Luis A. Plana

The SpiNNaker Project

The spiking neural network architecture (SpiNNaker) project aims to deliver a massively parallel million-core computer whose interconnect architecture is inspired by the connectivity characteristics of the mammalian brain, and which is suited to the modeling of large-scale spiking neural networks in biological real time. Specifically, the interconnect allows the transmission of a very large number of very small data packets, each conveying explicitly the source, and implicitly the time, of a single neural action potential or “spike.” In this paper, we review the current state of the project, which has already delivered systems with up to 2500 processors, and present the real-time event-driven programming model that supports flexible access to the resources of the machine and has enabled its use by a wide range of collaborators around the world.

Overview of the SpiNNaker System Architecture

SpiNNaker (a contraction of Spiking Neural Network Architecture) is a million-core computing engine whose flagship goal is to be able to simulate the behavior of aggregates of up to a billion neurons in real time. It consists of an array of ARM9 cores, communicating via packets carried by a custom interconnect fabric. The packets are small (40 or 72 bits), and their transmission is brokered entirely by hardware, giving the overall engine an extremely high bisection bandwidth of over 5 billion packets/s. Three of the principal axioms of parallel machine design (memory coherence, synchronicity, and determinism) have been discarded in the design without, surprisingly, compromising the ability to perform meaningful computations. A further attribute of the system is the acknowledgment, from the initial design stages, that the sheer size of the implementation will make component failures an inevitable aspect of day-to-day operation, and fault detection and recovery mechanisms have been built into the system at many levels of abstraction. This paper describes the architecture of the machine and outlines the underlying design philosophy; software and applications are to be described in detail elsewhere, and only introduced in passing here as necessary to illuminate the description.

SpiNNaker: Mapping neural networks onto a massively-parallel chip multiprocessor

SpiNNaker is a novel chip - based on the ARM processor - which is designed to support large scale spiking neural networks simulations. In this paper we describe some of the features that permit SpiNNaker chips to be connected together to form scalable massively-parallel systems. Our eventual goal is to be able to simulate neural networks consisting of 109 neurons running in dasiareal timepsila, by which we mean that a similarly sized collection of biological neurons would run at the same speed. In this paper we describe the methods by which neural networks are mapped onto the system, and how features designed into the chip are to be exploited in practice. We will also describe the modelling and verification activities by which we hope to ensure that, when the chip is delivered, it will work as anticipated.

A GALS Infrastructure for a Massively Parallel Multiprocessor

This case study focuses on a massively parallel multiprocessor for real-time simulation of billions of neurons. Every node of the design comprises 20 ARM9 cores, a memory interface, a multicast router, and two NoC structures for communicating between internal cores and the environment. The NoCs are asynchronous; the cores and RAM interfaces are synchronous. This GALS approach decouples clocking concerns for different parts of the die, leading to greater power efficiency.

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

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.

An investigation into the security of self-timed circuits

Self-timed logic may have advantages for security-sensitive applications. The absence of a clock, as a reliable timing reference, makes conventional power analysis attacks more difficult. However, the variability of the timing of self-timed circuits is a weakness that could be exploited by alternative attack techniques. This paper introduces a methodology for the differential power analysis of self-timed circuits which does not rely upon a clock signal. This methodology is used to investigate the security of a self-timed, ARM-compatible processor designed specifically to explore the benefits of self-timed design in secure applications. Timing analysis is also applied to the same design. The results from the analyses are presented and confirm that self-timed logic with dual-rail encoding and secure storage significantly improves resistance to non-invasive attacks.

SPA - a synthesisable Amulet core for smartcard applications

SPA is a synthesised, self-timed, ARM-compatible processor core. The use of synthesis was mandated by a need for rapid implementation. This has proved to be very effective, albeit with increased cost in terms of area and performance compared with earlier non-synthesised processors. SPA is employed in an experimental smartcard chip which is being designed to evaluate the applicability of self-timed logic in security-sensitive devices. The Balsa synthesis system is used to generate dual-rail logic with some enhancements to improve security against non-invasive attacks. A complete system-on-chip is being synthesised with a only small amount of hand design being employed to boost the throughput of the on-chip interconnection system.

Understanding the interconnection network of SpiNNaker

SpiNNaker is a massively parallel architecture designed to model large-scale spiking neural networks in (biological) real-time. Its design is based around ad-hoc multi-core System-on-Chips which are interconnected using a two-dimensional toroidal triangular mesh. Neurons are modeled in software and their spikes generate packets that propagate through the on- and inter-chip communication fabric relying on custom-made on-chip multicast routers. This paper models and evaluates large-scale instances of its novel interconnect (more than 65 thousand nodes, or over one million computing cores), focusing on real-time features and fault-tolerance. The key contribution can be summarized as understanding the properties of the feasible topologies and establishing the stable operation of the SpiNNaker under different levels of degradation. First we derive analytically the topological characteristics of the network, which are later confirmed by experimental work. With the computational model developed, we investigate the topology of SpiNNaker, and compare it with a standard 3-dimensional torus. The novel emergency routing mechanism, implemented within the routers, allows the topology of SpiNNaker to be more robust than the 3-dimensional torus, regardless of the latter having better topological characteristics. Furthermore, we obtain optimal values of two router parameters related with livelock and deadlock avoidance mechanisms.

A hierachical configuration system for a massively parallel neural hardware platform

Simulation of large networks of neurons is a powerful and increasingly prominent methodology for investigate brain functions and structures. Dedicated parallel hardware is a natural candidate for simulating the dynamic activity of many non-linear units communicating asynchronously. It is only scientifically useful, however, if the simulation tools can be configured and run easily and quickly. We present a method to map network models to computational nodes on the SpiNNaker system, a programmable parallel neurally-inspired hardware architecture, by exploiting the hierarchies built in the model. This PArtitioning and Configuration MANager (PACMAN) system supports arbitrary network topologies and arbitrary membrane potential and synapse dynamics, and (most importantly) decouples the model from the device, allowing a variety of languages (PyNN, Nengo, etc.) to drive the simulation hardware. Model representation operates on a Population/Projection level rather than a single-neuron and connection level, exploiting hierarchical properties to lower the complexity of allocating resources and mapping the model onto the system. PACMAN can be thus be used to generate structures coming from different models and front-ends, either with a host-based process, or by parallelising it on the SpiNNaker machine itself to speed up the generation process greatly. We describe the approach with a first implementation of the framework used to configure the current generation of SpiNNaker machines and present results from a set of key benchmarks. The system allows researchers to exploit dedicated simulation hardware which may otherwise be difficult to program. In effect, PACMAN provides automated hardware acceleration for some commonly used network simulators while also pointing towards the advantages of hierarchical configuration for large, domain-specific hardware systems.

SpiNNaker: A multi-core System-on-Chip for massively-parallel neural net simulation

The modelling of large systems of spiking neurons is computationally very demanding in terms of processing power and communication. SpiNNaker is a massively-parallel computer system designed to model up to a billion spiking neurons in real time. The basic block of the machine is the SpiNNaker multicore System-on-Chip, a Globally Asynchronous Locally Synchronous (GALS) system with 18 ARM968 processor nodes residing in synchronous islands, surrounded by a light-weight, packet-switched asynchronous communications infrastructure. The MPSoC contains 100 million transistors in a 102 mm2 die, provides a peak performance of 3.96 GIPS and has a power consumption of 1W at 1.2V when all processor cores operate at nominal frequency. SpiNNaker chips were delivered in May 2011, were fully operational, and met power and performance requirements.