The University of Southampton
University of Southampton Institutional Repository

Runtime DNN performance scaling through resource management on heterogeneous embedded platforms

Runtime DNN performance scaling through resource management on heterogeneous embedded platforms
Runtime DNN performance scaling through resource management on heterogeneous embedded platforms
DNN inference is increasingly being executed locally on embedded platforms, due to the clear advantages in latency, privacy and connectivity. Modern SoCs typically execute a combination of different and dynamic workloads concurrently, it is challenging to consistently meet latency/energy budgets because the local computing resources available to the DNN vary considerably. In this poster, we show how resource management can be applied to optimise the performance of DNN workloads by monitoring and tuning both software and hardware constantly at runtime. This work shows how dynamic DNNs trade-off accuracy with latency/energy/power on heterogeneous embedded CPU-GPU platform.
Xun, Lei
51a0da82-6979-49a8-8eff-ada011f5aff5
Al-Hashimi, Bashir
bfee994d-8c63-4fe7-8ec7-76680eb1b642
Hare, Jonathon
65ba2cda-eaaf-4767-a325-cd845504e5a9
Merrett, Geoff
89b3a696-41de-44c3-89aa-b0aa29f54020
Xun, Lei
51a0da82-6979-49a8-8eff-ada011f5aff5
Al-Hashimi, Bashir
bfee994d-8c63-4fe7-8ec7-76680eb1b642
Hare, Jonathon
65ba2cda-eaaf-4767-a325-cd845504e5a9
Merrett, Geoff
89b3a696-41de-44c3-89aa-b0aa29f54020

Xun, Lei, Al-Hashimi, Bashir, Hare, Jonathon and Merrett, Geoff (2021) Runtime DNN performance scaling through resource management on heterogeneous embedded platforms. tinyML EMEA Technical Forum 2021. 07 - 10 Jun 2021.

Record type: Conference or Workshop Item (Poster)

Abstract

DNN inference is increasingly being executed locally on embedded platforms, due to the clear advantages in latency, privacy and connectivity. Modern SoCs typically execute a combination of different and dynamic workloads concurrently, it is challenging to consistently meet latency/energy budgets because the local computing resources available to the DNN vary considerably. In this poster, we show how resource management can be applied to optimise the performance of DNN workloads by monitoring and tuning both software and hardware constantly at runtime. This work shows how dynamic DNNs trade-off accuracy with latency/energy/power on heterogeneous embedded CPU-GPU platform.

Text
Runtime DNN Performance Scaling through Resource Management on Heterogeneous Embedded Platforms - Accepted Manuscript
Download (415kB)

More information

Published date: 10 June 2021
Venue - Dates: tinyML EMEA Technical Forum 2021, 2021-06-07 - 2021-06-10

Identifiers

Local EPrints ID: 450052
URI: http://eprints.soton.ac.uk/id/eprint/450052
PURE UUID: 4cd13895-512e-420b-af95-0764b3aab1a3
ORCID for Jonathon Hare: ORCID iD orcid.org/0000-0003-2921-4283
ORCID for Geoff Merrett: ORCID iD orcid.org/0000-0003-4980-3894

Catalogue record

Date deposited: 07 Jul 2021 16:30
Last modified: 08 Jul 2021 01:41

Export record

Contributors

Author: Lei Xun
Author: Bashir Al-Hashimi
Author: Jonathon Hare ORCID iD
Author: Geoff Merrett ORCID iD

University divisions

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.

×