Please use this identifier to cite or link to this item: http://hdl.handle.net/2440/108407
Type: Conference paper
Title: A network-based communication platform for a cognitive computer
Author: Numan, M.
Frost, J.
Phillips, B.
Liebelt, M.
Citation: Proceedings of the 3rd International Workshop on Artificial Intelligence and Cognition, 2015 / Lieto, A., Battaglino, C., Radicioni, D., Sanguinetti, M. (ed./s), vol.1510, pp.94-103
Publisher: RWTH Aachen * Lehrstuhl Informatik V
Issue Date: 2015
Series/Report no.: AI*IA
ISSN: 1613-0073
Conference Name: International Workshop on Artificial Intelligence and Cognition (AIC) (28 Sep 2015 - 29 Sep 2015 : Turin, Italy)
Statement of
Responsibility: 
Mostafa W. Numan, Jesse Frost, Braden J. Phillips, and Michael Liebelt
Abstract: Street is a reconfigurable parallel computer architecture. It executes a production language directly in hardware with the aim of realising advanced cognitive agents in a more energy efficient manner than conventional computers. Street requires frequent communication between many processing elements and to make this communication more energy efficient, a network-based communication platform, StreetNet, is proposed in this paper. It maps the processing elements onto a 2D mesh architecture optimized according to the data dependencies between them. A deadlock-free deterministic routing function is considered for this platform along with the concept of sleep period, analogous to human sleeping, to reorganize the placements of processing elements based on runtime traffic statistics. These mechanisms serve to reduce total network traffic and hence minimise energy consumption.
Keywords: Cognitive computer; computer architecture; networks-on- chip; mapping
Rights: Copyright © 2015 for the individual papers by the papers' authors. Copying permitted for private and academic purposes. This volume is published and copyrighted by its editors.
RMID: 0030045772
Published version: http://ceur-ws.org/Vol-1510/
Appears in Collections:Electrical and Electronic Engineering publications

Files in This Item:
File Description SizeFormat 
hdl_108407.pdfPublished version398.71 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.