Radiation Effects Modeling and Analysis in RRAM-Based In-Memory Computing Systems

Tingrui Ren; Xvpeng Han; Kexin Yao; Huimeng Guo; Liang Wang; Yuanfu Zhao; Bi Wang

doi:10.1109/ICREED65908.2025.11036223

Radiation Effects Modeling and Analysis in RRAM-Based In-Memory Computing Systems

Tingrui Ren
, Xvpeng Han
, Kexin Yao
, Huimeng Guo
, Liang Wang
, Yuanfu Zhao
, Bi Wang

Beihang University
Beijing Microelectronics Technology Institute
Hangzhou Dianzi University
School of Transportation Science and Engineering

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

摘要

RRAM-based in-memory computing architectures offer ultra-high energy efficiency for matrixvector multiplication (MVM), making them highly suitable for large-scale neural network algorithms. However, the radiation tolerance of neuromorphic computing systems has not been comprehensively assessed. This study explores the sensitivity of RRAM-based in-memory computing architectures to singleevent effects (SEE) and total ionizing dose (TID) during the inference phase. By incorporating radiation-induced conductance error models into each inference simulation, based on weight mapping rules, we analyze the impact of radiation on the inference accuracy of various neural network models. The results demonstrate that RRAM-based in-memory computing systems can effectively withstand a TID up to 30 Mrad.

源语言	英语
主期刊名	2025 6th International Conference on Radiation Effects of Electronic Devices, ICREED 2025
出版商	Institute of Electrical and Electronics Engineers Inc.
ISBN（电子版）	9798331549299
DOI	https://doi.org/10.1109/ICREED65908.2025.11036223
出版状态	已出版 - 2025
已对外发布	是
活动	6th International Conference on Radiation Effects of Electronic Devices, ICREED 2025 - Yangzhou, 中国期限: 16 4月 2025 → 18 4月 2025

出版系列

姓名	2025 6th International Conference on Radiation Effects of Electronic Devices, ICREED 2025

会议

会议	6th International Conference on Radiation Effects of Electronic Devices, ICREED 2025
国家/地区	中国
市	Yangzhou
时期	16/04/25 → 18/04/25

联合国可持续发展目标

此成果有助于实现下列可持续发展目标：

可持续发展目标 7 经济适用的清洁能源

访问文件

10.1109/ICREED65908.2025.11036223

其它文件与链接

链接到 Scopus 的出版物

引用此

Ren, T., Han, X., Yao, K., Guo, H., Wang, L., Zhao, Y., & Wang, B. (2025). Radiation Effects Modeling and Analysis in RRAM-Based In-Memory Computing Systems. 在 2025 6th International Conference on Radiation Effects of Electronic Devices, ICREED 2025 (2025 6th International Conference on Radiation Effects of Electronic Devices, ICREED 2025). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICREED65908.2025.11036223

Ren, Tingrui ; Han, Xvpeng ; Yao, Kexin 等. / Radiation Effects Modeling and Analysis in RRAM-Based In-Memory Computing Systems. 2025 6th International Conference on Radiation Effects of Electronic Devices, ICREED 2025. Institute of Electrical and Electronics Engineers Inc., 2025. (2025 6th International Conference on Radiation Effects of Electronic Devices, ICREED 2025).

@inproceedings{d336e39868ba43f48f4c49748aecd28c,

title = "Radiation Effects Modeling and Analysis in RRAM-Based In-Memory Computing Systems",

abstract = "RRAM-based in-memory computing architectures offer ultra-high energy efficiency for matrixvector multiplication (MVM), making them highly suitable for large-scale neural network algorithms. However, the radiation tolerance of neuromorphic computing systems has not been comprehensively assessed. This study explores the sensitivity of RRAM-based in-memory computing architectures to singleevent effects (SEE) and total ionizing dose (TID) during the inference phase. By incorporating radiation-induced conductance error models into each inference simulation, based on weight mapping rules, we analyze the impact of radiation on the inference accuracy of various neural network models. The results demonstrate that RRAM-based in-memory computing systems can effectively withstand a TID up to 30 Mrad.",

keywords = "In-memory computing (IMC), neuromorphic computing, single-event effects (SEE), total ionizing dose (TID)",

author = "Tingrui Ren and Xvpeng Han and Kexin Yao and Huimeng Guo and Liang Wang and Yuanfu Zhao and Bi Wang",

note = "Publisher Copyright: {\textcopyright} 2025 IEEE.; 6th International Conference on Radiation Effects of Electronic Devices, ICREED 2025 ; Conference date: 16-04-2025 Through 18-04-2025",

