Experience with automatic, dynamic load balancing and adaptive finite element computation

Author

Wheat, Stephen R. ; Devine, Karen D. ; Maccabe, Arthur B.

Author_Institution

MP Comput. Res. Lab., Sandia Nat. Labs., Albuquerque, NM, USA

Volume

2

fYear

1994

fDate

4-7 Jan. 1994

Firstpage

463

Lastpage

472

Abstract

We describe a fine-grained, element-based data migration system that dynamically maintains global load balance on massively parallel MIMD computers, and is effective in the presence of changing work loads. Global load balance is achieved by overlapping neighborhoods of processors. Where each neighborhood performs local load balancing. The method supports a large class of finite element and finite difference based applications and provides an automatic element management system to which applications are easily integrated. We test the system´s effectiveness with an adaptive order (p-) refinement discontinuous Galerkin finite element method for the solution of hyperbolic conservation laws on 1024-processor nCUBE2. The results show the significant reduction in execution time synergistically obtained by combining the automatic data migration system and the adaptive finite element method.<>

Keywords

computational complexity; distributed memory systems; finite difference methods; finite element analysis; parallel algorithms; resource allocation; adaptive finite element computation; automatic element management system; discontinuous Galerkin finite element method; distributed memory; dynamic load balancing; element-based data migration system; execution time; finite difference; hyperbolic conservation laws; massively parallel MIMD computers; nCUBE2;

fLanguage

English

Publisher

ieee

Conference_Titel

System Sciences, 1994. Proceedings of the Twenty-Seventh Hawaii International Conference on

Conference_Location

Wailea, HI, USA

Print_ISBN

0-8186-5090-7

Type

conf

DOI

10.1109/HICSS.1994.323237

Filename

323237