A scalable chip multiprocessor for large-scale neural simulation
Lead Research Organisation:
University of Southampton
Department Name: Electronics and Computer Science
Abstract
See Joint Proposal D232208
Publications
Andrew Brown (Author)
(2006)
Grand Challenges in Microelectronic Design
Brown A
(2009)
Advances in Neuro-Information Processing
Dugan K
(2013)
Interconnection system for the SpiNNaker biologically inspired multi-computer
in IET Computers & Digital Techniques
Painkras E
(2013)
SpiNNaker: A 1-W 18-Core System-on-Chip for Massively-Parallel Neural Network Simulation
in IEEE Journal of Solid-State Circuits
Furber S
(2013)
Overview of the SpiNNaker System Architecture
in IEEE Transactions on Computers
| Description | The human brain remains as one of the great frontiers of science - how does this organ upon which we all depend so critically actually do its job? A great deal is known about the underlying technology - the neuron - and we can observe large-scale brain activity through techniques such as magnetic resonance imaging, but this knowledge barely starts to tell us how the brain works. Something is happening at the intermediate levels of processing that we have yet to begin to understand, but the essence of the brain's information processing function probably lies in these intermediate levels. To get at these middle layers requires that we build models of very large systems of spiking neurons, with structures inspired by the increasingly detailed findings of neuroscience, in order to investigate the emergent behaviours of those systems. High-performance microprocessors have reached a brick wall in terms of improving single-thread performance. The technology advances that have delivered exponential performance gains over the last 3 decades will not deliver the same gains in the future, and a new approach is required. Industry giants, including Intel, are all agreed that the continuing increases in chip transistor count can no longer be turned into making one processor faster, but should instead be turned into putting more processors onto a chip. This delivers more total performance, but through parallelism, not single-thread performance. The grant was an early stepping stone to a much larger vision of creating a system containing a million cores; (subsequently funded by EPSRC EP/D079594/1, Samsung and others). "Project findings" is not really an appropriate term. It was an (extremely successful) enabling project. |
| Exploitation Route | See "potential use" in the follow-on project, EPSRC EP/D079594/1. See "exploitation routes" in the follow-on project, EPSRC EP/D079594/1. |
| Sectors | Digital/Communication/Information Technologies (including Software),Electronics,Pharmaceuticals and Medical Biotechnology |
| URL | http://www.cs.manchester.ac.uk/apt |
| Description | See apt/cs/manchester.ac.uk/projects/SpiNNaker |
| First Year Of Impact | 2008 |
| Sector | Digital/Communication/Information Technologies (including Software) |
| Description | A R M Ltd |
| Organisation | Arm Limited |
| Country | United Kingdom |
| Sector | Private |
| Start Year | 2006 |
| Description | Silistix Ltd |
| Organisation | Silistix Ltd |
| Country | United Kingdom |
| Sector | Private |
| Start Year | 2006 |