A Domain-Specific System-On-Chip Design for Energy Efficient Wearable Edge AI Applications

A Domain-Specific System-On-Chip Design for Energy Efficient Wearable Edge AI Applications
复制标题

适用于节能可穿戴边缘人工智能应用的特定领域片上系统设计

DOI:
10.1145/3531437.3539711
复制
发表时间:
2022
期刊:
Proceedings of the ACM/IEEE International Symposium on Low Power Electronics and Design
影响因子:
--
通讯作者:
Ogras, Umit
Ogras, Umit
中科院分区:
--
文献类型:
--
作者:
Tuncel, Yigit;Krishnakumar, Anish;Chithra, Aishwarya Lekshmi;Kim, Younghyun;Ogras, Umit

文献摘要

参考文献

相似文献

基于人工智能(AI)的可穿戴应用程序收集和处理大量的流式传感器数据。将原始数据传输到云处理器浪费了稀缺的能源,并威胁到用户隐私。可穿戴边缘AI设备应该理想地平衡两个相互竞争的要求:(1)使用目标硬件加速器最大限度地提高能效,以及(2)使用通用内核提供多功能性以支持任意应用程序。为此,我们提出了一种开源的特定领域可编程片上系统(SoC),它将RISC-V内核与一组针对可穿戴应用的精心确定的加速器相结合。我们应用所提出的设计方法来设计一个FPGA原型和六个真实的用例,以证明所提出的SoC的有效性。彻底的实验评估表明,所提出的SoC提供高达9.1倍的执行速度和高达8.9倍的能源效率比在FPGA中的软件实现,同时保持可编程性。
Artificial intelligence (AI) based wearable applications collect and process a significant amount of streaming sensor data. Transmitting the raw data to cloud processors wastes scarce energy and threatens user privacy. Wearable edge AI devices should ideally balance two competing requirements: (1) maximizing the energy efficiency using targeted hardware accelerators and (2) providing versatility using general-purpose cores to support arbitrary applications. To this end, we present an open-source domain-specific programmable system-on-chip (SoC) that combines a RISC-V core with a meticulously determined set of accelerators targeting wearable applications. We apply the proposed design method to design an FPGA prototype and six real-life use cases to demonstrate the efficacy of the proposed SoC. Thorough experimental evaluations show that the proposed SoC provides up to 9.1 × faster execution and up to 8.9 × higher energy efficiency than software implementations in FPGA while maintaining programmability.
DOI: 10.1109/mdat.2019.2906110
发表时间: 2019-10-01
期刊: IEEE DESIGN & TEST
影响因子: 2
作者:
Bhat, Ganapati;Deb, Ranadeep;Ogras, Umit Y.
通讯作者: Ogras, Umit Y.
DOI: 10.1145/3424669
发表时间: 2019-12
期刊: ACM Transactions on Architecture and Code Optimization (TACO)
影响因子: --
作者:
S. Xi;Yuan Yao;K. Bhardwaj;P. Whatmough;Gu-Yeon Wei;D. Brooks
通讯作者: S. Xi;Yuan Yao;K. Bhardwaj;P. Whatmough;Gu-Yeon Wei;D. Brooks
我们每天可以为可穿戴应用收集多少能量?
DOI: 10.1109/islped52811.2021.9502507
发表时间: 2021
期刊: IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED
影响因子: --
作者:
Tuncel, Yigit;Basaklar, Toygun;Ogras, Umit
通讯作者: Ogras, Umit
用于微创耳后脑电图和诱发电位的可穿戴设备
DOI: 10.1109/biocas.2018.8584814
发表时间: 2018
期刊: 2018 IEEE Biomedical Circuits and Systems Conference (BioCAS)
影响因子: --
作者:
M. Guermandi;Simone Benatti;Victor Javier Kartsch Morinigo;Luca Bertini
通讯作者: Luca Bertini
DOI: 10.3390/s20185356
发表时间: 2020-09-18
期刊: Sensors (Basel, Switzerland)
影响因子: --
作者:
Bhat G;Tran N;Shill H;Ogras UY
通讯作者: Ogras UY