Unpublished conference/Abstract (Scientific congresses, symposiums and conference proceedings)
Parallelizing XDEM: Load-balancing policies and efficiency, a study
Rousset, Alban; Besseron, Xavier; Peters, Bernhard
2017International Conference on Particle-Based Methods (PARTICLES17)
 

Files


Full Text
a66.pdf
Publisher postprint (103.39 kB)
Download

All documents in ORBilu are protected by a user license.

Send to



Details



Keywords :
HPC; load-balancing; DEM
Abstract :
[en] In XDEM, the simulation domain is geometrically decomposed in regular fixed-size cells that are used to distribute the workload between the processes. The role of the partitioning algorithm is to distribute the cells among all the processes in order to balance the workload. To accomplish this task, the partitioning algorithm relies on a computing/communication cost that has been estimated for each cell. A proper estimation of these costs is fundamental to obtain pertinent results during this phase. The study in the work is twofold. First, we integrate five partitioning algorithms (ORB, RCB, RIB, kway and PhG) in the XDEM framework [1]. Most of these algorithms are implemented within the Zoltan library [2], a parallel framework for partitioning and ordering problems. Secondly, we propose different policies to estimate the computing cost and communication cost of the different cells composing the simulation domain. Then, we present an experimental evaluation and a performance comparison of these partitioning algorithms and cost-estimation policies on a large scale parallel execution of XDEM running on the HPC platform of the University of Luxembourg. Finally, after explaining the pros and cons of each partitioning algorithms and cost-estimation policies, we discuss on the best choices to adopt depending on the simulation case.
Disciplines :
Computer science
Author, co-author :
Rousset, Alban ;  University of Luxembourg > Faculty of Science, Technology and Communication (FSTC) > Engineering Research Unit
Besseron, Xavier  ;  University of Luxembourg > Faculty of Science, Technology and Communication (FSTC) > Engineering Research Unit
Peters, Bernhard ;  University of Luxembourg > Faculty of Science, Technology and Communication (FSTC) > Engineering Research Unit
External co-authors :
no
Language :
English
Title :
Parallelizing XDEM: Load-balancing policies and efficiency, a study
Publication date :
September 2017
Event name :
International Conference on Particle-Based Methods (PARTICLES17)
Event place :
Hannover, Germany
Event date :
from 26-09-2017 to 28-09-2017
Audience :
International
Focus Area :
Computational Sciences
Name of the research project :
Luxdem.LSDEM
Available on ORBilu :
since 05 November 2017

Statistics


Number of views
151 (30 by Unilu)
Number of downloads
94 (22 by Unilu)

Bibliography


Similar publications



Contact ORBilu