A simple multi threaded cpp-11 code

multithread.cpp

#include <iostream>
#include <string>
#include <vector>

#include <atomic>
#include <thread>
#include <future>

template <class F>
void par_for(int begin, int end, F fn) {
  std::atomic<int> idx;
  idx = begin;

  int num_cpus = std::thread::hardware_concurrency();
  std::vector<std::future<void>> futures (num_cpus);
  for (int cpu = 0; cpu != num_cpus; ++cpu) {
    futures[cpu] = std::async(
      std::launch::async,
      [cpu, &idx, end, &fn]() {
        for (;;) {
          int i = idx++;
          if (i >= end) break;
          fn(i, cpu);
        }
      }
    );
  }
  for (int cpu = 0; cpu != num_cpus; ++cpu) {
    futures[cpu].get();
  }
}

int main()
{
 par_for(
    10, 20,
    [](int idx, int cpu) {
       printf("task %d running on cpu %d\n", idx, cpu);
    }
  );
}

http://coliru.stacked-crooked.com/a/332f5d89cfb17ef6