SpiNNaker 2: A 10 Million Core Processor System for Brain Simulation and Machine Learning

TL;DR

SpiNNaker 2 is a massively scalable ARM-based processor system designed for advanced brain simulation and machine learning, featuring power-efficient technology, numerical accelerators, and expanded application potential beyond neuroscience.

Contribution

This paper presents the design and roadmap of SpiNNaker 2, a 10 million core processor system with enhanced power management and accelerators, significantly increasing simulation capacity and application scope.

Findings

Simulation capacity increased by over 50 times

Power consumption optimized through adaptive body biasing

Enhanced utility for neural network simulation and AI applications

Abstract

SpiNNaker is an ARM-based processor platform optimized for the simulation of spiking neural networks. This brief describes the roadmap in going from the current SPINNaker1 system, a 1 Million core machine in 130nm CMOS, to SpiNNaker2, a 10 Million core machine in 22nm FDSOI. Apart from pure scaling, we will take advantage of specific technology features, such as runtime adaptive body biasing, to deliver cutting-edge power consumption. Power management of the cores allows a wide range of workload adaptivity, i.e. processor power scales with the complexity and activity of the spiking network. Additional numerical accelerators will enhance the utility of SpiNNaker2 for simulation of spiking neural networks as well as for executing conventional deep neural networks. These measures should increase the simulation capacity of the machine by a factor $>$50. The interplay between the two domains, i.e. spiking and rate based, will provide an interesting field for algorithm exploration on SpiNNaker2. Apart from the platforms' traditional usage as a neuroscience exploration tool, the extended functionality opens up new application areas such as automotive AI, tactile internet, industry 4.0 and biomedical processing.