<![CDATA[Geschwindigkeit von STL numerics]]>Hallo,
ich habe zwei Funktionen verglichen, die mir den Korrelationskoeffizienten zweier Zahlenlisten berechnen. Die eine benutzt STL-Funktionen, die andere berechnet die benoetigten Summen "von Hand". Bei einer Listenlaenge von je 1000000 double's:x
benoetigt die STL-Version 130000 clock ticks waehrend die "von Hand" Version nur 70000 benoetigt (kompiliert mit g++ -O2 -march=k6 test.cpp).

Kann mir jemand erklaeren, woran das liegt? Ich haette erwartet, dass die STL vergleichbar, wenn nicht gar schneller waere. Hier der Code:

#include <iostream>
#include <numeric>
#include <cmath>
#include <vector>
#include <time.h>

// compare two versions of calculating correlation coefficients
// using STL functions
template <typename T> T CC_stl(const std::vector<T>& l1,
                               const std::vector<T>& l2)
{
    T corr_coefficient;
    T sum1, sum1_sq, sum2, sum2_sq, sum12;
    T nominator;
    T denominator;

    int list_size = l1.size();

    sum1    = std::accumulate(l1.begin(), l1.end(), 0.0);
    sum2    = std::accumulate(l2.begin(), l2.end(), 0.0);
    sum1_sq = std::inner_product(l1.begin(), l1.end(), l1.begin(), 0.0);
    sum2_sq = std::inner_product(l2.begin(), l2.end(), l2.begin(), 0.0);
    sum12   = std::inner_product(l1.begin(), l1.end(), l2.begin(), 0.0);

    nominator   = sum12 - sum1*sum2/list_size;
    denominator =   (sum1_sq - sum1*sum1/list_size)
        * (sum2_sq - sum2*sum2/list_size);
    corr_coefficient = nominator / std::sqrt(denominator);
    return corr_coefficient;
}

// manual calculation
template <typename T> T CC(const std::vector<T>& l1, const std::vector<T>& l2)
{
    T corr_coefficient;
    T sum1, sum1_sq, sum2, sum2_sq, sum12;
    T nominator;
    T denominator;

    sum1 = sum2 = sum1_sq = sum2_sq = sum12 = 0;

    int list_size = l1.size();

    for ( int i = 0; i < list_size; i++)
    {
        sum1    += l1[i];
        sum2    += l2[i];
        sum1_sq += l1[i]*l1[i];
        sum2_sq += l2[i]*l2[i];
        sum12   += l1[i]*l2[i];
    }

    nominator   = sum12 - 1.0*sum1/list_size * sum2;
    denominator = (sum1_sq - 1.0/list_size * sum1*sum1) *
                  (sum2_sq - 1.0/list_size * sum2*sum2);

    corr_coefficient = nominator / std::sqrt(denominator);
    return corr_coefficient;
}

int main()
{
    const unsigned int points = 1000000;
    std::vector<double> l1(points), l2(points);

    clock_t stl0, stl1, std0, std1;

    // populate both vectors with numbers
    for ( int i = 0; i < points; i++)
    {
        l1[i] = std::sqrt(1.0*i);
        l2[i] = 1.0/(i+1);
    }

    stl0 = clock();
    double cc_stl = CC_stl(l1, l2);
    stl1 = clock();

    std0 = clock();
    double cc_std = CC(l1, l2);
    std1 = clock();

    std::cout << " STL Version:    " << cc_stl << " clocks: "
              << stl1 - stl0 << '\n'
              << " Normal Version: " << cc_std << " clocks: "
              << std1 - std0 << '\n';

    return 0;
}

Vielen Dank,

Tim

]]>https://www.c-plusplus.net/forum/topic/122499/geschwindigkeit-von-stl-numericsRSS for NodeSun, 23 Aug 2026 01:41:43 GMTThu, 06 Oct 2005 12:32:45 GMT60<![CDATA[Reply to Geschwindigkeit von STL numerics on Thu, 06 Oct 2005 12:32:45 GMT]]>Hallo,
ich habe zwei Funktionen verglichen, die mir den Korrelationskoeffizienten zweier Zahlenlisten berechnen. Die eine benutzt STL-Funktionen, die andere berechnet die benoetigten Summen "von Hand". Bei einer Listenlaenge von je 1000000 double's:x
benoetigt die STL-Version 130000 clock ticks waehrend die "von Hand" Version nur 70000 benoetigt (kompiliert mit g++ -O2 -march=k6 test.cpp).

