Soft error mitigation and recovery of SRAM-based FPGAs using brain-inspired hybrid-grained scrubbing mechanism

Frontiers in Computational Neuroscience

Neuroscience

He Chen¹  Yu Xie¹  Tingting Qiao¹  Yizhuang Xie² 

[1] Beijing Key Laboratory of Embedded Real-Time Information Processing Technology, School of Information and Electronics, Beijing Institute of Technology, Beijing, China;null;

关键词: brain-inspired;    configuration scrubbing;    hybrid-grained;    single event upset (SEU);    SRAM-based FPGA;   

DOI  :  10.3389/fncom.2023.1268374

 received in 2023-07-28, accepted in 2023-08-15,  发布年份 2023

来源: Frontiers

【 摘 要 】

Soft error has increasingly become a critical concern for SRAM-based field programmable gate arrays (FPGAs), which could corrupt the configuration memory that stores configuration data describing the custom-designed circuit architecture. To mitigate this kind of error, this study proposes a brain-inspired hybrid-grained scrubbing mechanism consisting of fine-grained and coarse-grained scrubbing to mitigate and repair the errors as quickly as possible after an SEU occurrence. Inspired by the human brain's ability to filter out redundant and irrelevant information, we propose a mechanism that can mask invalid position information when errors occur. Compared with the scrubbing of full configuration memory, this mechanism can achieve precise error location and recovery utilizing targeted scrubbing of specific frames or modules. The effectiveness is evaluated by executing fault injection campaigns on the International Symposium on Circuits and Systems 1989 (ISCAS89) benchmark circuits and fault tolerant fast Fourier transform (FT-FFT) circuit. If upsets are detected, they will be repaired with fine-grained or coarse-grained scrubbing depending on their location. The experiment results show that this mechanism can effectively mitigate and repair single-bit upsets (SBUs) and double-bit upsets (DBUs). In addition, the mechanism is proven to be superior in error recovery time and hardware overhead compared to counterpart approaches.

【 授权许可】

Unknown   
Copyright © 2023 Xie, Qiao, Xie and Chen.