Commit 17f6e010 authored by THIBAULT Samuel's avatar THIBAULT Samuel
Browse files

emphasize that schedulers are not centralized

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/starpu/website@18074 176f6dd6-97d6-42f4-bd05-d3db9ad07c7a
parent d03579c2
...@@ -208,10 +208,12 @@ machine, for instance by using scheduling strategies based on auto-tuned ...@@ -208,10 +208,12 @@ machine, for instance by using scheduling strategies based on auto-tuned
performance models. These determine the relative performance achieved performance models. These determine the relative performance achieved
by the different processing units for the various kinds of task, and thus by the different processing units for the various kinds of task, and thus
permits to <b>automatically let processing units execute the tasks they are the best for</b>. permits to <b>automatically let processing units execute the tasks they are the best for</b>.
Various strategies and variants are available: dmda (a data-aware MCT strategy, Various strategies and variants are available. Some of them are centralized, but
most of them are completely distributed: dmda (a data-aware MCT strategy,
thus similar to heft but starts executing tasks before the whole task graph is thus similar to heft but starts executing tasks before the whole task graph is
submitted, thus allowing dynamic task submission), eager, locality-aware submitted, thus allowing dynamic task submission and a decentralized scheduler),
work-stealing, ... The overhead per task is typically around the order of eager (dumb centralized queue), decentralized locality-aware work-stealing, ...
The overhead per task is typically around the order of
magnitude of a microsecond. Tasks should thus be a few orders of magnitude magnitude of a microsecond. Tasks should thus be a few orders of magnitude
bigger, such as 100 microseconds or 1 millisecond, to make the overhead bigger, such as 100 microseconds or 1 millisecond, to make the overhead
negligible. negligible.
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment