Characterising Across-Stack Optimisations for Deep Convolutional Neural Networks

Turner, J., Cano, J. , Radu, V., Crowley, E. J., O’Boyle, M. and Storkey, A. (2018) Characterising Across-Stack Optimisations for Deep Convolutional Neural Networks. In: 2018 IEEE International Symposium on Workload Characterization (IISWC), Raleigh, NC, USA, 30 Sep - 02 Oct 2018, pp. 101-110. ISBN 9781538667804 (doi: 10.1109/IISWC.2018.8573503)

Abstract

Convolutional Neural Networks (CNNs) are extremely computationally demanding, presenting a large barrier to their deployment on resource-constrained devices. Since such systems are where some of their most useful applications lie (e.g. obstacle detection for mobile robots, vision-based medical assistive technology), significant bodies of work from both machine learning and systems communities have attempted to provide optimisations that will make CNNs available to edge devices. In this paper we unify the two viewpoints in a Deep Learning Inference Stack and take an across-stack approach by implementing and evaluating the most common neural network compression techniques (weight pruning, channel pruning, and quantisation) and optimising their parallel execution with a range of programming approaches (OpenMP, OpenCL) and hardware architectures (CPU, GPU). We provide comprehensive Pareto curves to instruct trade-offs under constraints of accuracy, execution time, and memory space.

• Item Type: Conference Proceedings
• Additional Information: This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 732204 (Bonseyes). This work is supported by the Swiss State Secretariat for Education, Research and Innovation (SERI) under contract number 16.0159.
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Cano Reyes, Dr Jose
• Authors: Turner, J., Cano, J., Radu, V., Crowley, E. J., O’Boyle, M., and Storkey, A.
• College/School: College of Science and Engineering > School of Computing Science
• ISBN: 9781538667804
• Published Online: 13 December 2018
• Copyright Holders: Copyright © 2018 IEEE
• First Published: First published in 2018 IEEE International Symposium on Workload Characterization (IISWC): 101-110
• Publisher Policy: Reproduced in accordance with the publisher copyright policy