year = "2025",

doi = "10.1109/ICREED65908.2025.11036223",

language = "英语",

series = "2025 6th International Conference on Radiation Effects of Electronic Devices, ICREED 2025",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2025 6th International Conference on Radiation Effects of Electronic Devices, ICREED 2025",

address = "美国",

}

Ren, T, Han, X, Yao, K, Guo, H, Wang, L, Zhao, Y & Wang, B 2025, Radiation Effects Modeling and Analysis in RRAM-Based In-Memory Computing Systems. 在 2025 6th International Conference on Radiation Effects of Electronic Devices, ICREED 2025. 2025 6th International Conference on Radiation Effects of Electronic Devices, ICREED 2025, Institute of Electrical and Electronics Engineers Inc., 6th International Conference on Radiation Effects of Electronic Devices, ICREED 2025, Yangzhou, 中国, 16/04/25. https://doi.org/10.1109/ICREED65908.2025.11036223

Radiation Effects Modeling and Analysis in RRAM-Based In-Memory Computing Systems. / Ren, Tingrui; Han, Xvpeng; Yao, Kexin 等.
2025 6th International Conference on Radiation Effects of Electronic Devices, ICREED 2025. Institute of Electrical and Electronics Engineers Inc., 2025. (2025 6th International Conference on Radiation Effects of Electronic Devices, ICREED 2025).

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

TY - GEN

T1 - Radiation Effects Modeling and Analysis in RRAM-Based In-Memory Computing Systems

AU - Ren, Tingrui

AU - Han, Xvpeng

AU - Yao, Kexin

AU - Guo, Huimeng

AU - Wang, Liang

AU - Zhao, Yuanfu

AU - Wang, Bi

PY - 2025

Y1 - 2025

N2 - RRAM-based in-memory computing architectures offer ultra-high energy efficiency for matrixvector multiplication (MVM), making them highly suitable for large-scale neural network algorithms. However, the radiation tolerance of neuromorphic computing systems has not been comprehensively assessed. This study explores the sensitivity of RRAM-based in-memory computing architectures to singleevent effects (SEE) and total ionizing dose (TID) during the inference phase. By incorporating radiation-induced conductance error models into each inference simulation, based on weight mapping rules, we analyze the impact of radiation on the inference accuracy of various neural network models. The results demonstrate that RRAM-based in-memory computing systems can effectively withstand a TID up to 30 Mrad.

AB - RRAM-based in-memory computing architectures offer ultra-high energy efficiency for matrixvector multiplication (MVM), making them highly suitable for large-scale neural network algorithms. However, the radiation tolerance of neuromorphic computing systems has not been comprehensively assessed. This study explores the sensitivity of RRAM-based in-memory computing architectures to singleevent effects (SEE) and total ionizing dose (TID) during the inference phase. By incorporating radiation-induced conductance error models into each inference simulation, based on weight mapping rules, we analyze the impact of radiation on the inference accuracy of various neural network models. The results demonstrate that RRAM-based in-memory computing systems can effectively withstand a TID up to 30 Mrad.

KW - In-memory computing (IMC)

KW - neuromorphic computing

KW - single-event effects (SEE)

KW - total ionizing dose (TID)

UR - https://www.scopus.com/pages/publications/105010197440

U2 - 10.1109/ICREED65908.2025.11036223

DO - 10.1109/ICREED65908.2025.11036223

M3 - 会议稿件

AN - SCOPUS:105010197440

T3 - 2025 6th International Conference on Radiation Effects of Electronic Devices, ICREED 2025

BT - 2025 6th International Conference on Radiation Effects of Electronic Devices, ICREED 2025

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 6th International Conference on Radiation Effects of Electronic Devices, ICREED 2025

Y2 - 16 April 2025 through 18 April 2025

ER -

Ren T, Han X, Yao K, Guo H, Wang L, Zhao Y 等. Radiation Effects Modeling and Analysis in RRAM-Based In-Memory Computing Systems. 在 2025 6th International Conference on Radiation Effects of Electronic Devices, ICREED 2025. Institute of Electrical and Electronics Engineers Inc. 2025. (2025 6th International Conference on Radiation Effects of Electronic Devices, ICREED 2025). doi: 10.1109/ICREED65908.2025.11036223

Radiation Effects Modeling and Analysis in RRAM-Based In-Memory Computing Systems

摘要

出版系列

会议

联合国可持续发展目标

访问文件

其它文件与链接

指纹

引用此