SpiNNaker
enabling brain-inspired AI
Manchester is the place where AI was born. It was conceived when Alan Turing, a resident academic, published Computing Machinery and Intelligence, the paper credited for starting modern thinking around AI.
75 years on, our researchers continue to lead the field, by creating the world’s largest neuromorphic computing platform, simulating brain circuits in biological real time.
20 years in conception and 15 in construction, the SpiNNaker (short for spiking neural network architecture) is a neuromorphic computing platform incorporating over one million ARM mobile phone processors and capable of modelling spiking neural networks at the scale of a mouse brain in biological real time.
This machine, hosted at The University of Manchester, provides cutting-edge research capability to advance our knowledge in neuroscience and computing.
Offering access to real-time brain modelling, it enables researchers to test new hypotheses about how the brain might work. It also aids the investigation of new computer architectures, helping to break the rules of conventional supercomputing to lead to new and advanced principles for energy-efficient brain-inspired AI.
Completely digital, it can be used in numerous experiments and applications and supports research across multiple sectors, including robotics, machine learning, computational and theoretical neuroscience, and art.
In addition to the million-core machine at Manchester, around 100 smaller SpiNNaker machines have been loaned and sold to research labs around the world. Examples of its impact include:
Enabling UK business MindTrace, in its early start-up phase, to generate new intellectual property described as “unique in the commercial world’’, and offering “substantial cost, energy efficiency and speed advantages over competitive approaches.’’
Stimulated industry-funded research, with an estimated total value of €60 million across projects including KI-ASIC, a venture between Infineon and BMW, and Scale4Edge, a collaboration between Infineon and Bosch.
Speak to our experts
Professor Steve Furber
ICL Professor of Computer Engineering
- Steve leads the SpiNNaker team and conceived the architectural innovations required to support real-time brain modelling back in2000 to 2005.
Dr Andrew Rowley
Senior Research Software Engineer
- Since 2014, Andrew has been leading the software development for SpiNNaker where, along with a team of Research Software Engineers, he has been designing and implementing the tools that allow large neural networks to be compiled and executed on the Million-core Machine and results to be read back and interpreted.
Dr Genting Liu
Research Associate in Neuromorphic Circuits and Systems
- Gengting has been working on the hardware design and low-level software system of the second-generation SpiNNaker machine, he joined the group in 2014 as a PhD candidate, he is one of the SpiNNaker2 chip designers, and is responsible for the design and implementation of the neuromorphic on-chip router.