Kann mir jemand erklaeren, woran das liegt? Ich haette erwartet, dass die STL vergleichbar, wenn nicht gar schneller waere. Hier der Code:

#include <iostream>
#include <numeric>
#include <cmath>
#include <vector>
#include <time.h>

// compare two versions of calculating correlation coefficients
// using STL functions
template <typename T> T CC_stl(const std::vector<T>& l1,
                               const std::vector<T>& l2)
{
    T corr_coefficient;
    T sum1, sum1_sq, sum2, sum2_sq, sum12;
    T nominator;
    T denominator;

    int list_size = l1.size();

    sum1    = std::accumulate(l1.begin(), l1.end(), 0.0);
    sum2    = std::accumulate(l2.begin(), l2.end(), 0.0);
    sum1_sq = std::inner_product(l1.begin(), l1.end(), l1.begin(), 0.0);
    sum2_sq = std::inner_product(l2.begin(), l2.end(), l2.begin(), 0.0);
    sum12   = std::inner_product(l1.begin(), l1.end(), l2.begin(), 0.0);

    nominator   = sum12 - sum1*sum2/list_size;
    denominator =   (sum1_sq - sum1*sum1/list_size)
        * (sum2_sq - sum2*sum2/list_size);
    corr_coefficient = nominator / std::sqrt(denominator);
    return corr_coefficient;
}

// manual calculation
template <typename T> T CC(const std::vector<T>& l1, const std::vector<T>& l2)
{
    T corr_coefficient;
    T sum1, sum1_sq, sum2, sum2_sq, sum12;
    T nominator;
    T denominator;

    sum1 = sum2 = sum1_sq = sum2_sq = sum12 = 0;

    int list_size = l1.size();

    for ( int i = 0; i < list_size; i++)
    {
        sum1    += l1[i];
        sum2    += l2[i];
        sum1_sq += l1[i]*l1[i];
        sum2_sq += l2[i]*l2[i];
        sum12   += l1[i]*l2[i];
    }

    nominator   = sum12 - 1.0*sum1/list_size * sum2;
    denominator = (sum1_sq - 1.0/list_size * sum1*sum1) *
                  (sum2_sq - 1.0/list_size * sum2*sum2);

    corr_coefficient = nominator / std::sqrt(denominator);
    return corr_coefficient;
}

int main()
{
    const unsigned int points = 1000000;
    std::vector<double> l1(points), l2(points);

    clock_t stl0, stl1, std0, std1;

    // populate both vectors with numbers
    for ( int i = 0; i < points; i++)
    {
        l1[i] = std::sqrt(1.0*i);
        l2[i] = 1.0/(i+1);
    }

    stl0 = clock();
    double cc_stl = CC_stl(l1, l2);
    stl1 = clock();

    std0 = clock();
    double cc_std = CC(l1, l2);
    std1 = clock();

    std::cout << " STL Version:    " << cc_stl << " clocks: "
              << stl1 - stl0 << '\n'
              << " Normal Version: " << cc_std << " clocks: "
              << std1 - std0 << '\n';

    return 0;
}

Vielen Dank,

Tim

]]>https://www.c-plusplus.net/forum/post/886392https://www.c-plusplus.net/forum/post/886392Thu, 06 Oct 2005 12:32:45 GMT<![CDATA[Reply to Geschwindigkeit von STL numerics on Thu, 06 Oct 2005 12:53:02 GMT]]>Bei der handgeschriebenen Variante machst du ja alles in einer Schleife und in der STL müssen ja 5 mal der ganze Vektor durchlaufen werden?!

]]>https://www.c-plusplus.net/forum/post/886407https://www.c-plusplus.net/forum/post/886407Thu, 06 Oct 2005 12:53:02 GMT<![CDATA[Reply to Geschwindigkeit von STL numerics on Thu, 06 Oct 2005 13:17:07 GMT]]>ich hab mal den source genommen und bei mir kompiliert, folgende ergebnisse:

STL Version: -0.0251371 clocks: 234
Normal Version: -0.0251371 clocks: 282

STL Version: -0.0251371 clocks: 250
Normal Version: -0.0251371 clocks: 266

STL Version: -0.0251371 clocks: 234
Normal Version: -0.0251371 clocks: 282

STL Version: -0.0251371 clocks: 234
Normal Version: -0.0251371 clocks: 266

STL Version: -0.0251371 clocks: 234
Normal Version: -0.0251371 clocks: 282

STL Version: -0.0251371 clocks: 250
Normal Version: -0.0251371 clocks: 266

STL Version: -0.0251371 clocks: 250
Normal Version: -0.0251371 clocks: 266

STL Version: -0.0251371 clocks: 234
Normal Version: -0.0251371 clocks: 282

STL Version: -0.0251371 clocks: 235
Normal Version: -0.0251371 clocks: 281

bei mir ist die "handmade" also bissl langsamer.
habs einfach mit dem aktuellen dev-cpp und standard compiler-einstellungen kompiliert.

]]>https://www.c-plusplus.net/forum/post/886425https://www.c-plusplus.net/forum/post/886425Thu, 06 Oct 2005 13:17:07 GMT