Re: [Algorithms] General purpose task parallel threading approach
Brought to you by:
vexxed72
|
From: Sebastian S. <seb...@gm...> - 2009-04-09 23:25:31
|
On Thu, Apr 9, 2009 at 11:51 PM, Jarkko Lempiainen <al...@gm...>wrote: > > It's actually not vital for throughput, and I couldn't see anything in > the presentation you linked saying it is. > > > > That’s what “Minimizing the Critical Path” is about. Ignoring the issue > doesn’t mean it doesn’t exist. > > That section only seems to talk about optimizing scheduling based on static (in the sense that they're known ahead of time - not necessarily at compile time) dependencies, not about the necessity to support priorities. And of course, general code doesn't have a static call graph, so it's even impossible to do this analysis unless your code happens to be simple enough (see: the halting problem). -- Sebastian Sylvan +44(0)7857-300802 UIN: 44640862 |