Develop a C++ program to find all prime numbers within a given range using parallel processing, making use of multiple cores to speed up the computation. The program should take the start and end integers of the range as input and display all prime numbers within that range.

#include <iostream>
#include<time.h>
#include <cstdlib>
#include <pthread.h>
#include <fstream>
#include <chrono>

using namespace std;

struct thread_data {
  int start;
  int end;
};

void *calculatePrimes(void *threadarg) {
  // extract the struct data from the void pointer
  struct thread_data *my_data;
  my_data = (struct thread_data *) threadarg;

  // get the start and end numbers from the parameter
  int start = my_data->start;
  int end = my_data->end;

  // this is where the primes will be displayed
  ofstream output;
  output.open("output.txt", ios::app);

  // calculate all the primes within the range
  for(int i = start; i <= end; i++) {
    int flag = 0;
    for (int j = 2; j <= i/2; j++) {
      if(i