SpiNNaker: A 1-W 18-Core System-on-Chip for Massively-Parallel Neural Network Simulation

Solid-State Circuits, IEEE Journal of(2013)

引用 442|浏览16
The modelling of large systems of spiking neurons is computationally very demanding in terms of processing power and communication. SpiNNaker - Spiking Neural Network architecture - is a massively parallel computer system designed to provide a cost-effective and flexible simulator for neuroscience experiments. It can model up to a billion neurons and a trillion synapses in biological real time. The basic building block is the SpiNNaker Chip Multiprocessor (CMP), which is a custom-designed globally asynchronous locally synchronous (GALS) system with 18 ARM968 processor nodes residing in synchronous islands, surrounded by a lightweight, packet-switched asynchronous communications infrastructure. In this paper, we review the design requirements for its very demanding target application, the SpiNNaker micro-architecture and its implementation issues. We also evaluate the SpiNNaker CMP, which contains 100 million transistors in a 102-mm2 die, provides a peak performance of 3.96 GIPS, and has a peak power consumption of 1 W when all processor cores operate at the nominal frequency of 180 MHz. SpiNNaker chips are fully operational and meet their power and performance requirements.
microprocessor chips,neural net architecture,parallel architectures,system-on-chip,ARM968 processor node,CMP,SpiNNaker chip multiprocessor,cost effective simulator,custom designed globally asynchronous locally synchronous system,flexible simulator,massively parallel neural network simulation,neuroscience experiment,packet switched asynchronous communications,parallel computer system,power 1 W,spiking neural network architecture,spiking neuron,synchronous island,system-on-chip,Asynchronous interconnect,chip multiprocessor,energy efficiency,globally asynchronous locally synchronous (GALS),network-on-chip,neuromorphic hardware,real-time simulation,spiking neural networks (SNNs)
AI 理解论文
Chat Paper