EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Fast and Accurate Error Simulation for CNNs Against Soft Errors

Cristiana Bolchini, Luca Cassano, Antonio Miele, Alessandro Toschi

IEEE Transactions on Computers · 01.04.2023 · 72 (4) · 984-997

DOI: 10.1109/tc.2022.3184274 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Computers, erschienen am 01.04.2023. Verfasst von Cristiana Bolchini und 3 weiteren Autor:innen. Die Arbeit wurde bisher 46-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The great quest for adopting AI-based computation for safety-/mission-critical applications motivates the interest towards methods for assessing the robustness of the application w.r.t. not only its training/tuning but also errors due to faults, in particular soft errors, affecting the underlying hardware. Two strategies exist: architecture-level fault injection and application-level functional error simulation. We present a framework for the reliability analysis of Convolutional Neural Networks (CNNs) via an error simulation engine that exploits a set of validated error models extracted from a detailed fault injection campaign. These error models are defined based on the corruption patterns of the output of the CNN operators induced by faults and bridge the gap between fault injection and error simulation, exploiting the advantages of both approaches. We compared our methodology against SASSIFI for the accuracy of functional error simulation w.r.t. fault injection, and against TensorFI in terms of speedup for the error simulation strategy. Experimental results show that our methodology achieves about 99% accuracy of the fault effects w.r.t. SASSIFI, and a speedup ranging from 44x up to 63x w.r.t. TensorFI, that only implements a limited set of error models.

Zitieren

APA

Bolchini, C., Cassano, L., Miele, A., & Toschi, A. (2023). Fast and Accurate Error Simulation for CNNs Against Soft Errors. IEEE Transactions on Computers, 72(4), 984-997. https://doi.org/10.1109/tc.2022.3184274

Vancouver

Bolchini C, Cassano L, Miele A, Toschi A. Fast and Accurate Error Simulation for CNNs Against Soft Errors. IEEE Transactions on Computers. 2023;72(4):984-997. doi:10.1109/tc.2022.3184274

BibTeX
@article{Bolchini2023,
  author = {Bolchini, Cristiana and Cassano, Luca and Miele, Antonio and Toschi, Alessandro},
  title = {Fast and Accurate Error Simulation for CNNs Against Soft Errors},
  journal = {IEEE Transactions on Computers},
  year = {2023},
  volume = {72},
  number = {4},
  pages = {984--997},
  doi = {10.1109/tc.2022.3184274}
}
Kostenlos starten →