GoingNative 31: Easy Parallelization with Parallel STL

Play GoingNative 31: Easy Parallelization with Parallel STL
Sign in to queue

Description

Our show at this time dons a most festive theme,
As we bid you good viewers, "Happy Halloween!"
Join us this day in our episode,
With one neat little trick to parallelize your code.
Perhaps you scarce know how to do this task well,
Until you've had a go with Parallel STL!
With code that, once changed, still so simply reads,
It's -- dare I say -- spooky! (with its simplicity)
But the basket of treats is not quite yet gone,
For parallel stl (dot) codeplex (dot) com
Is a great way for you to be part of the force,
That influences the future of C++'s course!

And now I shall cease from extending this rhyme
For there's already the video to take up your time ;)

P.S. Please welcome Mr. Carroll!

Embed

Download

Right click to download this episode

The Discussion

  • User profile image
    Norbert

    Hi,
    I'd like to know if it is possible to get the implementation of the measure_time utility Artur is using. I have my own one (more precise than 1/1000 sec using Windows multimedia timers, not std::chrono), but since I'm only a "hobbyist programmer" I'd still like to see how a "Pro" implements a function like that. One that measures correctly if parallelism is involved - where mine might probably measure incorrectly since it wasn't designed with parallelism in mind. Thank you,
    Norbert

  • User profile image
    Artur Laksberg

    @Norbert: You can find the implementation here.

    To get reliable results, you need to perform multiple runs, preferably on different types of hardware. The variance is usually more significant than the precision of the timer, so measuring small differences in performance comes down to probability and statistics. We've found Student's t-test to be useful for measuring the difference between the sets of runs.

Add Your 2 Cents