The following program compiled under gcc 4.6.2 on centos with -O3:

#include <iostream>
#include <vector>
#include <algorithm>
#include <ctime>
using namespace std;

template <typename T>
class F {
public:
     typedef void (T::*Func)();

     F(Func f) : f_(f) {}

     void operator()(T& t) {
         (t.*f_)();
     }
private:
     Func f_;
};

struct X {
    X() : x_(0) {}

    void f(){
        ++x_;
    }

    int x_;
};

int main()
{
     const int N = 100000000;
     vector<X> xv(N);
     auto begin = clock();
     for_each (xv.begin(), xv.end(), F<X>(&X::f));
     auto end = clock();
     cout << end - begin << endl;
}

objdump -D shows that the generated code for the loop is:

  40097c:       e8 57 fe ff ff          callq  4007d8 <clock@plt>
  400981:       49 89 c5                mov    %rax,%r13
  400984:       0f 1f 40 00             nopl   0x0(%rax)
  400988:       48 89 ef                mov    %rbp,%rdi
  40098b:       48 83 c5 04             add    $0x4,%rbp
  40098f:       e8 8c ff ff ff          callq  400920 <_ZN1X1fEv>
  400994:       4c 39 e5                cmp    %r12,%rbp
  400997:       75 ef                   jne    400988 <main+0x48>
  400999:       e8 3a fe ff ff          callq  4007d8 <clock@plt>

Obviously gcc doesn't inline the function. Why isn't gcc capable of this optimization? Is there any compiler flag that can make gcc do the desired optimization?

c++ gcc
Edit
Report