收藏切换
RR-SC: Run-Time Reconfigurable Framework for Stochastic Computing-Based Neural Networks on Edge Devices
收藏切换
Yuhong Song, Hsing-Mean Sha Edwin, Qingfeng Zhuge*, Rui Xu, Han Wang
Journal of Computer Research and Development | 2024, 61(4) : 840 - 855
Less
收藏切换
Journal of Computer Research and Development | 2024, 61(4): 840-855
• Architecture •
RR-SC: Run-Time Reconfigurable Framework for Stochastic Computing-Based Neural Networks on Edge Devices
Full
Yuhong Song, Hsing-Mean Sha Edwin, Qingfeng Zhuge*, Rui Xu, Han Wang
Affiliations
  • 1School of Computer Science and Technology, East China Normal University, Shanghai 200062
  • born in 1997. PhD candidate. Student member of CCF. Her main research interests include embedded system, software-hardware co-design, automated machine learning, stochastic computing, and quantum computing

    born in 1964. PhD, professor, PhD supervisor. Senior member of CCF. His main research interests include big data systems, high-performance intelligent computing, advanced storage, parallel/distributed systems and computing, embedded systems, scheduling and optimization, resource allocation, and quantum computing

    born in 1970. PhD, professor, PhD supervisor. Member of CCF. Her main research interests include parallel architectures, embedded systems, supply-chain management, real-time systems, optimization algorithms, compilers, and scheduling

    born in 1996. PhD candidate. Student member of CCF. Her main research interests include non-volatile memory, optimization algorithms, and computer architecture

    born in 1997. PhD candidate. Her main research interests include storage systems, embedded systems, optimization algorithms, machine learning, and adaptive learning systems

About Author:

born in 1997. PhD candidate. Student member of CCF. Her main research interests include embedded system, software-hardware co-design, automated machine learning, stochastic computing, and quantum computing

born in 1964. PhD, professor, PhD supervisor. Senior member of CCF. His main research interests include big data systems, high-performance intelligent computing, advanced storage, parallel/distributed systems and computing, embedded systems, scheduling and optimization, resource allocation, and quantum computing

born in 1970. PhD, professor, PhD supervisor. Member of CCF. Her main research interests include parallel architectures, embedded systems, supply-chain management, real-time systems, optimization algorithms, compilers, and scheduling

born in 1996. PhD candidate. Student member of CCF. Her main research interests include non-volatile memory, optimization algorithms, and computer architecture

born in 1997. PhD candidate. Her main research interests include storage systems, embedded systems, optimization algorithms, machine learning, and adaptive learning systems

Published: 2024-04-01 doi: 10.7544/issn1000-1239.202220738
Outline
收藏切换

With the development of AI democratization, deep neural networks (DNNs) have been widely applied to edge devices, such as smart phones and automated driving, etc. Stochastic computing (SC) as a promising technique performs fundamental machine learning (ML) tasks using simple logic gates instead of complicated binary arithmetic circuits. SC has advantages of low-power and low-cost DNNs execution on edge devices with constrained resources (e.g., energy, computation and memory units, etc.). However, previous SC work only designs one group of setting for fixed hardware implementation, ignoring the dynamic hardware resources (e.g., battery), which leads to low hardware efficiency and short battery life. In order to save energy for battery-powered edge devices, dynamic voltage and frequency scaling (DVFS) technique is widely used for hardware reconfiguration to prolong battery life. In this paper, we creatively propose a run-time reconfigurable framework, namely RR-SC, for SC-based DNNs and first attempt to combine hardware and software reconfigurations to satisfy the time constraint of inference and maximally save energy. RR-SC using reinforcement learning (RL) can generate multiple groups of model settings at one time, which can satisfy the accuracy constraints under different hardware settings (i.e., different voltage/frequency levels). The solution has the best accuracy and hardware efficiency trade-off. Meanwhile, the model settings are switched on a backbone model at run-time, which enables lightweight software reconfiguration. Experimental results show that RR-SC can switch the lightweight settings within 110 ms to guarantee the required real-time constraint at different hardware levels. Meanwhile, it can achieve up to 7.6 times improvement for the number of model inference with only 1% accuracy loss.

edge devices  /  stochastic computing  /  run-time reconfiguration  /  dynamic hardware conditions  /  lightweight software reconfiguration  /  reinforcement learning
宋玉红, 沙行勉, 诸葛晴凤, 许瑞, 王寒. RR-SC: 边缘设备中基于随机计算神经网络的运行时可重配置框架. 计算机研究与发展, 2024 , 61 (4) : 840 -855 . DOI: 10.7544/issn1000-1239.202220738
Yuhong Song, Hsing-Mean Sha Edwin, Qingfeng Zhuge, Rui Xu, Han Wang. RR-SC: Run-Time Reconfigurable Framework for Stochastic Computing-Based Neural Networks on Edge Devices[J]. Journal of Computer Research and Development, 2024 , 61 (4) : 840 -855 . DOI: 10.7544/issn1000-1239.202220738
Year 2024 volume 61 Issue 4
88
41
Cite this Article
BibTeX
Article Info
doi: 10.7544/issn1000-1239.202220738
  • Receive Date:2022-08-22
  • Online Date:2026-11-17
  • Published:2024-04-01
Article Data
Affiliations
History
  • Received:2022-08-22
  • Revised:2023-05-19
Affiliations
    1School of Computer Science and Technology, East China Normal University, Shanghai 200062
References
Share
https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202220738
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT