arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2310.18329cs.NIcs.AIcs.LGcs.PF
收藏

揭示深度学习中的能效:跨边缘设备的测量、预测与评分

Unveiling Energy Efficiency in Deep Learning: Measurement, Prediction, and Scoring across Edge Devices

Georgia State University(佐治亚州立大学);The University of North Carolina at Charlotte(北卡罗来纳大学夏洛特分校);Toyota InfoTech Labs(丰田信息技术实验室)

Xiaolong Tu, Anik Mallik, Dawei Chen, Kyungtae Han, Onur Altintas, Haoxin Wang, Jiang Xie

AI总结:

本文通过测量、预测和评分三方面研究边缘设备深度学习能效,构建三个能源数据集,提出首个算子级能源预测器及PCS、IECS评分指标,以推动边缘计算可持续性。

摘要:

如今,深度学习优化主要由以实现高推理精度和降低延迟为目标的研究所驱动。然而,能效方面往往被忽视,这可能是由于该领域缺乏可持续性思维以及缺少整体性能源数据集所致。在本文中,我们开展了一项包含能源测量、预测和效率评分三部分的研究,目标是提高各类边缘设备上深度学习功耗和能耗的透明度。首先,我们呈现了一项详尽且首次开展的测量研究,揭示了端侧深度学习的能耗特征。该研究促成了三个面向边缘设备的大规模能源数据集的创建,覆盖广泛的算子、最先进的DNN模型以及流行的AI应用。其次,我们基于算子级能源数据集,设计并实现了首个面向边缘设备的算子级能源预测器。评估结果表明,我们的预测器能够在未见过的DNN模型上提供一致且准确的能耗估计。最后,我们引入了两个评分指标,即PCS和IECS,旨在将边缘设备复杂的功耗和能耗数据转换为边缘设备最终用户易于理解的形式。我们希望我们的工作能够帮助最终用户和研究界转变思维,朝着边缘计算中的可持续性方向发展,而这一原则正是推动我们研究的动力。请在https://amai-gsu.github.io/DeepEn2023查找数据、代码和更多最新信息。

英文摘要:

Today, deep learning optimization is primarily driven by research focused on achieving high inference accuracy and reducing latency. However, the energy efficiency aspect is often overlooked, possibly due to a lack of sustainability mindset in the field and the absence of a holistic energy dataset. In this paper, we conduct a threefold study, including energy measurement, prediction, and efficiency scoring, with an objective to foster transparency in power and energy consumption within deep learning across various edge devices. Firstly, we present a detailed, first-of-its-kind measurement study that uncovers the energy consumption characteristics of on-device deep learning. This study results in the creation of three extensive energy datasets for edge devices, covering a wide range of kernels, state-of-the-art DNN models, and popular AI applications. Secondly, we design and implement the first kernel-level energy predictors for edge devices based on our kernel-level energy dataset. Evaluation results demonstrate the ability of our predictors to provide consistent and accurate energy estimations on unseen DNN models. Lastly, we introduce two scoring metrics, PCS and IECS, developed to convert complex power and energy consumption data of an edge device into an easily understandable manner for edge device end-users. We hope our work can help shift the mindset of both end-users and the research community towards sustainability in edge computing, a principle that drives our research. Find data, code, and more up-to-date information at https://amai-gsu.github.io/DeepEn2023.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