分析微控制器上TinyML系统的能效表现，找出抽象层的性能损耗。
Power-Performance Characterization of TinyML Systems
- 构建模型量化各抽象层带来的开销，指导优化设计
- 揭示软件库与硬件架构对能效的影响差异
- 适合边缘设备模型压缩与神经网络搜索研究者
TinyML系统正推动机器学习推理向边缘端迁移。然而，现有研究缺乏对此类系统在微控制器（MCU）上性能与功耗的定量分析。本文系统地评估了多种TinyML应用在不同神经网络模型、软件库、操作系统和硬件架构下的表现，重点关注多层抽象带来的可编程性提升与性能、能效下降之间的权衡。提出一种模型估算各抽象层的成本，并给出降低这些成本的优化建议。研究成果可为边缘设备上的神经架构搜索（NAS）和卷积神经网络（CNN）推理优化提供支持。
原文摘要 · Abstract (English)
TinyML systems are enabling machine learning (ML) inference at the edge. However, there is little quantitative analysis of such systems. This paper presents a systematic performance and power characterization of diverse TinyML applications on microcontrollers (MCUs), spanning neural network models, software libraries, operating systems, and hardware architectures. We focus on the impact of the multiple layers of abstraction that provide higher programmability at the expense of performance and energy efficiency. We propose a model to estimate the costs of different abstraction layers and make recommendations for minimizing those costs. Our findings can help designers with Neural Architecture Search (NAS) and CNN inference optimization on edge devices.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。