Paper Info
Title
Analytical Assessment of the Suitability of Multicast Communications for the SpiNNaker Neuromimetic System
Abstract
SpiNNaker is a custom-made architecture designed to model large-scale spiking neural nets. One of the most significant characteristics of neural nets is their extreme communication needs; each neuron propagates its activation to thousands of other neurons. This paper shows analytical proof that the novel multicast router in SpiNNaker is a better solution for simulating neural nets than more powerful point-to-point routers such as those found on datacentres or high performance computing systems, even when it has significantly lower requirements in terms of complexity, area and power. First, we characterised the utilization of resources required by both multicast and unicast networks. Then we derived the band-width needs of different communication architectures. Finally, we derived the amount of neurons the different networks can support. From these analyses we determined that the multicast communications adopted in SpiNNaker will be able to support the target application under the expected operation conditions.
Year
DOI
Venue
2012
10.1109/HPCC.2012.11
HPCC-ICESS
Keywords
Field
DocType
different communication architecture,multicast communications,extreme communication need,analytical proof,band-width need,analytical assessment,different network,multicast communication,large-scale spiking neural net,better solution,novel multicast router,spinnaker neuromimetic system,neural net,high performance computing,communication complexity,network routing,neurophysiology,parallel processing,resource allocation,massively parallel processing,biomimetics,neural nets,decision support systems
Supercomputer,Massively parallel,Computer science,Parallel computing,Computer network,Communication complexity,Resource allocation,Router,Unicast,Multicast,Artificial neural network,Distributed computing
Conference
ISSN
ISBN
Citations 
2576-3504
978-1-4673-2164-8
3
PageRank 
References 
Authors
0.36
17
6
Name
Order
Citations
PageRank
Javier Navaridas120123.58
Mikel Luján254046.40
L. A. Plana378659.01
Jose Miguel-Alonso432214.96
S. B. Furber51484179.05
Miguel-Alonso, J.630.36