我已经编写了程序，并在 Intel Core i5-2500 上的 Visual Studio 2010 中为 x64 和 x86 平台编译了它。x64 版本执行大约需要 19 秒，x86 大约需要 17 秒。这种行为的原因是什么？
#include "timer.h"
#include <vector>
#include <iostream>
#include <algorithm>
#include <string>
#include <sstream>
/********************DECLARATIONS************************************************/
class Vector
{
public:
Vector():x(0),y(0),z(0){}
Vector(double x, double y, double z)
: x(x)
, y(y)
, z(z)
{
}
double x;
double y;
double z;
};
double Dot(const Vector& a, const Vector& b)
{
return a.x * b.x + a.y * b.y + a.z * b.z;
}
class Vector2
{
public:
typedef double value_type;
Vector2():x(0),y(0){}
Vector2(double x, double y)
: x(x)
, y(y)
{
}
double x;
double y;
};
/******************************TESTS***************************************************/
void Test(const std::vector<Vector>& m, std::vector<Vector2>& m2)
{
Vector axisX(0.3f, 0.001f, 0.25f);
Vector axisY(0.043f, 0.021f, 0.45f);
std::vector<Vector2>::iterator i2 = m2.begin();
std::for_each(m.begin(), m.end(),
[&](const Vector& v)
{
Vector2 r(0,0);
r.x = Dot(axisX, v);
r.y = Dot(axisY, v);
(*i2) = r;
++i2;
});
}
int main()
{
cpptask::Timer timer;
int len2 = 300;
size_t len = 5000000;
std::vector<Vector> m;
m.reserve(len);
for (size_t i = 0; i < len; ++i)
{
m.push_back(Vector(i * 0.2345, i * 2.67, i * 0.98));
}
/***********************************************************************************/
{
std::vector<Vector2> m2(m.size());
double time = 0;
for (int i = 0; i < len2; ++i)
{
timer.Start();
Test(m, m2);
time += timer.End();
}
std::cout << "Dot product double - " << time / len2 << std::endl;
}
/***********************************************************************************/
return 0;
}