Finding large difference b/w execution time of c++ and D codes for same problem

[Sparsh Mittal]

I am writing Julia sets program in C++ and D; exactly same way as 
much as possible. On executing I find large difference in their 
execution time. Can you comment what wrong am I doing or is it 
expected?

//===============C++ code, compiled with -O3 ==============
#include <sys/time.h>
#include <iostream>
using namespace std;
const  int DIM= 4194304;

struct complexClass {
  float r;
  float i;
  complexClass( float a, float b )
  {
    r = a;
    i = b;
  }


  float squarePlusMag(complexClass another)
  {
    float r1 = r*r - i*i + another.r;
    float i1 = 2.0*i*r + another.i;

    r = r1;
    i = i1;

    return (r1*r1+ i1*i1);
  }
};


int juliaFunction( int x, int y )
{

  complexClass a (x,y);

   complexClass c(-0.8, 0.156);

  int i = 0;

  for (i=0; i<200; i++) {
   if( a.squarePlusMag(c) > 1000)
      return 0;
  }

  return 1;
}


void kernel(  ){
  for (int x=0; x<DIM; x++) {
    for (int y=0; y<DIM; y++) {
      int offset = x + y * DIM;
      int juliaValue = juliaFunction( x, y );
        //juliaValue will be used by some function.
    }
  }
}


int main()
{

  struct timeval start, end;
  gettimeofday(&start, NULL);
  kernel();
  gettimeofday(&end, NULL);
  float delta = ((end.tv_sec  - start.tv_sec) * 1000000u +
         end.tv_usec - start.tv_usec) / 1.e6;


  cout<<" C++ code with dimension " << DIM <<" Total time: "<< 
delta << "[sec]\n";
}






//=====================D++ code, compiled with -O -release 
-inline=========

#!/usr/bin/env rdmd
import std.stdio;
import std.datetime;
immutable int DIM= 4194304;


struct complexClass {
  float r;
  float i;

  float squarePlusMag(complexClass another)
  {
    float r1 = r*r - i*i + another.r;
    float i1 = 2.0*i*r + another.i;

    r = r1;
    i = i1;

    return (r1*r1+ i1*i1);
  }
};


int juliaFunction( int x, int y )
{

  complexClass c = complexClass(0.8, 0.156);
  complexClass a= complexClass(x, y);


  for (int i=0; i<200; i++) {

    if( a.squarePlusMag(c) > 1000)
      return 0;
  }
  return 1;
}


void kernel(  ){
  for (int x=0; x<DIM; x++) {
    for (int y=0; y<DIM; y++) {
      int offset = x + y * DIM;
      int juliaValue = juliaFunction( x, y );
      //juliaValue will be used by some function.       
    }
  }
}


void main()
{
  StopWatch sw;
  sw.start();
  kernel();
  sw.stop();
  writeln(" D code serial with dimension ", DIM ," Total time: ", 
(sw.peek().msecs/1000), "[sec]");
}

//================
I will appreciate any help.