Title
Scalable communications for a million-core neural processing architecture
Abstract
The design of a new high-performance computing platform to model biological neural networks requires scalable, layered communications in both hardware and software. SpiNNaker's hardware is based upon Multi-Processor System-on-Chips (MPSoCs) with flexible, power-efficient, custom communication between processors and chips. The architecture scales from a single 18-processor chip to over 1 million processors and to simulations of billion-neuron, trillion-synapse models, with tens of trillions of neural spike-event packets conveyed each second. The communication networks and overlying protocols are key to the successful operation of the SpiNNaker architecture, designed together to maximise performance and minimise the power demands of the platform. SpiNNaker is a work in progress, having recently reached a major milestone with the delivery of the first MPSoCs. This paper presents the architectural justification, which is now supported by preliminary measured results of silicon performance, indicating that it is indeed scalable to a million-plus processor system.
Year
DOI
Venue
2012
10.1016/j.jpdc.2012.01.016
J. Parallel Distrib. Comput.
Keywords
Field
DocType
scalable communication,silicon performance,neural spike-event packet,new high-performance computing platform,million-core neural processing architecture,architecture scale,18-processor chip,biological neural network,custom communication,spinnaker architecture,communication network,layered communication,neuromorphic,network on chip,hpc
Telecommunications network,Work in process,Computer science,Parallel computing,Network packet,Neuromorphic engineering,Network on a chip,Chip,Software,Embedded system,Scalability,Distributed computing
Journal
Volume
Issue
ISSN
72
11
0743-7315
Citations 
PageRank 
References 
6
0.66
29
Authors
8
Name
Order
Citations
PageRank
Cameron Patterson191.73
Jim Garside2485.52
Eustace Painkras31477.33
Steve Temple451535.17
L. A. Plana578659.01
Javier Navaridas620123.58
Thomas Sharp7413.43
S. B. Furber81484179.05