The University of Southampton
University of Southampton Institutional Repository

Optimising resource management for embedded machine learning

Optimising resource management for embedded machine learning
Optimising resource management for embedded machine learning
Machine learning inference is increasingly being executed locally on mobile and embedded platforms, due to the clear advantages in latency, privacy and connectivity. In this paper, we present approaches for online resource management in heterogeneous multi-core systems and show how they can be applied to optimise the performance of machine learning workloads. Performance can be defined using platform-dependent (e.g. speed, energy) and platform-independent (accuracy, confidence) metrics. In particular, we show how a Deep Neural Network (DNN) can be dynamically scalable to trade-off these various performance metrics. Achieving consistent performance when executing on different platforms is necessary yet challenging, due to the different resources provided and their capability, and their time-varying availability when executing alongside other workloads. Managing the interface between available hardware resources (often numerous and heterogeneous in nature), software requirements, and user experience is increasingly complex.
Xun, Lei
51a0da82-6979-49a8-8eff-ada011f5aff5
Tran-Thanh, Long
e0666669-d34b-460e-950d-e8b139fab16c
Al-Hashimi, Bashir
0b29c671-a6d2-459c-af68-c4614dce3b5d
Merrett, Geoff
89b3a696-41de-44c3-89aa-b0aa29f54020
Xun, Lei
51a0da82-6979-49a8-8eff-ada011f5aff5
Tran-Thanh, Long
e0666669-d34b-460e-950d-e8b139fab16c
Al-Hashimi, Bashir
0b29c671-a6d2-459c-af68-c4614dce3b5d
Merrett, Geoff
89b3a696-41de-44c3-89aa-b0aa29f54020

Xun, Lei, Tran-Thanh, Long, Al-Hashimi, Bashir and Merrett, Geoff (2020) Optimising resource management for embedded machine learning. In Design, Automation and Test in Europe Conference 2020 (DATE'20). 6 pp .

Record type: Conference or Workshop Item (Paper)

Abstract

Machine learning inference is increasingly being executed locally on mobile and embedded platforms, due to the clear advantages in latency, privacy and connectivity. In this paper, we present approaches for online resource management in heterogeneous multi-core systems and show how they can be applied to optimise the performance of machine learning workloads. Performance can be defined using platform-dependent (e.g. speed, energy) and platform-independent (accuracy, confidence) metrics. In particular, we show how a Deep Neural Network (DNN) can be dynamically scalable to trade-off these various performance metrics. Achieving consistent performance when executing on different platforms is necessary yet challenging, due to the different resources provided and their capability, and their time-varying availability when executing alongside other workloads. Managing the interface between available hardware resources (often numerous and heterogeneous in nature), software requirements, and user experience is increasingly complex.

Text
Optimising resource management for embedded machine learning - Version of Record
Available under License Creative Commons Attribution.
Download (580kB)
Text
Optimising resource management for embedded machine learning_v2 - Other
Available under License Creative Commons Attribution.
Download (677kB)
Text
Optimising resource management for embedded machine learning_v3 - Other
Available under License Creative Commons Attribution.
Download (599kB)

More information

Accepted/In Press date: 30 October 2019
Published date: 2020
Venue - Dates: Design, Automation and Test in Europe Conference 2020 (DATE'20), France, 2020-03-09 - 2020-03-13

Identifiers

Local EPrints ID: 436228
URI: http://eprints.soton.ac.uk/id/eprint/436228
PURE UUID: 3525323f-b950-4620-a008-2f0bb3612852
ORCID for Long Tran-Thanh: ORCID iD orcid.org/0000-0003-1617-8316
ORCID for Geoff Merrett: ORCID iD orcid.org/0000-0003-4980-3894

Catalogue record

Date deposited: 04 Dec 2019 17:30
Last modified: 15 Aug 2020 01:38

Export record

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×