Title :
Mapping of finite-element grids onto parallel computers using neural networks
Author :
Tan, Rudy S. ; Narasimhan, V. Lakshmi
Abstract :
In this paper, LSOM (Load-balancing Self-Organizing Map), a neural network based on Kohonen´s self-organizing map is proposed for the problem of mapping finite-element method (FEM) grids to distributed-memory parallel computers with mesh interconnection networks. The rough global ordering produced by LSOM is then combined with the local refinement Kernighan-Lin algorithm (called LSOM-KL) to obtain the solution. LSOM-KL obtained a load imbalance of less than 0.1% and a low number of hops, comparable to results obtained with commonly used recursive bisection methods
Keywords :
distributed memory systems; finite element analysis; mathematics computing; multiprocessor interconnection networks; parallel machines; resource allocation; self-organising feature maps; LSOM; distributed-memory parallel computers; finite-element method grid mapping; load-balancing self-organizing map; local refinement Kernighan-Lin algorithm; mesh interconnection networks; neural networks; recursive bisection methods; rough global ordering; Computer network reliability; Computer networks; Concurrent computing; Distributed computing; Finite element methods; Grid computing; Load management; Multiprocessor interconnection networks; Network topology; Neural networks;
Conference_Titel :
Algorithms and Architectures for Parallel Processing, 1997. ICAPP 97., 1997 3rd International Conference on
Conference_Location :
Melbourne, Vic.
Print_ISBN :
0-7803-4229-1
DOI :
10.1109/ICAPP.1997.651533
