Access based data decomposition for distributed memory machines
Document Type
Conference Proceeding
Publication Date
1-1-1991
Abstract
This paper addresses the problem of partitioning data for distributed memory machines or multicomputer. If insufficient attention is paid to the data allocation problem, then the amount of time spent in interprocessor communication might be so high as to seriously undermine the benefits of parallelism. It is therefore worthwhile for a compiler to analyze patterns of data usage to determine allocation, in order to minimize interprocessor communication. We present a matrix notation to describe array accesses in fully parallel loops which lets us derive sufficient conditions for communication-free decomposition of arrays.
Publication Source (Journal or Book title)
6th Distributed Memory Computing Conference, DMCC 1991 - Proceedings
First Page
196
Last Page
199
Recommended Citation
Ramanujam, J., & Sadayappan, P. (1991). Access based data decomposition for distributed memory machines. 6th Distributed Memory Computing Conference, DMCC 1991 - Proceedings, 196-199. https://doi.org/10.1109/DMCC.1991.633122