arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1911.03314cs.LGeess.SPstat.ML
收藏

FANN-on-MCU:物联网边缘节能神经网络推理的开源工具包

FANN-on-MCU: An Open-Source Toolkit for Energy-Efficient Neural Network Inference at the Edge of the Internet of Things

ETH Zürich(苏黎世联邦理工学院);University of Bologna(博洛尼亚大学)

Xiaying Wang, Michele Magno, Lukas Cavigelli, Luca Benini

摘要:

物联网中越来越多的低功耗智能设备与“边缘计算”的概念相结合,即将一些智能,特别是机器学习,推向网络边缘。使机器学习算法能够在资源受限的硬件上运行,通常在低功耗智能设备上运行,在硬件(优化和节能的集成电路)、算法和固件实现方面具有挑战性。本文介绍了FANN-on-MCU,这是一个基于快速人工神经网络(FANN)库构建的开源工具包,可在基于ARM Cortex-M系列和基于RISC-V的新型并行超低功耗(PULP)平台的微控制器上运行轻量级和节能的神经网络。该工具包采用用FANN训练的多层感知器,并生成针对在低功耗微控制器上执行的代码,该微控制器具有浮点单元(即,ARM Cortex-M4 F和M7 F)或无(即,ARM Cortex M0-M3或基于PULP的处理器)。本文还提供了一个架构性能评估的神经网络上最流行的ARM Cortex-M系列和并行RISC-V处理器称为沃尔夫先生。该评估包括使用可自我维持的可穿戴多传感器手镯的三种不同应用的实验结果。实验结果表明,测量延迟的顺序只有几微秒和几毫瓦的功耗,同时保持低于目标微控制器的限制的内存要求。特别是,在八核RISC-V平台上的并行实现达到了22倍的加速比,相对于Cortex-M4上的单核实现,能耗降低了69%,用于连续实时分类。

英文摘要:

The growing number of low-power smart devices in the Internet of Things is coupled with the concept of "Edge Computing", that is moving some of the intelligence, especially machine learning, towards the edge of the network. Enabling machine learning algorithms to run on resource-constrained hardware, typically on low-power smart devices, is challenging in terms of hardware (optimized and energy-efficient integrated circuits), algorithmic and firmware implementations. This paper presents FANN-on-MCU, an open-source toolkit built upon the Fast Artificial Neural Network (FANN) library to run lightweight and energy-efficient neural networks on microcontrollers based on both the ARM Cortex-M series and the novel RISC-V-based Parallel Ultra-Low-Power (PULP) platform. The toolkit takes multi-layer perceptrons trained with FANN and generates code targeted at execution on low-power microcontrollers either with a floating-point unit (i.e., ARM Cortex-M4F and M7F) or without (i.e., ARM Cortex M0-M3 or PULP-based processors). This paper also provides an architectural performance evaluation of neural networks on the most popular ARM Cortex-M family and the parallel RISC-V processor called Mr. Wolf. The evaluation includes experimental results for three different applications using a self-sustainable wearable multi-sensor bracelet. Experimental results show a measured latency in the order of only a few microseconds and a power consumption of few milliwatts while keeping the memory requirements below the limitations of the targeted microcontrollers. In particular, the parallel implementation on the octa-core RISC-V platform reaches a speedup of 22x and a 69% reduction in energy consumption with respect to a single-core implementation on Cortex-M4 for continuous real-time classification.

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。

↑