arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2309.15467cs.LGcs.AIcs.DC
收藏

通过跨层级优化实现资源高效的 AIoT 系统:综述

Enabling Resource-efficient AIoT System with Cross-level Optimization: A survey

Northwestern Polytechnical University(西北工业大学);Harbin Engineering University(哈尔滨工程大学);City University of Hong Kong(香港城市大学)

Sicong Liu, Bin Guo, Cheng Fang, Ziqi Wang, Shiyan Luo, Zimu Zhou, Zhiwen Yu

AI总结:

本文综述 AIoT 中资源受限下的深度学习部署问题,梳理从模型、计算图到硬件指令的跨层级协同优化与上下文自适应控制方法。

摘要:

人工智能物联网(AIoT,AI+IoT)这一新兴领域由智能基础设施的广泛使用和深度学习(DL)令人瞩目的成功所推动。随着 DL 部署在各类具有丰富传感器但 DL 计算能力较弱的智能基础设施上,多种多样的 AIoT 应用成为可能。然而,DL 模型是众所周知的资源密集型模型。现有研究致力于在资源稀缺的基础设施上实现 AIoT 实时数据的近实时/实时推理,以及利用 AIoT 数据集进行低成本训练。因此,DL 模型的精度和响应能力受到资源可用性的限制。为此,算法-系统协同设计联合优化资源友好型 DL 模型和模型自适应的系统调度,提高了运行时资源可用性,从而突破了由单一独立层级所设定的性能边界。不同于以往关于资源友好型 DL 模型或仅对部分组件进行微调的手工 DL 编译器/框架的综述,本综述旨在提供更广阔的优化空间,以实现更自由的资源-性能权衡。跨层级优化图景涉及多种粒度,包括端侧和分布式两种范式下的 DL 模型、计算图、算子、内存调度以及硬件指令。此外,由于 AIoT 上下文具有动态特性,其中包括异构硬件、未知传感数据、不断变化的用户指定性能需求以及资源约束,本综述探讨了用于自动跨层级适配的、具备上下文感知能力的设备间/设备内控制器。另外,我们还指出了资源高效 AIoT 系统的一些潜在方向。通过整合分散在不同层级的问题和技术,我们旨在帮助读者理解它们之间的联系,并激发进一步的讨论。

英文摘要:

The emerging field of artificial intelligence of things (AIoT, AI+IoT) is driven by the widespread use of intelligent infrastructures and the impressive success of deep learning (DL). With the deployment of DL on various intelligent infrastructures featuring rich sensors and weak DL computing capabilities, a diverse range of AIoT applications has become possible. However, DL models are notoriously resource-intensive. Existing research strives to realize near-/realtime inference of AIoT live data and low-cost training using AIoT datasets on resource-scare infrastructures. Accordingly, the accuracy and responsiveness of DL models are bounded by resource availability. To this end, the algorithm-system co-design that jointly optimizes the resource-friendly DL models and model-adaptive system scheduling improves the runtime resource availability and thus pushes the performance boundary set by the standalone level. Unlike previous surveys on resource-friendly DL models or hand-crafted DL compilers/frameworks with partially fine-tuned components, this survey aims to provide a broader optimization space for more free resource-performance tradeoffs. The cross-level optimization landscape involves various granularity, including the DL model, computation graph, operator, memory schedule, and hardware instructor in both on-device and distributed paradigms. Furthermore, due to the dynamic nature of AIoT context, which includes heterogeneous hardware, agnostic sensing data, varying user-specified performance demands, and resource constraints, this survey explores the context-aware inter-/intra-device controllers for automatic cross-level adaptation. Additionally, we identify some potential directions for resource-efficient AIoT systems. By consolidating problems and techniques scattered over diverse levels, we aim to help readers understand their connections and stimulate further discussions.

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。

↑