I disagree.
One goal of one-sided is to allow more natural programming of
applications.
Typically they have a data area (the window) where the other processes
can put (or get) their results.
Looking at applications with irregular grids and with automatic
load balance, they dont want for each process an own data region.
Therefore it is important to allow one window with many non
overlapping regions which dynamically change in position and
length channging.
Rolf
PS: Please can someone explane whether any alternative model
is better in efficiency or functionality than the main draft?
In the moment they all seem to be worse because they need
more unnecessary locks, barriers or cache flushes or invalidates.
And for the implementation the code consuming problems
(e.g. window bondary inside a cache line) are still the same.
Eric wrote:
Well, we want a model that is:
1) Easy to understand
2) Easy/possible to implement
3) Useful for applications
4) Portable
5) Fast
I believe, that the user primarily wants
*) Useful for applications
*) Fast
*) possible to implement on each platform
Rolf Rabenseifner (Computer Center )
Rechenzentrum Universitaet Stuttgart (University of Stuttgart)
Allmandring 30 Phone: ++49 711 6855530
D-70550 Stuttgart 80 FAX: ++49 711 6787626
Germany rabenseifner@rus.uni-stuttgart.de