我最近读到这篇文章：Floating point vs integer calculations on modern hardware，并对我自己的处理器在这个准基准测试中的性能感到好奇，所以我将两个版本的代码放在一起，一个是C#，一个是C++（Visual Studio 2010 Express），并对它们进行了优化编译，看看有什么问题。我的C#版本的输出是相当合理的：

int add/sub: 350ms
int div/mul: 3469ms
float add/sub: 1007ms
float div/mul: 67493ms
double add/sub: 1914ms
double div/mul: 2766ms

当我编译并运行C++版本时，出现了完全不同的东西：

int add/sub: 210.653ms
int div/mul: 2946.58ms
float add/sub: 3022.58ms
float div/mul: 172931ms
double add/sub: 1007.63ms
double div/mul: 74171.9ms

我期望有一些性能差异，但不是这么大！我不明白为什么C中的除法/乘法比加法/减法慢得多，而托管C#版本更符合我的期望。该函数的C版本代码如下：

template< typename T> void GenericTest(const char *typestring)
{
    T v = 0;
    T v0 = (T)((rand() % 256) / 16) + 1;
    T v1 = (T)((rand() % 256) / 16) + 1;
    T v2 = (T)((rand() % 256) / 16) + 1;
    T v3 = (T)((rand() % 256) / 16) + 1;
    T v4 = (T)((rand() % 256) / 16) + 1;
    T v5 = (T)((rand() % 256) / 16) + 1;
    T v6 = (T)((rand() % 256) / 16) + 1;
    T v7 = (T)((rand() % 256) / 16) + 1;
    T v8 = (T)((rand() % 256) / 16) + 1;
    T v9 = (T)((rand() % 256) / 16) + 1;

    HTimer tmr = HTimer();
    tmr.Start();
    for (int i = 0 ; i < 100000000 ; ++i)
    {
        v += v0;
        v -= v1;
        v += v2;
        v -= v3;
        v += v4;
        v -= v5;
        v += v6;
        v -= v7;
        v += v8;
        v -= v9;
    }
    tmr.Stop();

      // I removed the bracketed values from the table above, they just make the compiler
      // assume I am using the value for something do it doesn't optimize it out.
    cout << typestring << " add/sub: " << tmr.Elapsed() * 1000 << "ms [" << (int)v << "]" << endl;

    tmr.Start();
    for (int i = 0 ; i < 100000000 ; ++i)
    {
        v /= v0;
        v *= v1;
        v /= v2;
        v *= v3;
        v /= v4;
        v *= v5;
        v /= v6;
        v *= v7;
        v /= v8;
        v *= v9;
    }
    tmr.Stop();

    cout << typestring << " div/mul: " << tmr.Elapsed() * 1000 << "ms [" << (int)v << "]" << endl;
}

C#测试的代码不是通用的，并且是这样实现的：

static double DoubleTest()
{
    Random rnd = new Random();
    Stopwatch sw = new Stopwatch();

    double v = 0;
    double v0 = (double)rnd.Next(1, int.MaxValue);
    double v1 = (double)rnd.Next(1, int.MaxValue);
    double v2 = (double)rnd.Next(1, int.MaxValue);
    double v3 = (double)rnd.Next(1, int.MaxValue);
    double v4 = (double)rnd.Next(1, int.MaxValue);
    double v5 = (double)rnd.Next(1, int.MaxValue);
    double v6 = (double)rnd.Next(1, int.MaxValue);
    double v7 = (double)rnd.Next(1, int.MaxValue);
    double v8 = (double)rnd.Next(1, int.MaxValue);
    double v9 = (double)rnd.Next(1, int.MaxValue);

    sw.Start();
    for (int i = 0; i < 100000000; i++)
    {
        v += v0;
        v -= v1;
        v += v2;
        v -= v3;
        v += v4;
        v -= v5;
        v += v6;
        v -= v7;
        v += v8;
        v -= v9;
    }
    sw.Stop();

    Console.WriteLine("double add/sub: {0}", sw.ElapsedMilliseconds);
    sw.Reset();

    sw.Start();
    for (int i = 0; i < 100000000; i++)
    {
        v /= v0;
        v *= v1;
        v /= v2;
        v *= v3;
        v /= v4;
        v *= v5;
        v /= v6;
        v *= v7;
        v /= v8;
        v *= v9;
    }
    sw.Stop();

    Console.WriteLine("double div/mul: {0}", sw.ElapsedMilliseconds);
    sw.Reset();

    return v;
}

有什么想法吗？