One-dimensional partitioning for heterogeneous systems: theory and practice
Date
2008-11Source Title
Journal of Parallel and Distributed Computing
Print ISSN
0743-7315
Publisher
Academic Press
Volume
68
Issue
11
Pages
1473 - 1486
Language
English
Type
ArticleItem Usage Stats
212
views
views
193
downloads
downloads
Abstract
We study the problem of one-dimensional partitioning of nonuniform workload arrays, with optimal load balancing for heterogeneous systems. We look at two cases: chain-on-chain partitioning, where the order of the processors is specified, and chain partitioning, where processor permutation is allowed. We present polynomial time algorithms to solve the chain-on-chain partitioning problem optimally, while we prove that the chain partitioning problem is NP-complete. Our empirical studies show that our proposed exact algorithms produce substantially better results than heuristics, while solution times remain comparable. © 2008 Elsevier Inc. All rights reserved.
Keywords
Chain-on-chain partitioningDynamic programming
Load balancing
One-dimensional partitioning
Parallel computing
Parametric search
Heuristic programming
Nuclear propulsion
Parallel processing systems
Polynomial approximation
Chain partitioning
Empirical studies
Exact algorithms
Heterogeneous systems
Non uniform
NP-complete
Optimal load balancing
Polynomial-time algorithms
Real time systems