Optimising Resource Management for Embedded Machine Learning

TL;DR

This paper explores online resource management strategies for embedded machine learning on heterogeneous multi-core systems, aiming to optimize performance metrics like speed, energy, and accuracy amidst resource variability.

Contribution

It introduces approaches for dynamic resource management that enable scalable DNN execution, balancing multiple performance metrics on diverse embedded platforms.

Findings

Dynamic scalability of DNNs improves performance trade-offs.

Resource management strategies adapt to platform heterogeneity.

Consistent performance achieved across varying hardware conditions.

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.