The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.12 - Dec. (2013 vol.62)
pp: 2454-2467
Steve B. Furber , The University of Manchester, Manchester
David R. Lester , The University of Manchester, Manchester
Luis A. Plana , The University of Manchester, Manchester
Jim D. Garside , The University of Manchester, Manchester
Eustace Painkras , The University of Manchester, Manchester
Steve Temple , The University of Manchester, Manchester
Andrew D. Brown , University of Southampton, Southampton
ABSTRACT
SpiNNaker (a contraction of Spiking Neural Network Architecture) is a million-core computing engine whose flagship goal is to be able to simulate the behavior of aggregates of up to a billion neurons in real time. It consists of an array of ARM9 cores, communicating via packets carried by a custom interconnect fabric. The packets are small (40 or 72 bits), and their transmission is brokered entirely by hardware, giving the overall engine an extremely high bisection bandwidth of over 5 billion packets/s. Three of the principal axioms of parallel machine design (memory coherence, synchronicity, and determinism) have been discarded in the design without, surprisingly, compromising the ability to perform meaningful computations. A further attribute of the system is the acknowledgment, from the initial design stages, that the sheer size of the implementation will make component failures an inevitable aspect of day-to-day operation, and fault detection and recovery mechanisms have been built into the system at many levels of abstraction. This paper describes the architecture of the machine and outlines the underlying design philosophy; software and applications are to be described in detail elsewhere, and only introduced in passing here as necessary to illuminate the description.
INDEX TERMS
Network architecture, Program processors, Biological system modeling, Computer architecture, Neural networks, real-time distributed, Interconnection architectures, parallel processors, neurocomputers
CITATION
Steve B. Furber, David R. Lester, Luis A. Plana, Jim D. Garside, Eustace Painkras, Steve Temple, Andrew D. Brown, "Overview of the SpiNNaker System Architecture", IEEE Transactions on Computers, vol.62, no. 12, pp. 2454-2467, Dec. 2013, doi:10.1109/TC.2012.142
REFERENCES
[1] SpiNNaker Project Website : http://apt.cs.man.ac.uk/projectsSpiNNaker /, 2013.
[2] L.A. Plana, D. Clark, S. Davidson, S. Furber, J. Garside, E. Painkras, J. Pepper, S. Temple, and J. Bainbridge, "SpiNNaker: Design and Implementation of a GALS Multi-Core System-on-Chip," ACM J. Emerging Technologies in Computing Systems, vol. 7, no. 4,article 17, pp. 17:1-17:18, Dec. 2011.
[3] X. Jin, M. Lujan, L.A. Plana, S. Davies, S. Temple, and S. Furber, "Modeling Spiking Neural Networks on SpiNNaker," Computing in Science & Eng., vol. 12, no. 5, pp. 91-97, Sept./Oct. 2010.
[4] S.B. Furber and S. Temple, "Neural Systems Engineering," J. The Royal Soc. Interface, vol. 4, no. 13, pp. 193-206, Apr. 2007, doi:10.1098/rsif.2006.0177.
[5] B. Pakkenberg, D. Pelvig, L. Marner, M.J. Bundgaard, H.J.G. Gundersen, J.R. Nyengaard, and L. Regeur, "Aging and the Human Neocortex," Experimental Gerontology, vol. 38, nos. 1/2, pp. 95-99, Jan./Feb. 2003.
[6] D. Purves, G.J. Augustine, D. Fitzpatrick, W.C. Hall, A.-S. LaMantia, J.O. McNamara, and L.E. White, eds., Neuroscience, fourth ed. Sinauer Assoc. 2008.
[7] C.U.M. Smith, Elements of Molecular Neurobiology, third ed. Wiley, 2002.
[8] M. Mahowald, An Analog VLSI System for Stereoscopic Vision. Kluwer Academic Publishers, 1994.
[9] M. Sivilotti, "Wiring Considerations in Analog VLSI Systems, with Application to Field-Programmable Networks," PhD dissertation, California Inst. of Technology, Pasadena, CA, 1991.
[10] H. Markram, "The Blue Brain Project," Nature Rev. Neuroscience, vol. 7, pp. 153-160, Feb. 2006, doi:10.1038/nrn1848.
[11] IBM Blue Gene Team, "Overview of the IBM Blue Gene/P Project," , IBM J. Research and Development, vol. 52, nos. 1/2, pp. 199-220, Jan. 2008.
[12] R. Ananthanarayanan, S.K. Esser, H.D. Simon, and D.S. Modha, "The Cat Is Out of the Bag: Cortical Simulations with $10^{9}$ Neurons and $10^{13}$ Synapses," Proc. ACM/IEEE Conf. Supercomputing, pp. 1-12, 2009.
[13] E.M. Izhikevich, "Simulation of Large-Scale Brain Models," www.nsi.edu/users/izhikevich/interestindex.htm , 2005.
[14] E.M. Izhikevich and G.M. Edelman, "Large-Scale Model of Mammalian Thalamocortical Systems," Proc. Nat'l Academy of Sciences of USA, vol. 105, no. 9, pp. 3593-3598, Feb. 2008, doi: 10.1073/pnas.0712231105.
[15] J. Bainbridge, "The CHAIN Works Tool Suite: A Complete Industrial Design Flow for Networks-on-Chips," Networks-on-Chips: Theory and Practice, F. Gebali, H. Elmilgi, and M.W. El-Kharashi eds., pp. 281-306, Taylor & Francis, Inc., 2009.
[16] ARM968E-S Tech. Ref. Manual, ARM DDI 0311C, 2004.
[17] AMBA Design Kit Tech. Ref. Manual, ARM DDI 0243A, 2003.
[18] T. Sharp, L.A. Plana, F. Galluppi, and S.B. Furber, "Event-Driven SpiNNaker Simulation," Proc. Int'l Conf. Neural Information Processing (ICONIP '11), pp. 424-430, 2011.
[19] ARM PL190 Tech. Ref. Manual, ARM DDI 0181E, 2004.
[20] J. Wu and S.B. Furber, "A Multicast Routing Scheme for a Universal Spiking Neural Network Architecture," The Computer J., vol. 53, no. 3, pp. 280-288, 2010, doi:10.1093/comjnl/bxp024.
[21] I. Koren and C. Krishna, Fault-Tolerant Systems. Morgan Kaufmann, 2007.
[22] L.A. Plana, S.B. Furber, S. Temple, M. Khan, Y. Shi, J. Wu, and S. Yang, "A GALS Infrastructure for a Massively Parallel Multiprocessor," IEEE Design & Test of Computers, vol. 24, no. 5, pp. 454-463, Sept. 2007, doi:10.1109/MDT.2007.149.
[23] L.D. Solano-Quinde and B.M. Bode, "Module Prototype for Online Failure Prediction for the IBM Blue Gene/L," Proc. IEEE Electro/Information Technology Conf. (EIT '08), pp. 470-474, May 2008, doi:10.1109/EIT.2008.4554349.
[24] A.P. Davison, D. Brüderle, J.M. Eppler, J. Kremkow, E. Muller, D.A. Pecevski, L. Perrinet, and P. Yger P, "PyNN: A Common Interface for Neuronal Network Simulators," Frontiers Neuroinformatics, vol. 2, pp. 1-10, 2008, doi:10.3389/neuro.11.011.2008.
202 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool