Special Session: Approximate TinyML Systems: Full System Approximations for Extreme Energy-Efficiency in Intelligent Edge Devices
Special Session: Approximate TinyML Systems: Full System Approximations for Extreme Energy-Efficiency in Intelligent Edge Devices
复制标题
特别会议：近似 TinyML 系统：智能边缘设备中极高能效的全系统近似
DOI：
10.1109/iccd53106.2021.00015
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
V. Raghunathan
中科院分区：
文献类型：
--
作者：
Arnab Raha;Soumendu Kumar Ghosh;D. Mohapatra;D. Mathaikutty;Raymond Sung;C. Brick;V. Raghunathan
近似计算（AxC）已经从一种新兴的设计范式发展成为计算机视觉，图像/视频处理，数据挖掘，分析和搜索领域应用中最流行和最有效的能量优化方法之一。人工智能（AI）的同时兴起为在智能边缘平台中采用各种AxC技术提供了额外的推动力，在这些平台中，能源效率不仅是可取的，而且是必要的。尽管人们对AxC的兴趣大增，但近似硬件的采用大多仅限于系统的一个组件（通常是处理子系统），而这通常只占整个系统级功率的一小部分。AxC的全系统方法使我们能够将近似扩展到其他子系统，例如存储器，传感器和通信子系统。本文介绍了近似TinyML系统的基本概念，该系统将近似协同应用于边缘推理设备中的多个子系统。这些近似值被智能地应用，以显著降低能耗，同时在应用程序级质量方面产生可忽略的损失。我们展示了多个版本的近似智能相机系统，该系统可以执行最先进的深度神经网络（DNN），同时仅消耗典型系统总能量的一小部分。
Approximate computing (AxC) has advanced from being an emerging design paradigm to becoming one of the most popular and effective methods of energy optimization for applications in the domains of computer vision, image/video processing, data mining, analytics, and search. The simultaneous rise of artificial intelligence (AI) has provided an additional thrust to the adoption of various AxC techniques in intelligent edge platforms where energy-efficiency is not only desirable but necessary. In spite of the big rise in interest for AxC, the adoption of approximate hardware has mostly been limited to only one component of the system (usually the processing subsystem) which often contributes only a fraction of the overall system-level power. A full system approach to AxC enables us to extend approximations to other subsystems, such as the memory, sensor, and communications subsystems. This paper presents the foundational concepts of an approximate TinyML system that applies approximations synergistically to multiple subsystems in an edge inference device. These approximations are applied intelligently to significantly reduce energy while incurring a negligible loss in application-level quality. We demonstrate multiple versions of an approximate smart camera system that can execute state-of-the-art deep neural networks (DNNs) while consuming only a fraction of the total energy in a typical system.