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 appli...

Full description

Saved in:
Bibliographic Details
Main Authors: Xun, Lei, Tran-Thanh, Long, Al-Hashimi, Bashir M, Merrett, Geoff V.
Format: Conference Proceeding
Language:English
Subjects:
Central Processing Unit
Computational modeling
Dynamic Deep Neural Network
Embedded Machine Learning
Graphics processing units
Hardware
Measurement
Resource management
Runtime
Runtime Resource Management
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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 work-loads. 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.
ISSN:1558-1101
DOI:10.23919/DATE48585.2020.9116235