| INTERDISCIPLINARY PHYSICS AND RELATED AREAS OF SCIENCE AND TECHNOLOGY |
Prev
Next
|
|
|
Atmospheric neutron single event effects for multiple convolutional neural networks based on 28-nm and 16-nm SoC |
| Xu Zhao(赵旭)1, Xuecheng Du(杜雪成)1,†, Chao Ma(马超)1, Zhiliang Hu(胡志良)2,3, Weitao Yang(杨卫涛)4, and Bo Zheng(郑波)1 |
1 School of Nuclear Science and Technology, University of South China, Hengyang 421001, China;
2 Spallation Neutron Source Science Center, Dongguan 523000, China;
3 Institute of High Energy Physics, Chinese Academy of Sciences (CAS), Beijing 100049, China;
4 School of Microelectronics, Xidian University, Xi'an 710071, China |
|
|
|
|
Abstract The single event effects (SEEs) evaluations caused by atmospheric neutrons were conducted on three different convolutional neural network (CNN) models (Yolov3, MNIST, and ResNet50) in the atmospheric neutron irradiation spectrometer (ANIS) at the China Spallation Neutron Source (CSNS). The Yolov3 and MNIST models were implemented on the XILINX 28-nm system-on-chip (SoC). Meanwhile, the Yolov3 and ResNet50 models were deployed on the XILINX 16-nm FinFET UltraScale+MPSoC. The atmospheric neutron SEEs on the tested CNN systems were comprehensively evaluated from six aspects, including chip type, network architecture, deployment methods, inference time, datasets, and the position of the anchor boxes. The various types of SEE soft errors, SEE cross-sections, and their distribution were analyzed to explore the radiation sensitivities and rules of 28-nm and 16-nm SoC. The current research can provide the technology support of radiation-resistant design of CNN system for developing and applying high-reliability, long-lifespan domestic artificial intelligence chips.
|
Received: 22 September 2024
Revised: 21 October 2024
Accepted manuscript online: 25 October 2024
|
|
PACS:
|
85.30.De
|
(Semiconductor-device characterization, design, and modeling)
|
| |
61.82.Fk
|
(Semiconductors)
|
| |
85.35.-p
|
(Nanoelectronic devices)
|
| |
61.80.Hg
|
(Neutron radiation effects)
|
|
| Fund: Project supported by the National Natural Science Foundation of China (Grant No. 12305303), the Natural Science Foundation of Hunan Province of China (Grant Nos. 2023JJ40520, 2024JJ2044, and 2021JJ40444), the Science and Technology Innovation Program of Hunan Province, China (Grant No. 2020RC3054), the Postgraduate Scientific Research Innovation Project of Hunan Province, China (Grant No. CX20240831), the Natural Science Basic Research Plan in the Shaanxi Province of China (Grant No. 2023-JC-QN-0015), and the Doctoral Research Fund of University of South China (Grant No. 200XQD033). |
Corresponding Authors:
Xuecheng Du
E-mail: duxuecheng@usc.edu.cn
|
Cite this article:
Xu Zhao(赵旭), Xuecheng Du(杜雪成), Chao Ma(马超), Zhiliang Hu(胡志良), Weitao Yang(杨卫涛), and Bo Zheng(郑波) Atmospheric neutron single event effects for multiple convolutional neural networks based on 28-nm and 16-nm SoC 2025 Chin. Phys. B 34 018501
|
[1] Cosmas K and Kenichi A 2020 Aerospace. 7 159
[2] Gao H B, Cheng B,Wang J Q, Li K Q, Zhao J H and Li D Y 2018 IEEE Trans. Industr. Inform. 14 4224
[3] Jin X M, ChenW, Li J L, Qi C, Guo X Q, Li R B and Liu Y 2019 Chin. Phys. B 28 104212
[4] Guo X T, Pimentel A D and Stefanov T 2023 IEEE Internet Things J. 10 5843
[5] Cheng T, Zhao R S, Wang S, Wang R and Ma H Y 2024 Chin. Phys. B 33 040303
[6] Meloni P, Capotondi A, Deriu G, Brian M, Conti F, Rossi D, Raffo L and Benini L 2018 ACM T Reconfig. Techn. 11 1
