Basic HTML version of Foils prepared May 7 1996

Foil 32 Computer Architectures - MIMD - Distributed Memory

From MetaComputing -- MRA Meeting Part I:Concepts and Issues Tutorial for CRPC MRA Meeting at Cornell -- May 7 1996. by Mark Baker, Geoffrey Fox


A single large regular data structure, such as an array, can be left intact within SM, and each co-operating processor is simply told which ranges of indices its is to deal with;
In DM, once the decision as to index-ranges has been made, the data structure has to be decomposed, i.e., the data within a given set of ranges assigned to a particular processor must be physically sent to that processor in order for the processing to be done, and then any results must be sent back to whichever processor has responsibility for co-ordinating the final result.
And, to make matters even more interesting, it's very common in these types of cases for the boundary values, the values along each "outer" side of each section, to be relevant to the processor which shares that boundary.



Northeast Parallel Architectures Center, Syracuse University, npac@npac.syr.edu

If you have any comments about this server, send e-mail to webmaster@npac.syr.edu.

Page produced by wwwfoil on Sun Apr 11 1999