TinyML系统的功耗与性能表征
Power-Performance Characterization of TinyML Systems
- School of Computing, National University of Singapore（新加坡国立大学计算机学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文针对微控制器上的TinyML系统开展性能与功耗表征，提出估算抽象层成本的模型，其结果可辅助边缘设备的NAS与CNN推理优化。
AI中文摘要：
TinyML系统支持在边缘设备上运行机器学习（ML）推理，但目前针对这类系统的定量分析较少。本文对微控制器（MCU）上的多种TinyML应用开展了系统的性能与功耗表征，覆盖神经网络模型、软件库、操作系统及硬件架构。我们聚焦于多层抽象的影响——这些抽象提升了可编程性，但会牺牲性能与能效。我们提出了一个模型来估算不同抽象层的成本，并给出了最小化这些成本的建议。研究结果可帮助设计人员在边缘设备上开展神经架构搜索（NAS）与卷积神经网络（CNN）推理优化。
英文摘要：
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.
