gcc 4.5.1(Ubuntu 10.04,intel core2duo 3.0 Ghz)下考虑此代码
它只有2个测试,在第一个测试中,我直接调用了虚拟功能,在第二个测试中,我通过Wrapper类调用了它:

测试文件

#define ITER 100000000

class Print{

public:

typedef Print* Ptr;

virtual void print(int p1, float p2, float p3, float p4){/*DOES NOTHING */}

};

class PrintWrapper
{

    public:

      typedef PrintWrapper* Ptr;

      PrintWrapper(Print::Ptr print, int p1, float p2, float p3, float p4) :
      m_print(print), _p1(p1),_p2(p2),_p3(p3),_p4(p4){}

      ~PrintWrapper(){}

      void execute()
      {
        m_print->print(_p1,_p2,_p3,_p4);
      }

    private:

      Print::Ptr m_print;
      int _p1;
      float _p2,_p3,_p4;

};

 Print::Ptr p = new Print();
 PrintWrapper::Ptr pw = new PrintWrapper(p, 1, 2.f,3.0f,4.0f);

void test1()
{

 //-------------test 1-------------------------

 for (auto var = 0; var < ITER; ++var)
 {
   p->print(1, 2.f,3.0f,4.0f);
 }

 }

 void test2()
 {

  //-------------test 2-------------------------

 for (auto var = 0; var < ITER; ++var)
 {
   pw->execute();
 }

}

int main()
{
  test1();
  test2();
}

我使用gprof和objdump对其进行了概要分析:

g++ -c -std=c++0x -pg -g -O2 test.cpp
objdump -d -M intel -S test.o > objdump.txt
g++ -pg test.o -o test
./test
gprof test > gprof.output

在gprof.output中,我观察到test2()比test1()需要更多时间,但我无法解释

Each sample counts as 0.01 seconds.
  %   cumulative   self              self     total
 time   seconds   seconds    calls  ms/call  ms/call  name
 49.40      0.41     0.41        1   410.00   540.00  test2()
 31.33      0.67     0.26 200000000     0.00     0.00  Print::print(int, float, float, float)
 19.28      0.83     0.16        1   160.00   290.00  test1()
  0.00      0.83     0.00        1     0.00     0.00  global constructors keyed to p

objdump.txt中的汇编代码也不能帮助我:

 //-------------test 1-------------------------
 for (auto var = 0; var < ITER; ++var)
  15:   83 c3 01                add    ebx,0x1
 {
   p->print(1, 2.f,3.0f,4.0f);
  18:   8b 10                   mov    edx,DWORD PTR [eax]
  1a:   c7 44 24 10 00 00 80    mov    DWORD PTR [esp+0x10],0x40800000
  21:   40
  22:   c7 44 24 0c 00 00 40    mov    DWORD PTR [esp+0xc],0x40400000
  29:   40
  2a:   c7 44 24 08 00 00 00    mov    DWORD PTR [esp+0x8],0x40000000
  31:   40
  32:   c7 44 24 04 01 00 00    mov    DWORD PTR [esp+0x4],0x1
  39:   00
  3a:   89 04 24                mov    DWORD PTR [esp],eax
  3d:   ff 12                   call   DWORD PTR [edx]

  //-------------test 2-------------------------
 for (auto var = 0; var < ITER; ++var)
  65:   83 c3 01                add    ebx,0x1

      ~PrintWrapper(){}

      void execute()
      {
        m_print->print(_p1,_p2,_p3,_p4);
  68:   8b 10                   mov    edx,DWORD PTR [eax]
  6a:   8b 70 10                mov    esi,DWORD PTR [eax+0x10]
  6d:   8b 0a                   mov    ecx,DWORD PTR [edx]
  6f:   89 74 24 10             mov    DWORD PTR [esp+0x10],esi
  73:   8b 70 0c                mov    esi,DWORD PTR [eax+0xc]
  76:   89 74 24 0c             mov    DWORD PTR [esp+0xc],esi
  7a:   8b 70 08                mov    esi,DWORD PTR [eax+0x8]
  7d:   89 74 24 08             mov    DWORD PTR [esp+0x8],esi
  81:   8b 40 04                mov    eax,DWORD PTR [eax+0x4]
  84:   89 14 24                mov    DWORD PTR [esp],edx
  87:   89 44 24 04             mov    DWORD PTR [esp+0x4],eax
  8b:   ff 11                   call   DWORD PTR [ecx]

我们如何解释这种差异?

最佳答案

test2()中,程序必须首先从堆中加载pw,然后调用pw->execute()(这会产生调用开销),然后通过pw->m_print参数加载_p1_p4,然后为pw加载vtable指针,然后为pw->Print加载vtable插槽,然后调用pw->Print。由于编译器看不到虚拟调用,因此它必须假定所有这些值在下一次迭代时都已更改,然后重新加载所有值。

test()中,参数在代码段中是内联的,我们只需要加载p,vtable指针和vtable插槽。这样,我们已经节省了五个负载。这很容易解释时差。

简而言之,这里的罪魁祸首是pw->m_printpw->_p1pw->_p4的负载。

关于C++ : difference of execution time between two call of a virtual function,我们在Stack Overflow上找到一个类似的问题:https://stackoverflow.com/questions/8405937/

10-10 22:35