Abstract
Simulations of biological tissue have been extensively used to replicate phenomena observed by in-vivo and in-vitro experiments as an alternative methodology for explaining how computations could take place in a brain region. Additional benefits of simulated neural networks over in-vivo experiments include greater observability, experimental control and reproducibility. General-purpose supercomputers provide the computational power and parallelism required to implement highly complex neural models, but this comes at the expense of high power requirements and communication overheads. Moreover, there are certain cases where real-time simulation performance is a desirable feature, for example in the field of cognitive robotics where embodied agents need to interact with their environment through biologically inspired asynchronous sensors. The SpiNNaker neuromimetic platform is a scalable architecture that has been designed to enable energy-efficient, large-scale simulations of spiking neurons in biological realtime. This work is based on a recent study which revealed that while they are generally energy efficient, SpiNNaker chips dissipate significant amount of power whilst in the idle state. In this paper we perform a systematic investigation into the overall energy consumption of a SpiNNaker system and propose a number of optimised suspend modes in order to reduce this. The proposed implementation is 60% more energy efficient in the idle state, 50% in the uploading and 52% in the downloading phases, while the power dissipation of the whole simulation is reduced by 52%. For demonstration purposes, we run a neural network simulation comprising thousands of neurons and millions of complex synapses on a 48-chip SpiNNaker board, generating millions of synaptic events per second.
Original language | English |
---|---|
Title of host publication | Proc. Neural Networks (IJCNN), 2014 International Joint Conference on |
Place of Publication | USA |
Publisher | IEEE |
Pages | 4280-4287 |
Number of pages | 8 |
ISBN (Print) | 978-1-4799-6627-1 |
DOIs | |
Publication status | Published - 6 Jul 2014 |
Event | Neural Networks (IJCNN), 2014 International Joint Conference on - Beijing, China Duration: 6 Jul 2014 → 11 Jul 2014 |
Conference
Conference | Neural Networks (IJCNN), 2014 International Joint Conference on |
---|---|
City | Beijing, China |
Period | 6/07/14 → 11/07/14 |
Keywords
- neural net architecture optimisation power aware computing