Understanding the interconnection network of SpiNNaker

SpiNNaker is a massively parallel architecture designed to model large-scale spiking neural networks in (biological) real-time. Its design is based around ad-hoc multi-core System-on-Chips which are interconnected using a two-dimensional toroidal triangular mesh. Neurons are modeled in software and their spikes generate packets that propagate through the on- and inter-chip communication fabric relying on custom-made on-chip multicast routers. This paper models and evaluates large-scale instances of its novel interconnect (more than 65 thousand nodes, or over one million computing cores), focusing on real-time features and fault-tolerance. The key contribution can be summarized as understanding the properties of the feasible topologies and establishing the stable operation of the SpiNNaker under different levels of degradation. First we derive analytically the topological characteristics of the network, which are later confirmed by experimental work. With the computational model developed, we investigate the topology of SpiNNaker, and compare it with a standard 3-dimensional torus. The novel emergency routing mechanism, implemented within the routers, allows the topology of SpiNNaker to be more robust than the 3-dimensional torus, regardless of the latter having better topological characteristics. Furthermore, we obtain optimal values of two router parameters related with livelock and deadlock avoidance mechanisms.

[1]  M. Geike,et al.  Emulation engine for spiking neurons and adaptive synaptic weights , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[2]  Stephen B. Furber,et al.  Efficient modelling of spiking neural networks on a scalable chip multiprocessor , 2008, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).

[3]  William J. Dally,et al.  Principles and Practices of Interconnection Networks , 2004 .

[4]  Luis A. Plana,et al.  SpiNNaker: Mapping neural networks onto a massively-parallel chip multiprocessor , 2008, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).

[5]  Krste Asanovic,et al.  Parallel neural network training on Multi-Spert , 1997, Proceedings of 3rd International Conference on Algorithms and Architectures for Parallel Processing.

[6]  Steve B. Furber,et al.  Neural Systems Engineering , 2008, Computational Intelligence: A Compendium.

[7]  Philip Heidelberger,et al.  IBM Research Report Design and Analysis of the BlueGene/L Torus Interconnection Network , 2003 .

[8]  Hans Werner Meuer,et al.  Top500 Supercomputer Sites , 1997 .

[9]  Valentin Puente,et al.  Immucube: Scalable Fault-Tolerant Routing for k-ary n-cube Networks , 2007, IEEE Transactions on Parallel and Distributed Systems.

[10]  Luis A. Plana,et al.  A GALS Infrastructure for a Massively Parallel Multiprocessor , 2007, IEEE Design & Test of Computers.

[11]  José Miguel-Alonso,et al.  INSEE: An Interconnection Network Simulation and Evaluation Environment , 2005, Euro-Par.

[12]  Peter Dayan,et al.  Theoretical Neuroscience: Computational and Mathematical Modeling of Neural Systems , 2001 .

[13]  Andrew D. Brown,et al.  On-chip and inter-chip networks for modeling large-scale neural systems , 2006, 2006 IEEE International Symposium on Circuits and Systems.

[14]  Antonio Robles,et al.  A routing methodology for achieving fault tolerance in direct networks , 2006, IEEE Transactions on Computers.

[15]  Terry Elliott,et al.  Developmental robotics: manifesto and application , 2003, Philosophical Transactions of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[16]  José-Ángel Gregorio,et al.  Improving the performance of large interconnection networks using congestion-control mechanisms , 2008, Perform. Evaluation.

[17]  Jerome A. Feldman,et al.  A supercomputer for neural computation , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[18]  Steve B. Furber,et al.  An On-Chip and Inter-Chip Communications Network for the SpiNNaker Massively-Parallel Neural Net Simulator , 2008, Second ACM/IEEE International Symposium on Networks-on-Chip (nocs 2008).

[19]  Javier Navaridas,et al.  Mixed-radix Twisted Torus Interconnection Networks , 2007, 2007 IEEE International Parallel and Distributed Processing Symposium.

[20]  Javier Navaridas,et al.  Reducing complexity in tree-like computer interconnection networks , 2010, Parallel Comput..

[21]  Cruz Izu,et al.  The Adaptive Bubble Router , 2001, J. Parallel Distributed Comput..