Graph Repartitioning with both Dynamic Load and Dynamic Processor Allocation - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2013

Graph Repartitioning with both Dynamic Load and Dynamic Processor Allocation

Abstract

Dynamic load balancing is an important step conditioning the performance of parallel programs, like adaptive mesh refinement codes. If the global workload varies drastically over time (such that memory is exceeded), it can be relevant to adjust the number of processors while maintaining the load balanced. We propose two different solutions, that extend classic graph repartitioning approaches to accept a variable number of processors: one based on biased partitioning method and one based on a diffusive method. We call this problem: the MxN graph repartitioning problem. Finally, an experimental study on real-life graphs validates our algorithms against state-of-the-art methods.
Fichier principal
Vignette du fichier
article-final-hal.pdf (733.75 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00857881 , version 1 (04-09-2013)
hal-00857881 , version 2 (04-09-2013)

Identifiers

Cite

Clément Vuchener, Aurélien Esnard. Graph Repartitioning with both Dynamic Load and Dynamic Processor Allocation. International Conference on Parallel Computing - ParCo2013, Sep 2013, München, Germany. pp.243-252, ⟨10.3233/978-1-61499-381-0-243⟩. ⟨hal-00857881v2⟩

Collections

CNRS INRIA INRIA2
213 View
347 Download

Altmetric

Share

Gmail Facebook X LinkedIn More