[7] Yang S H, Zhang Z G, Lei Z F, Huang Y, Xi K, Wang S L, Liang T J, Tong T, Liu X H, Peng C, Wu F G and Li B 2022 Chin. Phys. B 31 126103
[8] Yang W T, Li Y H, Guo Y X, Zhao H Y, Li Y, Li P, He C H, Guo G, Liu J, Yang S S and An H 2020 Chin. Phys. B 29 108504
[9] Wei J N, Li Y, Liao W L, Liu F, Li Y H, Liu J C, He C H and Guo G 2022 Chin. Phys. B 31 086106
[10] Hu Z L, Yang W T, Zhou B, Liu Y N, He C H, Wang S L, Yu Q Z and Liang T J 2022 J. Nucl. Sci. Technol. 60 473
[11] Mo L H, Yu Q Z, Hu Z L, Zhou B, Yi T C, Yuan L B, Shen F and Liang T J 2023 Microelectron. Reliab. 146 114997
[12] Lbrahim Y, Wang H B, Bai M, Liu Z, Wang J N, Yang Z M and Chen Z M 2020 IEEE Access 8 19490
[13] Abich G, Garibotti R, Reis R and Ost L 2022 IEEE T. Circuits-II 69 679
[14] Zhao X, Du X C, Xiong X, Ma C, Yang W T, Zheng B and Zhou C 2024 Chin. Phys. B 33 078501
[15] Wang H B, Wang Y S, Xiao J H, Wang S L and Liang T J 2021 IEEE Trans. Nucl. Sci. 68 394
[16] Agiakatsikas D, Foutris N, Sari A, Vlagkoulis V, Souvatzoglou L, Psarakis M, Ye R Q, Goodacre J, Luján M, Kastriotou M, Cazzaniga C and Frost C 2024 IEEE Trans. Reliab. 73 771
[17] Ruospo A and Sanchez E 2021 Appl. Sci. 11 6455
[18] Rech P 2024 IEEE Trans. Nucl. Sci. 71 377
[19] Xilinx, lnc. 2018 Zynq-7000 SoC Data Sheet: Overview, DS190 (v1.11.1)
[20] Xilinx, lnc. 2024 Zynq UltraScale+ MPSoC Data Sheet: Overview, DS891 (v1.11).
[21] Liang S Y, Wu H, Zhen L, Hua Q Z, Garg S, Kaddoum G, Hassan M M and Yu K P 2022 IEEE Trans. Intell. Transp. Syst. 23 25345
[22] Cheng Q, HuangMQ, Man C H, Shen A, Dai L Y, Yu H and Hashimoto M 2023 IEEE T. Circuits-I 70 3978
[23] Traiola M, dos Santos F F, Rech P, Cazzaniga C, Sentieys O and Kritikakou A 2024 IEEE Trans. Nucl. Sci. 71 845
[24] Liu B K, He F J, Du S Q, Li J C and Liu W J 2023 J. Intell. Fuzzy Syst. 45 5807
[25] Mascarenhas S and Agarwal M 2021 International Conference on Disruptive Technologies for Multi-Disciplinary Research and Applications (CENTCON), November 19-21, 2021, Bengaluru, India, p. 96
[26] Xilinx, lnc. 2023 Vitis High-Level Synthesis User Guide, UG1399
[27] Xilinx, lnc. 2021 Vitis AI User Guide, UG1414 (v1.2)
[28] Measurement and Reporting of Alpha Particle and Terrestrial Cosmic Ray-induced Soft Errors in Semiconductor Devices
[29] Bosio A, Bernardi P, Ruospo A and Sanchez E 2019 IEEE Latin American Test Symposium (LATS), March 11-13, 2019, Santiago, Chile, p. 1
[30] Howard J W, Carts M A, Stattel R, Rogers C E, Lrwin T L, Dunsmore C, Sciarini J A and LaBel K A 2001 IEEE Radiation Effects DataWorkshop (REDW) and IEEE Nuclear and Space Radiation Effects Conference (NSREC), July 16-20, 2001, Vancouver, BC, Canada, p. 38 |
| No Suggested Reading articles found! |
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
Altmetric
|
|
blogs
Facebook pages
Wikipedia page
Google+ users
|
Online attention
Altmetric calculates a score based on the online attention an article receives. Each coloured thread in the circle represents a different type of online attention. The number in the centre is the Altmetric score. Social media and mainstream news media are the main sources that calculate the score. Reference managers such as Mendeley are also tracked but do not contribute to the score. Older articles often score higher because they have had more time to get noticed. To account for this, Altmetric has included the context data for other articles of a similar age.
View more on Altmetrics
|
|
|
