article · 2024

AIP-SEM: An Efficient ML-Boost In-Place Soft Error Mitigation Method for SRAM-Based FPGA

Zhuoli Wang, Lei Chen, Shuo Wang, Jing Zhou, Chunsheng Tian, Hanxu Feng

Cited by 1Abstract and details only

Abstract

With the wide application of SRAM-base FPGA in aerospace engineering, the radiation resistance performance of FPGAs becomes unprecedented important. To correct errors, the Triple Modular Redundancy (TMR) technique uses a voter and incurs significant PPA overhead. We propose an efficient in-place soft error mitigation method, that can mitigate soft errors without any additional PPA overhead. Compared to other synthesis-based algorithms, our method uses an XGBoost-based prediction model which predicts time-consuming circuit metrics. For the EPFL benchmark circuit, our approach achieves up to 19.42% runtime speedup, and under 3% loss on the failure rate reduction.

Cite this paper

APA 7

Wang, Z., Chen, L., Wang, S., Zhou, J., Tian, C., & Feng, H. (2024). AIP-SEM: An Efficient ML-Boost In-Place Soft Error Mitigation Method for SRAM-Based FPGA. https://doi.org/10.1109/iseda62518.2024.10617841

MLA 9

Wang, Zhuoli, et al. “AIP-SEM: An Efficient ML-Boost In-Place Soft Error Mitigation Method for SRAM-Based FPGA.” vol. 44, 2024, pp. 351–54, https://doi.org/10.1109/iseda62518.2024.10617841.

Chicago

Wang, Zhuoli, Lei Chen, Shuo Wang, Jing Zhou, Chunsheng Tian, and Hanxu Feng. 2024. “AIP-SEM: An Efficient ML-Boost In-Place Soft Error Mitigation Method for SRAM-Based FPGA.” https://doi.org/10.1109/iseda62518.2024.10617841.

Harvard

Wang, Z. et al. (2024) ‘AIP-SEM: An Efficient ML-Boost In-Place Soft Error Mitigation Method for SRAM-Based FPGA’. Available at: https://doi.org/10.1109/iseda62518.2024.10617841.

BibTeX

@article{wang2024efficient,
  title = {{AIP-SEM: An Efficient ML-Boost In-Place Soft Error Mitigation Method for SRAM-Based FPGA}},
  author = {Wang, Zhuoli and Chen, Lei and Wang, Shuo and Zhou, Jing and Tian, Chunsheng and Feng, Hanxu},
  volume = {44},
  pages = {351--354},
  year = {2024},
  doi = {10.1109/iseda62518.2024.10617841}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.