NASA Logo

NTRS

NTRS - NASA Technical Reports Server

Back to Results
Dynamic Load Balancing for Adaptive Meshes using Symmetric Broadcast NetworksMany scientific applications involve grids that lack a uniform underlying structure. These applications are often dynamic in the sense that the grid structure significantly changes between successive phases of execution. In parallel computing environments, mesh adaptation of grids through selective refinement/coarsening has proven to be an effective approach. However, achieving load balance while minimizing inter-processor communication and redistribution costs is a difficult problem. Traditional dynamic load balancers are mostly inadequate because they lack a global view across processors. In this paper, we compare a novel load balancer that utilizes symmetric broadcast networks (SBN) to a successful global load balancing environment (PLUM) created to handle adaptive unstructured applications. Our experimental results on the IBM SP2 demonstrate that performance of the proposed SBN load balancer is comparable to results achieved under PLUM.
Document ID
20020052635
Acquisition Source
Ames Research Center
Document Type
Preprint (Draft being sent to journal)
Authors
Das, Sajal K.
(University of North Texas Denton, TX United States)
Harvey, Daniel J.
(University of North Texas Denton, TX United States)
Biswas, Rupak
(MRJ Technology Solutions, Inc. Moffett Field, CA United States)
Saini, Subhash
Date Acquired
August 20, 2013
Publication Date
January 1, 1998
Subject Category
Communications And Radar
Meeting Information
Meeting: 12th ACM International Conference on Supercomputing
Location: Melbourne
Country: Australia
Start Date: July 13, 1998
End Date: July 17, 1998
Sponsors: Association for Computing Machinery
Funding Number(s)
CONTRACT_GRANT: NAS2-14303
PROJECT: RTOP 519-40-12
Distribution Limits
Public
Copyright
Work of the US Gov. Public Use Permitted.
Document Inquiry

Available Downloads

There are no available downloads for this record.
No Preview Available