Deep neural network (DNN) has driven extensive applications in mobile technology. However, for long-running mobile apps like voice assistants or video applications on smartphones, energy efficiency is critical for battery-powered devices. The rise of heterogeneous processors in mobile devices today has introduced new challenges for optimizing energy efficiency. Our key insight is that partitioning computations across different processors for parallelism and speedup doesn't necessarily correlate with energy consumption optimization and may even increase it. To address this, we present AdaOper, an energy-efficient concurrent DNN inference system. It optimizes energy efficiency on mobile heterogeneous processors while maintaining responsiveness. AdaOper includes a runtime energy profiler that dynamically adjusts operator partitioning to optimize energy efficiency based on dynamic device conditions. We conduct preliminary experiments, which show that AdaOper reduces energy consumption by 16.88% compared to the existing concurrent method while ensuring real-time performance.
@article{arxiv.2404.19209,
title = {AdaOper: Energy-efficient and Responsive Concurrent DNN Inference on Mobile Devices},
author = {Zheng Lin and Bin Guo and Sicong Liu and Wentao Zhou and Yasan Ding and Yu Zhang and Zhiwen Yu},
journal= {arXiv preprint arXiv:2404.19209},
year = {2024}
}