The load balancing algorithm based on the parallel implementation of IPO and FMM

Authors:
Ting Wang;Yue Hu;Yanbao Cui;Weiqin Tong;Xiaoli Zhi
Affiliations:
Computer engineering and science college, Shanghai University, Shanghai, China;Computer engineering and science college, Shanghai University, Shanghai, China;Computer engineering and science college, Shanghai University, Shanghai, China;Computer engineering and science college, Shanghai University, Shanghai, China;Computer engineering and science college, Shanghai University, Shanghai, China
Venue:
HPCA'09 Proceedings of the Second international conference on High Performance Computing and Applications
Year:
2009

Citing 5
Cited 0

A comparison of parallel programming models for multiblock flow computations

Journal of Computational Physics
Communicating across parallel message-passing environments

Journal of Systems Architecture: the EUROMICRO Journal - Special double issue: cluster computing
PLUM: parallel load balancing for adaptive unstructured meshes

Journal of Parallel and Distributed Computing
A Distributed Computing Center Software for the Efficient Use of Parallel Computer Systems

HPCN Europe 1994 Proceedings of the nternational Conference and Exhibition on High-Performance Computing and Networking Volume II: Networking and Tools
On the Parallelization of Electrodynamic Multilevel Fast Multipole Method on Distributed Memory Computers

IWIA '99 Proceedings of the 1999 International Workshop on Innovative Architecture

Quantified Score

Hi-index	0.00

Visualization

Abstract

The large scale arbitrary cavity scattering problems can be tackled by parallel computing approach. This paper proposes a new method to distribute cavity scattering computing tasks on multiprocessors computer based on the IPO and FMM. The samples of IPO and FMM pattern can be divided into eight blocks, and this paper just analyzes the load balancing of the block in the lower-left corner using the invariability of angle. So this problem can be transformed into how to equally distribute an N*N matrix on P processors. Two matrix partitioning algorithms are introduced, and experimental results show that the optimal sub-structure algorithm is able to balance the load among multiprocessors effectively, thereby, improving the performance of the entire system.