c++ - 我可以报告 openmp 任务的进度吗？

Question

想象一个经典的 OMP 任务:

• 对 [0.0, 1.0) 范围内的大型 double vector 求和

Live On Coliru

using namespace std;

int main() {
    vector<double> v;

    // generate some data
    generate_n(back_inserter(v), 1ul << 18, 
       bind(uniform_real_distribution<double>(0,1.0), default_random_engine { random_device {}() }));

    long double sum = 0;

    {
#pragma omp parallel for reduction(+:sum)
        for(size_t i = 0; i < v.size(); i++)
        {
            sum += v[i];
        }
    }
    std::cout << "Done: sum = " << sum << "\n";
}

我很难想出如何报告进度。毕竟，OMP 正在为我处理所有团队线程之间的协调，而我没有一 block 全局状态。

我可能会使用常规的 std::thread 并从那里观察一些共享变量，但是没有更“omp-ish”的方法来实现这一点吗？

Answer 1

在没有 native 原子支持(甚至有它们)的处理器上使用 #pragma omp atomic，正如此处其他答案所建议的那样，可以减慢您的程序。

进度指示器的想法是让用户知道什么时候完成。想法。如果您的目标是加上/减去总运行时间的一小部分，用户就不会太在意。也就是说，用户希望事情尽快完成，但以更准确地知道事情何时结束为代价。

出于这个原因，我通常只跟踪单个线程的进度并用它来估计总进度。这适用于每个线程具有相似工作负载的情况。由于您正在使用 #pragma omp parallel for，您可能会处理一系列没有相互依赖性的相似元素，因此我的假设可能对您的用例有效。

我已将此逻辑包装在类 ProgressBar 中，我通常将其包含在头文件中，连同它的辅助类 Timer。该类使用 ANSI 控制信号来保持美观。

输出看起来像这样:

[======                                            ] (12% - 22.0s - 4 threads)

通过声明 -DNOPROGRESS 编译标志，让编译器消除进度条的所有开销也很容易。

代码和示例用法如下:

#include <iostream>
#include <chrono>
#include <thread>
#include <iomanip>
#include <stdexcept>

#ifdef _OPENMP
  ///Multi-threading - yay!
  #include <omp.h>
#else
  ///Macros used to disguise the fact that we do not have multithreading enabled.
  #define omp_get_thread_num()  0
  #define omp_get_num_threads() 1
#endif


///@brief Used to time how intervals in code.
///
///Such as how long it takes a given function to run, or how long I/O has taken.
class Timer{
 private:
  typedef std::chrono::high_resolution_clock clock;
  typedef std::chrono::duration<double, std::ratio<1> > second;

  std::chrono::time_point<clock> start_time; ///< Last time the timer was started
  double accumulated_time;                   ///< Accumulated running time since creation
  bool running;                              ///< True when the timer is running

 public:
  Timer(){
    accumulated_time = 0;
    running          = false;
  }

  ///Start the timer. Throws an exception if timer was already running.
  void start(){
    if(running)
      throw std::runtime_error("Timer was already started!");
    running=true;
    start_time = clock::now();
  }

  ///Stop the timer. Throws an exception if timer was already stopped.
  ///Calling this adds to the timer's accumulated time.
  ///@return The accumulated time in seconds.
  double stop(){
    if(!running)
      throw std::runtime_error("Timer was already stopped!");

    accumulated_time += lap();
    running           = false;

    return accumulated_time;
  }

  ///Returns the timer's accumulated time. Throws an exception if the timer is
  ///running.
  double accumulated(){
    if(running)
      throw std::runtime_error("Timer is still running!");
    return accumulated_time;
  }

  ///Returns the time between when the timer was started and the current
  ///moment. Throws an exception if the timer is not running.
  double lap(){
    if(!running)
      throw std::runtime_error("Timer was not started!");
    return std::chrono::duration_cast<second> (clock::now() - start_time).count();
  }

