Talk:Checkpoint synchronization: Difference between revisions
I like FFT, but not specifically for this.
No edit summary |
(I like FFT, but not specifically for this.) |
||
Line 2:
: That's what it looks like to me. There are scenarios where that's the normal model (most notably GPGPU programming; the checkpoint is needed for hardware instruction resync.). In languages where data structure syncronization is implicit, I don't think a communication phase is necessary. Otherwise, (if I were writing in C++, for example), the communication phase might get used for work item distribution and condition checks. --[[User:Short Circuit|Michael Mol]] 00:37, 11 August 2010 (UTC)
::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 "[[Checkpoing synchronization]] with a communication phase"...for something like that, a more appropriate task might be something like map/reduce with an otherwise meaningless function call on each data block. (I wanted to say "generic function call", but that might force a distinction between languages that have (or can fake) first-class functions, and languages that don't/can't.) I like the FFT idea, but I don't care to have distinct tasks for a FFT map/reduce-like task, and FFT in general. Ditto for matrix block multiplication, for the same reasons; it's not helpful for site organization to demonstrate the same thing (such as a transform or algorithm) in multiple places. --[[User:Short Circuit|Michael Mol]] 10:46, 11 August 2010 (UTC)
| |||