SpiNNaker brain simulation machine

Last updated: Aug 14, 2012

SpiNNaker brain machine SpiNNaker is a massively parallel, low power, neuromorphic supercomputer currently being built at Manchester University in the UK. It is designed to model very large, biologically realistic, spiking neural networks in real time. The machine will consist of 65,536 identical 18-core processors, giving it 1,179,648 cores in total. Each processor has an on-board router to form links with its neighbours, as well as its own 128 MB of memory to hold synaptic weights. Each core is an ARM968 manufactured using a 130 nm process.

The machine is built to mimic the brain's biological structure and behaviour. It will exhibit massive parallelism and resilience to failure of individual components. With over one million cores, and one thousand simulated neurons per core, the machine will be capable of simulating one billion neurons. This equates to just over 1% of the human brain's 85 billion neurons.

Rather than implement one particular algorithm, SpiNNaker will be a platform on which different algorithms can be tested. Various types of neural networks can be designed and run on the machine, thus simulating different kinds of neurons and connectivity patterns. SpiNNaker is a contrived acronym derived from Spiking Neural Network Architecture.

SpiNNaker is a British project lead by Professor Steve Furber at Manchester University. Also involved are collaborators from the universities of Southampton, Cambridge, and Sheffield. The project started in 2005 and is currently funded by a UK government grant until early 2014. The microchips were manufactured and delivered to the lab in June 2011. A prototype with 864 cores was built in mid-2012. The full machine with over 1 million cores is expected to be complete by the end of 2013.

Contents    (hide)

Latest news

August 1, 2012  -   News article reveals that the current system is a single board containing 48 SpiNNaker chips (i.e. 864 ARM cores). At 1,000 neurons per core, this means the system could theoretically simulate 864,000 neurons. There have been no significant setbacks in the development, so work will continue to scale up to one million ARM cores.
May 11, 2012  -   Video of Professor Steve Furber giving a talk at Edinburgh University entitled "Building brains".
April 13, 2012  -   Live-blog mention of the SpiNNaker project and a "demo of a robot controlled by a neural network".
April 13, 2012  -   Paper describes four SpiNNaker chips simulating, in real time, a cortical circuit of 10k spiking neurons and 4 million synapses.

Hardware description

The SpiNNaker machine is comprised of up to 65,536 custom-built microchips. Each chip is connected to six neighbours, forming a toroidal network.

One chip contains 18 identical fasicles clocked at 200 MHz. A fasicle contains an ARM968 processor core, 32 kB of instruction memory, 64 kB of data memory, three controllers, a clock, and a timer.

Each multiprocessor chip has about 100 million transistors, most of which are in the 55 blocks of 32 kB SRAM local instruction and data memory. They were manufactured using an 130 nm process. Although the ARM968 is relatively old, it is used because the licensing agreement was committed to back in 2005.

On a separate die, but within the same chip package, is a 128 MB DDR SDRAM memory chip that operates at up to 166 MHz. This has about a billion transistors. The multiprocessor and memory chips are packaged together, one above the other, in a 19x19mm 300-pin ball grid array.

Each core dissipates 1 Watt of energy. The SpiNNaker machine is expected to consume 50-100 kW peak, although the average is predicted to be well below 50 kW. For comparison, the average human brain consumes around 20 W.

The finished million-processor machine will occupy several cabinets. At least six to eight, possibly more if the power density turns out to be an issue.

A possible configuration would be: 48 chips per board, 12 boards per rack, 20 racks per cabinet, 6 cabinets. This is a purely speculative configuration dreamt up by this article's author.

Modelling capabilities

The SpiNNaker machine has a million processor cores. Each core can model a variable number of neurons, but a typical number will be a thousand. This makes for a total of a billion simulated neurons. SpiNNaker is thus about 1% the size of the human brain, which has about 85 billion neurons.

Each processor core is programmable. It can implement any model that fits in its 32 kB instruction memory. In this sense the SpiNNaker machine can be considered an FPGA for neurons.

Signalling within the SpiNNaker chip is enterely digital, not analog. Each spike is a 40-bit packet containing a 32-bit identifier of the source neuron.

Each chip connected, asynchronously to six neighbours. The topology of the simulated neural network, however, is completely independent of the physical hardware design. In a typical simulation a neuron would have around 1,000 synapses.

It is anticipated that the machine will be useful for modelling and understanding the processes of learning, memory, and STDP in spiking neural networks.

