Predictive control of opto-electronic reconfigurable interconnection networks using neural networks

M. F. Sakr, S. P. Levitan, C. L. Giles, B. G. Horne, M. Maggini, D. M. Chiarulli

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Scopus citations

Abstract

Opto-electronic reconfigurable interconnection networks are limited by significant control latency when used in large multiprocessor systems. This latency is the time required to analyze the current traffic and reconfigure the network to establish the required paths. The goal of latency hiding is to minimize the effect of this control overhead. In this paper, we introduce a technique that performs latency hiding by learning the patterns of communication traffic and using that information to anticipate the need for communication paths. Hence, the network provides the required communication paths before a request for a path is made. In this study, the communication patterns (memory accesses) of a parallel program are used as input to a time delay neural network (TDNN) to perform on-line training and prediction. These predicted communication patterns are used by the interconnection network controller that provides routes for the memory requests. Based on our experiments, the neural network was able to learn highly repetitive communication patterns, and was thus able to predict the allocation of communication paths, resulting in a reduction of communication latency.

Original languageEnglish (US)
Title of host publicationInternational Conference on Massively Parallel Processing Using Optical Interconnections (MPPOI), Proceedings
Editors Anon
PublisherIEEE
Pages326-335
Number of pages10
StatePublished - 1995
EventProceedings of the 2nd International Conference on Massively Parallel Processing Using Optical Interconnections (MPPOI'95) - San Antonio, TX, USA
Duration: Oct 23 1995Oct 24 1995

Other

OtherProceedings of the 2nd International Conference on Massively Parallel Processing Using Optical Interconnections (MPPOI'95)
CitySan Antonio, TX, USA
Period10/23/9510/24/95

All Science Journal Classification (ASJC) codes

  • Computer Science(all)

Fingerprint Dive into the research topics of 'Predictive control of opto-electronic reconfigurable interconnection networks using neural networks'. Together they form a unique fingerprint.

Cite this