yade-dev team mailing list archive
-
yade-dev team
-
Mailing list archive
-
Message #00291
Re: Note on optimized compilation / optimized coding / profiling results
> I want to point out that I prefer to parallelize stuff using
> boost::thread, instead of openMP #pragma parallel. I would prefer to
> fork several loops with boost thread, where each loop is for selected
> start-end pairs.
>
OK, but openMP doesn't alter the code in any way unless tunrned on by
compiler flag. And later we can change stuff with boost::thread.
> Later, possibly, the start-end pairs can be adjusted depending on how
> much time was spent on them.
>
openMP has support for (automatic or manual) load-balancing as well.
Anyway, the loops have to be over integer indices (with random access to
elements), not iterators. That's what I meant.
_______________________________________________
yade-dev mailing list
yade-dev@xxxxxxxxxxxxxxxx
https://lists.berlios.de/mailman/listinfo/yade-dev
References