基元类型比C++中的用户类型慢

我很好奇，做了一些基准测试来确定int或float等基元类型与用户类型之间的性能增量。

我创建了一个模板类Var，创建了一些内联算术运算符。测试包括为基元和Var向量循环此循环：

for (unsigned i = 0; i < 1000; ++i) {
    in1[i] = i;
    in2[i] = -i;
    out[i] = (i % 2) ? in1[i] + in2[i] : in2[i] - in1[i];
}

我对结果感到非常惊讶，事实证明我的Var课大部分时间都更快，int 平均而言，该循环在该课程中花费了大约 5700 纳秒。 在 3000 次运行中，int 比 11 倍快。 Var快了2989倍。与float的结果类似，其中Var比浮点数2991的15100 nsec快15100 nsec。

基元类型不应该更快吗？

编辑：编译器是一个相当古老的 mingw 4.4.0，构建选项是 QtCreator 的默认值，没有优化：

qmake call: qmake.exe C:...untitled15.pro -r -spec win32-g++ "CONFIG+=release"

好的，发布完整源代码，平台是 64 位 Win7，4 GB DDR2-800，Core2Duo@3Ghz

#include <QTextStream>
#include <QVector>
#include <QElapsedTimer>
template<typename T>
class Var{
public:
    Var() {}
    Var(T val) : var(val) {}
    inline T operator+(Var& other)
    {
        return var + other.value();
    }
    inline T operator-(Var& other)
    {
        return var - other.value();
    }
    inline T operator+(T& other)
    {
        return var + other;
    }
    inline T operator-(T& other)
    {
        return var - other;
    }
    inline void operator=(T& other)
    {
        var = other;
    }
    inline T& value()
    {
        return var;
    }
private:
    T var;
};
int main()
{
    QTextStream cout(stdout);
    QElapsedTimer timer;
    unsigned count = 1000000;
    QVector<double> pin1(count), pin2(count), pout(count);
    QVector<Var<double> > vin1(count), vin2(count), vout(count);
    unsigned t1, t2, pAcc = 0, vAcc = 0, repeat = 10, pcount = 0, vcount = 0, ecount = 0;
    for (int cc = 0; cc < 5; ++cc)
    {
        for (unsigned c = 0; c < repeat; ++c)
        {
            timer.restart();
            for (unsigned i = 0; i < count; ++i)
            {
                pin1[i] = i;
                pin2[i] = -i;
                pout[i] = (i % 2) ? pin1[i] + pin2[i] : pin2[i] - pin1[i];
            }
            t1 = timer.nsecsElapsed();
            cout << t1 << endl;
            timer.restart();
            for (unsigned i = 0; i < count; ++i)
            {
                vin1[i] = i;
                vin2[i] = -i;
                vout[i] = (i % 2) ? vin1[i] + vin2[i] : vin2[i] - vin1[i];
            }
            t2 = timer.nsecsElapsed();
            cout << t2 << endl;;
            pAcc += t1;
            vAcc += t2;
        }
        pAcc /= repeat;
        vAcc /= repeat;
        if (pAcc < vAcc) {
            cout << "primitive was faster" << endl;
            pcount++;
        }
        else if (pAcc > vAcc) {
            cout << "var was faster" << endl;
            vcount++;
        }
        else {
            cout << "amazingly, both are equally fast" << endl;
            ecount++;
        }
        cout << "Average for primitive type is " << pAcc << ", average for Var is " << vAcc << endl;
    }
    cout << "int was faster " << pcount << " times, var was faster " << vcount << " times, equal " << ecount << " times, " << pcount + vcount + ecount << " times ran total" << endl;
}

相对而言，对于浮点数，Var 类比浮点数快 6-7%，整数约为 3%。

原来的 1000 的向量长度运行了测试，结果仍然一致并且有利于该类。