Talk:Checkpoint synchronization: Difference between revisions
m
fix typo
(What it does, what it might be used for) |
m (fix typo) |
||
Line 3:
::Right, the intent was to show the problem in its distilled form. It is comparable with plain events where there is no data exchange too, just a raw signals. event + data = message, it is already a different object and problem. But I agree with Kevin that another task with data exchange might be interesting too. I think it could be a bit more concrete problem. We could take some known parallel algorithm like block matrix multiplication or FFT. --[[User:Dmitry-kazakov|Dmitry-kazakov]] 06:51, 11 August 2010 (UTC)
::: FFT would be very interesting, because it's a very popular signal processing transform, and there are huge number of ways to improve performance via platform instruction sets, acceleration libraries and parallelization. It's very likely it will lead to multiple examples per language, but as long as there's at least one naive example per language (for logic clarity), I think that's probably a good thing.
::: That said, I'd be careful about appropriating FFT specifically to demonstrate "[[
: The principle is that there is a checkpoint group (which a thread may ask to join and leave) and on synchronization, nobody completes the checkpoint synch operation until all members of the group complete it. It's use might be if you've got a bunch of threads doing some kind of physical simulation, with a checkpoint barrier at the end of each simulation time step. –[[User:Dkf|Donal Fellows]] 13:53, 11 August 2010 (UTC)
|