Neutron Irradiation Testing and Analysis of a Fault-Tolerant RISC-V System-on-Chip - LIRMM - Laboratoire d’Informatique, de Robotique et de Microélectronique de Montpellier Access content directly
Conference Papers Year : 2022

Neutron Irradiation Testing and Analysis of a Fault-Tolerant RISC-V System-on-Chip

Abstract

The radiation in harsh environments affects electronic systems, inducing permanent and temporary errors. These effects lead to unpredictable behaviors detrimental to critical applications and fail-safe systems. This work evaluates the reliability of a fault-tolerant RISC-V System-on-Chip (SoC) under atmospheric neutron irradiation in a particle accelerator. Prior work has analyzed the effectiveness of the hardening techniques of this SoC in simulation and provided a preliminary characterization in an irradiation facility. The applied hardening techniques showed a significant reliability improvement compared to the unhardened implementation of the SoC. The system executed a performance benchmark as workload, which finished correctly in most runs despite suffering from Single Event Effects (SEEs). This work presents a detailed analysis of the experimental results, reporting error rates and classification, extending the analysis given in previous works. Finally, a comprehensive discussion of implementation limitations and the proposition of further improvements are provided.
Fichier principal
Vignette du fichier
2022___DFTS___Neutron_Irradiation_Testing_and_Analysis_of_a_Fault_Tolerant_RISC_V_System_on_Chip (8).pdf (5.39 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

lirmm-03833983 , version 1 (28-10-2022)

Identifiers

Cite

Douglas Almeida dos Santos, André Martins Pio de Mattos, Lucas Matana Luza, Carlo Cazzaniga, Maria Kastriotou, et al.. Neutron Irradiation Testing and Analysis of a Fault-Tolerant RISC-V System-on-Chip. DFT 2022 - 35th IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems, Oct 2022, Austin, United States. pp.1-6, ⟨10.1109/DFT56152.2022.9962335⟩. ⟨lirmm-03833983⟩
53 View
145 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More