Mapping graphs Of parallel programs onto graphs of distributed computer systems by recurrent neural networks

Authors:
M. S. Tarkov;A. V. Rzhanov'S
Affiliations:
Institute of Semiconductor Physics, Siberian branch, Russian Academy of Sciences, Novosibirsk, Russia 630090;Institute of Semiconductor Physics, Siberian branch, Russian Academy of Sciences, Novosibirsk, Russia 630090
Venue:
Optical Memory and Neural Networks
Year:
2011

Citing 3
Cited 0

Self-stabilizing systems in spite of distributed control

Communications of the ACM
Neural Networks for Combinatorial Optimization: a Review of More Than a Decade of Research

INFORMS Journal on Computing
Topology mapping for Blue Gene/L supercomputer

Proceedings of the 2006 ACM/IEEE conference on Supercomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

A problem of mapping graphs of parallel programs onto graphs of distributed computer systems by recurrent neural network is formulated. Parameter values providing absence of incorrect solutions are experimentally determined. Because of introduction of penalty coefficient into Lyapunov function for the program graph edges non-coincided with the system graph edges, optimal solutions are found for mapping a "line"-graph onto a two-dimensional torus. For increasing probability of finding optimal mapping, a method for splitting the mapping is proposed. The method essence is a reducing solution matrix to a block-diagonal form. The Wang recurrent neural network is used to exclude incorrect solutions of the problem of mapping the line-graph onto a three-dimensional torus. This network converges quicker than the Hopfield one.