Fast shared-memory streaming multilevel graph partitioning

A fast parallel graph partitioner can benefit many applications by reducing data transfers. The online methods for partitioning graphs have to be fast and they often rely on simple one-pass streaming algorithms, while the offline methods for partitioning graphs contain more involved algorithms and t...

Full description

Saved in:
Bibliographic Details
Published in:Journal of parallel and distributed computing Vol. 147; no. C; pp. 140 - 151
Main Authors: Jafari, Nazanin, Selvitopi, Oguz, Aykanat, Cevdet
Format: Journal Article
Language:English
Published: United States Elsevier Inc 01.01.2021
Elsevier
Subjects:
ISSN:0743-7315, 1096-0848
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A fast parallel graph partitioner can benefit many applications by reducing data transfers. The online methods for partitioning graphs have to be fast and they often rely on simple one-pass streaming algorithms, while the offline methods for partitioning graphs contain more involved algorithms and the most successful methods in this category belong to the multilevel approaches. In this work, we assess the feasibility of using streaming graph partitioning algorithms within the multilevel framework. Our end goal is to come up with a fast parallel offline multilevel partitioner that can produce competitive cutsize quality. We rely on a simple but fast and flexible streaming algorithm throughout the entire multilevel framework. This streaming algorithm serves multiple purposes in the partitioning process: a clustering algorithm in the coarsening, an effective algorithm for the initial partitioning, and a fast refinement algorithm in the uncoarsening. Its simple nature also lends itself easily for parallelization. The experiments on various graphs show that our approach is on the average up to 5.1x faster than the multi-threaded MeTiS, which comes at the expense of only 2x worse cutsize. •We propose a parallel multilevel graph partitioner based on a flexible streaming algorithm.•The same streaming algorithm is utilized within each of the three stages of the multilevel partitioning process.•By adopting a streaming-based approach for partitioning, we offer a tradeoff between speed and quality.•Our approach is five times faster than a very common offline partitioner while it degrades the quality only by a factor of two.
Bibliography:USDOE
AC02-05CH11231
ISSN:0743-7315
1096-0848
DOI:10.1016/j.jpdc.2020.09.004