C ++ overhead stream

I play with streams in C ++, in particular, using them to parallelize a map operation.

Here is the code:

#include <thread>
#include <iostream>
#include <cstdlib>
#include <vector>
#include <math.h>
#include <stdio.h>

double multByTwo(double x){
  return x*2;
}

double doJunk(double x){
  return cos(pow(sin(x*2),3));
}

template <typename T>
void map(T* data, int n, T (*ptr)(T)){
  for (int i=0; i<n; i++)
    data[i] = (*ptr)(data[i]);
}

template <typename T>
void parallelMap(T* data, int n, T (*ptr)(T)){
  int NUMCORES = 3;
  std::vector<std::thread> threads;
  for (int i=0; i<NUMCORES; i++)
    threads.push_back(std::thread(&map<T>, data + i*n/NUMCORES, n/NUMCORES, ptr));
  for (std::thread& t : threads)
    t.join();
}

int main()
{
  int n = 1000000000;
  double* nums = new double[n];
  for (int i=0; i<n; i++)
    nums[i] = i;

  std::cout<<"go"<<std::endl;

  clock_t c1 = clock();

  struct timespec start, finish;
  double elapsed;

  clock_gettime(CLOCK_MONOTONIC, &start);

  // also try with &doJunk
  //parallelMap(nums, n, &multByTwo);
  map(nums, n, &doJunk);

  std::cout << nums[342] << std::endl;

  clock_gettime(CLOCK_MONOTONIC, &finish);

  printf("CPU elapsed time is %f seconds\n", double(clock()-c1)/CLOCKS_PER_SEC);

  elapsed = (finish.tv_sec - start.tv_sec);
  elapsed += (finish.tv_nsec - start.tv_nsec) / 1000000000.0;

  printf("Actual elapsed time is %f seconds\n", elapsed);
}

The multByTwoparallel version is actually a bit slower (1.01 seconds versus .95 real time), and with doJunk it is faster (51 versus 136 in real time). It means that

• parallelization works, and
• There is REALLY big overhead with the announcement of new flows. Any thoughts on why the overhead is so high, and how can I avoid this?