Year: 2012
Type: dissertation
Abstract: A human brain has billions of processing elements operating simultaneously; the only practical way to model this computationally is with a massively-parallel computer.A computer on such a significant scale requires hundreds of thousands of interconnected processing elements, a complex environment which requires many levels of monitoring, management and control.Management begins from the moment power is applied and continues whilst the application software loads, executes, and the results are downloaded.This is the story of the research and development of a framework of scalable management tools that support SpiNNaker, a novel computing architecture designed to model spiking neural networks of biologically-significant sizes.This management framework provides solutions from the most fundamental set of power-on self-tests, through to complex, real-time monitoring of the health of the hardware and the software during simulation.The framework devised uses standard tools where appropriate, covering hardware up / down events and capacity information, through to bespoke software developed to provide real-time insight to neural network software operation across multiple levels of abstraction.With this layered management approach, users (or automated agents) have access to results dynamically and are able to make informed decisions on required actions in real-time.Within the University, I'd like to thank all those around me, past and present, within the SpiNNaker and broader APT groups.They have provided great support, including answering my daft (and sometimes not-so-daft) questions with enthusiasm and patience.The team have been a great source of inspiration and challenges in all respects, and some have become badminton / drinking buddies.I'm particularly lucky to have chosen this group to join, it's an honour to have played a small part in the team developing the SpiNNaker architecture.More specifically I'd like to particularly thank my supervisor Prof. Steve Furber, who responded positively to my initial contact in 2008, encouraged my application, and provided support all the way through the programme.Special thanks also go to Dr. J. V. Woods and Dr. J. D. Garside for their proof-reading and assistance in guiding the shape of this thesis into an examinable form.In addition I greatly appreciate the support of the
Author: James Cameron Patterson
Institution: University of Manchester
Language: English
Subfield: Hardware and Architecture
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W343314746
