Simplest TBB example

Can someone give me a TBB example how to:

1. set the maximum count of active threads.
2. execute tasks that are independent from each others and presented in the form of class, not static functions.

Here's a couple of complete examples, one using parallel_for, the other using parallel_for_each.

Update 2014-04-12: These show what I'd consider to be a pretty old fashioned way of using TBB now; I've added a separate answer using parallel_for with a C++11 lambda.

#include "tbb/blocked_range.h"
#include "tbb/parallel_for.h"
#include "tbb/task_scheduler_init.h"
#include <iostream>
#include <vector>

struct mytask {
  mytask(size_t n)
    :_n(n)
  {}
  void operator()() {
    for (int i=0;i<1000000;++i) {}  // Deliberately run slow
    std::cerr << "[" << _n << "]";
  }
  size_t _n;
};

struct executor
{
  executor(std::vector<mytask>& t)
    :_tasks(t)
  {}
  executor(executor& e,tbb::split)
    :_tasks(e._tasks)
  {}

  void operator()(const tbb::blocked_range<size_t>& r) const {
    for (size_t i=r.begin();i!=r.end();++i)
      _tasks[i]();
  }

  std::vector<mytask>& _tasks;
};

int main(int,char**) {

  tbb::task_scheduler_init init;  // Automatic number of threads
  // tbb::task_scheduler_init init(2);  // Explicit number of threads

  std::vector<mytask> tasks;
  for (int i=0;i<1000;++i)
    tasks.push_back(mytask(i));

  executor exec(tasks);
  tbb::parallel_for(tbb::blocked_range<size_t>(0,tasks.size()),exec);
  std::cerr << std::endl;

  return 0;
}

and

#include "tbb/parallel_for_each.h"
#include "tbb/task_scheduler_init.h"
#include <iostream>
#include <vector>

struct mytask {
  mytask(size_t n)
    :_n(n)
  {}
  void operator()() {
    for (int i=0;i<1000000;++i) {}  // Deliberately run slow
    std::cerr << "[" << _n << "]";
  }
  size_t _n;
};

template <typename T> struct invoker {
  void operator()(T& it) const {it();}
};

int main(int,char**) {

  tbb::task_scheduler_init init;  // Automatic number of threads
  // tbb::task_scheduler_init init(4);  // Explicit number of threads

  std::vector<mytask> tasks;
  for (int i=0;i<1000;++i)
    tasks.push_back(mytask(i));

  tbb::parallel_for_each(tasks.begin(),tasks.end(),invoker<mytask>());
  std::cerr << std::endl;

  return 0;
}

Both compile on a Debian/Wheezy (g++ 4.7) system with g++ tbb_example.cpp -ltbb (then run with ./a.out)

(See this question for replacing that "invoker" thing with a std::mem_fun_ref or boost::bind).

Here's a more modern use of parallel_for with a lambda; compiles and runs on Debian/Wheezy with g++ -std=c++11 tbb_example.cpp -ltbb && ./a.out:

#include "tbb/parallel_for.h"
#include "tbb/task_scheduler_init.h"
#include <iostream>
#include <vector>

struct mytask {
  mytask(size_t n)
    :_n(n)
  {}
  void operator()() {
    for (int i=0;i<1000000;++i) {}  // Deliberately run slow
    std::cerr << "[" << _n << "]";
  }
  size_t _n;
};

int main(int,char**) {

  //tbb::task_scheduler_init init;  // Automatic number of threads
  tbb::task_scheduler_init init(tbb::task_scheduler_init::default_num_threads());  // Explicit number of threads

  std::vector<mytask> tasks;
  for (int i=0;i<1000;++i)
    tasks.push_back(mytask(i));

  tbb::parallel_for(
    tbb::blocked_range<size_t>(0,tasks.size()),
    [&tasks](const tbb::blocked_range<size_t>& r) {
      for (size_t i=r.begin();i<r.end();++i) tasks[i]();
    }
  );

  std::cerr << std::endl;

  return 0;
}