Chip manufacture

The SpiNNaker machine and its multiprocessor chips were designed in Manchester, UK. The multiprocessor die were manufactured by United Microelectronics Corporation (UMC) in Taiwan using a 130 nm process. The accompanying memory die is an off-the-shelf 128 MB DDR SDRAM from Micron Technology in Idaho, US. The multiprocessor and memory were mounted together, one above the other, in a 300-BGA package. The packaging was done by Unisem Europe near Crumlin, Wales.

Future prospects

The SpiNNaker machine, when complete by the end of 2013, will be able to simulate around 1 billion neurons. This equates to just over 1% of the human brain's 85 billion neurons. If the system proves successful then similar machines can be built to take advantage of more advanced processors. For example, the 130 nm process used for the SpiNNaker chips is over a decade old - this process was used for the consumer processors that went on sale starting in 2001. If a more modern process were used, for example 22 nm as used in 2012's consumer-level devices, then power consumption could be reduced by a factor of 10.

The leaders of the SpiNNaker project have agreed to participate in the Human Brain Project (HBP) if it's approved. The HBP is a proposed 10-year, EU-funded project to understand the human brain. A decision on whether it'll get the funding go-ahead is due in February 2013. If the HBP does get approved, this could possibly provide at least partial funding for continued SpiNNaker development through until 2023. See page 27 of the HBP report.

Development timeline

2005  May - ARM approached
2006  Architectural commitments made
2009  Prototype chips made, and a four-chip test board evaluated
2011  Final SpiNNaker chips delivered to the lab in Manchester
2012  July - Partial machine built, one board containing 48 chips
2013  December - Full million-core machine expected to be complete
2014  Current funding expires


Current funding is a £4,906,665 UK government grant from the EPSRC. That is split between four universities as follows:

  • Professor S B Furber, Manchester, UKP 2,707,120, 01.Jan.2009 - 31.Dec.2013 G015740
  • Professor AD Brown, southampton, UKP 892,622, 01.Mar.2010 - 28.Feb.2014 G015775
  • Dr SW Moore, Cambridge, UKP 723,230, 01.Apr.2009 - 31.Mar.2014 G015783
  • Professor DJ Allerton, Sheffield, UKP 583,693, 15.Jun.2009 - 14.Jun.2014 D07908X

Previous funding:

  • D07908X £637,840 to manchester, 1.oct.2006 - 31.Mar.2010
  • D079594 £393,925 to southhampton, 1.oct.2006 - 31.Mar.2010

People involved

SpiNNaker is a British project is being developed at the universities of Manchester, Southampton, Cambridge, and Sheffield. It is lead by Professor Steve Furber in Manchester. Steve co-designed the BBC Micro processor system and the original ARM microprocessor. List of other staff.

Alex Rast   Homepage
Manchester, research staff 
  Alex Cope  
Sheffield research staff 
  Andrew Brown  
Southampton academic staff 
Cameron Patterson   Linkedin profile Twitter profile Homepage Homepage
Manchester, research student 
  Dave Allerton  
Sheffield academic staff 
  David Lester   Homepage
Manchester, academic staff 
Eustace Painkras   Linkedin profile Homepage
Manchester, research staff 
  Evangelos Stromatias   Google profile Homepage
Manchester, research student 
  Francesco Galluppi   Homepage
Manchester, research student 
James Garside   Homepage
Manchester, academic staff 
  Javier Navaridas   Homepage
Manchester, academic staff 
  Jeff Reeve  
Southampton academic staff 
John Woods   Homepage
Manchester, research staff 
  Julian Bailey  
Southampton research staff 
  Kevin Gurney  
Sheffield academic staff 
Kier Dugan  
Southampton research staff 
  Luis Plana   Homepage
Manchester, research staff 
  Martin Grymel   Homepage
Manchester, research student 
Paul Richmond  
Sheffield research staff 
  Paul Fox  
Cambridge research staff 
  Paul Fox  
Sheffield research staff 
Peter Wilson  
Southampton academic staff 
  Rob Mills  
Southampton research staff 
  Sergio Davies   Linkedin profile Homepage
Manchester, research student 
Simon Moore  
Cambridge academic staff 
  Simon Davidson   Linkedin profile Homepage
Manchester, research staff 
  Steve Furber   Google profile Linkedin profile Wikipedia page Homepage
Project leader, Manchester 
Steve Marsh  
Cambridge research staff 
  Steve Temple   Homepage
Manchester, research staff 
  Theo Markettos  
Cambridge research staff 
Thomas Sharp   Homepage Homepage
Manchester, research student 

Research papers