How to optimize a simple numeric type wrapper class in C++?

Question

I am trying to implement a fixed-point class in C++, but I face problems with performance. I have reduced the problem to a simple wrapper of the float type and it is still slow. My question is - why is the compiler unable optimize it fully?

The 'float' version is 50% faster than 'Float'. Why?!

(I use Visual C++ 2008, all possible compiler's options tested, Release configuration of course).

See the code below:

#include <cstdio>
#include <cstdlib>
#include "Clock.h"      // just for measuring time

#define real Float      // Option 1
//#define real float        // Option 2

struct Float
{
private:
    float value;

public:
    Float(float value) : value(value) {}
    operator float() { return value; }

    Float& operator=(const Float& rhs)
    {
        value = rhs.value;
        return *this;
    }

    Float operator+ (const Float& rhs) const
    {
        return Float( value + rhs.value );
    }

    Float operator- (const Float& rhs) const
    {
        return Float( value - rhs.value );
    }

    Float operator* (const Float& rhs) const
    {
        return Float( value * rhs.value );
    }

    bool operator< (const Float& rhs) const
    {
        return value < rhs.value;
    }
};

struct Point
{
    Point() : x(0), y(0) {}
    Point(real x, real y) : x(x), y(y) {}

    real x;
    real y;
};

int main()
{
    // Generate data
    const int N = 30000;
    Point points[N];
    for (int i = 0; i < N; ++i)
    {
        points[i].x = (real)(640.0f * rand() / RAND_MAX);
        points[i].y = (real)(640.0f * rand() / RAND_MAX);
    }

    real limit( 20 * 20 );

    // Check how many pairs of points are closer than 20
    Clock clk;

    int count = 0;
    for (int i = 0; i < N; ++i)
    {
        for (int j = i + 1; j < N; ++j)
        {
            real dx = points[i].x - points[j].x;
            real dy = points[i].y - points[j].y;
            real d2 = dx * dx + dy * dy;
            if ( d2 < limit )
            {
                count++;
            }
        }
    }

    double time = clk.time();

    printf("%d\n", count);
    printf("TIME: %lf\n", time);

    return 0;
}

Answer 1

IMO, It has to do with optimization flags. I checked your program in g++ linux-64 machine. Without any optimization, it give the same result as you told which 50% less.

With keeping the maximum optimization turned ON (i.e. -O4). Both versions are same. Turn on the optimization and check.