  ///Stops the timer and resets its accumulated time. No exceptions are thrown
  ///ever.
  void reset(){
    accumulated_time = 0;
    running          = false;
  }
};


///@brief Manages a console-based progress bar to keep the user entertained.
///
///Defining the global `NOPROGRESS` will
///disable all progress operations, potentially speeding up a program. The look
///of the progress bar is shown in ProgressBar.hpp.
class ProgressBar{
 private:
  uint32_t total_work;    ///< Total work to be accomplished
  uint32_t next_update;   ///< Next point to update the visible progress bar
  uint32_t call_diff;     ///< Interval between updates in work units
  uint32_t work_done;
  uint16_t old_percent;   ///< Old percentage value (aka: should we update the progress bar) TODO: Maybe that we do not need this
  Timer    timer;         ///< Used for generating ETA

  ///Clear current line on console so a new progress bar can be written
  void clearConsoleLine() const {
    std::cerr<<"\r\033[2K"<<std::flush;
  }

 public:
  ///@brief Start/reset the progress bar.
  ///@param total_work  The amount of work to be completed, usually specified in cells.
  void start(uint32_t total_work){
    timer = Timer();
    timer.start();
    this->total_work = total_work;
    next_update      = 0;
    call_diff        = total_work/200;
    old_percent      = 0;
    work_done        = 0;
    clearConsoleLine();
  }

  ///@brief Update the visible progress bar, but only if enough work has been done.
  ///
  ///Define the global `NOPROGRESS` flag to prevent this from having an
  ///effect. Doing so may speed up the program's execution.
  void update(uint32_t work_done0){
    //Provide simple way of optimizing out progress updates
    #ifdef NOPROGRESS
      return;
    #endif

    //Quick return if this isn't the main thread
    if(omp_get_thread_num()!=0)
      return;

    //Update the amount of work done
    work_done = work_done0;

    //Quick return if insufficient progress has occurred
    if(work_done<next_update)
      return;

    //Update the next time at which we'll do the expensive update stuff
    next_update += call_diff;

    //Use a uint16_t because using a uint8_t will cause the result to print as a
    //character instead of a number
    uint16_t percent = (uint8_t)(work_done*omp_get_num_threads()*100/total_work);

    //Handle overflows
    if(percent>100)
      percent=100;

    //In the case that there has been no update (which should never be the case,
    //actually), skip the expensive screen print
    if(percent==old_percent)
      return;

    //Update old_percent accordingly
    old_percent=percent;

    //Print an update string which looks like this:
    //  [================================================  ] (96% - 1.0s - 4 threads)
    std::cerr<<"\r\033[2K["
             <<std::string(percent/2, '=')<<std::string(50-percent/2, ' ')
             <<"] ("
             <<percent<<"% - "
             <<std::fixed<<std::setprecision(1)<<timer.lap()/percent*(100-percent)
             <<"s - "
             <<omp_get_num_threads()<< " threads)"<<std::flush;
  }

  ///Increment by one the work done and update the progress bar
  ProgressBar& operator++(){
    //Quick return if this isn't the main thread
    if(omp_get_thread_num()!=0)
      return *this;

    work_done++;
    update(work_done);
    return *this;
  }

  ///Stop the progress bar. Throws an exception if it wasn't started.
  ///@return The number of seconds the progress bar was running.
  double stop(){
    clearConsoleLine();

    timer.stop();
    return timer.accumulated();
  }

  ///@return Return the time the progress bar ran for.
  double time_it_took(){
    return timer.accumulated();
  }

  uint32_t cellsProcessed() const {
    return work_done;
  }
};

int main(){
  ProgressBar pg;
  pg.start(100);
  //You should use 'default(none)' by default: be specific about what you're
  //sharing
  #pragma omp parallel for default(none) schedule(static) shared(pg)
  for(int i=0;i<100;i++){
    pg.update(i);
    std::this_thread::sleep_for(std::chrono::seconds(1));
  }
}