set2(set2_unsorted.size());

    // Copy the unsorted data into them
    std::copy(set1_unsorted.begin(), set1_unsorted.end(), set1.begin());
    std::copy(set2_unsorted.begin(), set2_unsorted.end(), set2.begin());

    // Sort the data
    sort(set1.begin(),set1.end());
    sort(set2.begin(),set2.end());

    vector intersection;
    intersection.reserve(1000);

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

    return intersection.size(); 
}

void createSets( vector& set1, vector& set2 )
{
    srand ( time(NULL) );

    set1.reserve(100000);
    set2.reserve(1000);

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

    // Try to get half of our values intersecting
    float ratio = 200000.0f / RAND_MAX;


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

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

    // Make sure set1 is in random order (not sorted)
    random_shuffle(set1.begin(),set1.end());
}

int _tmain(int argc, _TCHAR* argv[])
{
    int intersectionSize = 0;

    vector set1, set2; 
    createSets( set1, set2 );

    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;

    timer.Reset();
    for ( int i = 0; i < 1000; i++ )
    {
        intersectionSize = runIntersectionTest2(set1,set2);
    }
    timer.Stop();

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

    getchar();

    return 0;
}