c++ - Measure computation time -

how measure computation time correctly?

variant 1:

std::chrono::time_point<std::chrono::system_clock> start, end;       float elapsed = 0;      int n = 100;      for(int i=0; i<n; ++i)     {         start = std::chrono::system_clock::now();         func();//target function         end = std::chrono::system_clock::now();         elapsed += std::chrono::duration_cast<std::chrono::microseconds>(end-start).count();     } 

variant 2:

start = std::chrono::system_clock::now(); for(int i=0; i<n; ++i)     func(); end = std::chrono::system_clock::now(); elapsed = std::chrono::duration_cast<std::chrono::microseconds>(end-start).count(); 

these variants show different results: tried replace virtual functions std::function :

struct base {     virtual void f() = 0; };  struct der1 : public base {     virtual void f() override      {         int i=0;          for(int j=0; j<100; ++j)             += 2*j;      } };  struct der2 : public base {     virtual void f() override      {         int i=0;          for(int j=0; j<100; ++j)             += 3*j;      } };  struct base_ {     base_(std::function<void()> f_) : f(f_) {}     std::function<void()> f; };  struct der1_ : public base_ {     der1_() : base_([]{                        int i=0;                         for(int j=0; j<100; ++j)                            += 2*j;                       }){} };  struct der2_ : public base_ {     der2_() : base_([]{                        int i=0;                         for(int j=0; j<100; ++j)                            += 3*j;                       }){} };   void process1(std::vector<base_*>& v) {     for(auto &elem : v)         elem->f(); }  void process2(std::vector<base*>& v) {     for(auto &elem : v)         elem->f(); }  int main() {      std::vector<base_*> vec1;     vec1.push_back(new der1_);     vec1.push_back(new der2_);     vec1.push_back(new der1_);     vec1.push_back(new der2_);      std::vector<base*> vec2;     vec2.push_back(new der1);     vec2.push_back(new der2);     vec2.push_back(new der1);     vec2.push_back(new der2);     std::chrono::time_point<std::chrono::system_clock> start1, end1, start2, end2;        float elapsed1 = 0;      float elapsed2 = 0;      int n = 6000;     //variant 2     start1 = std::chrono::system_clock::now();     for(int i=0; i<n; ++i)         process1(vec1);     end1 = std::chrono::system_clock::now();     elapsed1 = std::chrono::duration_cast<std::chrono::microseconds>(end1-start1).count();      start2 = std::chrono::system_clock::now();     for(int i=0; i<n; ++i)         process2(vec2);     end2 = std::chrono::system_clock::now();     elapsed2 = std::chrono::duration_cast<std::chrono::microseconds>(end2-start2).count();      std::cout<<"virtual: "<<elapsed2<<"\npointer: "<<elapsed1;      for(int i=0; i<vec1.size(); ++i)         delete vec1[i];      for(int i=0; i<vec2.size(); ++i)         delete vec2[i];      return 0; } 

and want understand whether performance gains replacement virtual functions on std::function. second variant indicates 2.5-3 gain, while first method shows drop of perfomance.

the reason difference in times time spent doing assignment end, add time counters. second way avoids @ cost of counting time takes increment i in loop, less.