Selective hardening of RISCV soft-processors for space applications

RISC-V soft processors are becoming popular in various fields, including safety-critical ones, thanks to their open-source nature and flexibility. Despite the rapid progress in the reliability analysis of these devices, all the mitigation techniques are usually adopted to the whole soft-processor architecture. In this study, we aim to identify the internal components of the RISC-V architecture that are particularly prone to errors, and accordingly investigate how the reliability of the design is affected when mitigation strategies, such as Triple Modular Redundancy (TMR), are applied selectively just to them. The proposed approach has been applied to RISC-V architecture, NEORV32 which is implemented on Zynq 7020 SoC on a PYNQ-Z2 board. While more vulnerable modules of NEORV32 were identified through accurate reliability analysis, implementing selective TMR in these modules shows achieving satisfactory reliability levels while reducing the overall space requirements compared to a complete TMR design. • RISC-V Architectures gained a lot of interest in Safety Critical applications. • RISC-V Modularity has been exploited to improve reliability. • A new Reliability analysis flow has been developed. • Reliability against SEUS and MBU have been analysed.

Authors

Institutions

Publication Details

Journal
Microelectronics Reliability
Published
2025-03-04
DOI
https://doi.org/10.1016/j.microrel.2025.115667
Citations
3
Primary Topic
Radiation Effects in Electronics
Type
article
Field-Weighted Citation Impact
2.19
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Selective hardening of RISCV soft-processors for space applications

Corrado De Sio, L. Sterpone, Giorgio Cora, S. Azimi
3 citations
Microelectronics Reliability
Radiation Effects in Electronics
2.19
article

Selective hardening of RISCV soft-processors for space applications

Corrado De Sio, L. Sterpone, Giorgio Cora, S. Azimi
article en
3 citations

Abstract

RISC-V soft processors are becoming popular in various fields, including safety-critical ones, thanks to their open-source nature and flexibility. Despite the rapid progress in the reliability analysis of these devices, all the mitigation techniques are usually adopted to the whole soft-processor architecture. In this study, we aim to identify the internal components of the RISC-V architecture that are particularly prone to errors, and accordingly investigate how the reliability of the design is affected when mitigation strategies, such as Triple Modular Redundancy (TMR), are applied selectively just to them. The proposed approach has been applied to RISC-V architecture, NEORV32 which is implemented on Zynq 7020 SoC on a PYNQ-Z2 board. While more vulnerable modules of NEORV32 were identified through accurate reliability analysis, implementing selective TMR in these modules shows achieving satisfactory reliability levels while reducing the overall space requirements compared to a complete TMR design. • RISC-V Architectures gained a lot of interest in Safety Critical applications. • RISC-V Modularity has been exploited to improve reliability. • A new Reliability analysis flow has been developed. • Reliability against SEUS and MBU have been analysed.

Microelectronics ReliabilityVol. 167
Politecnico di Torino (IT)
Affordable and clean energy
Openalex Percentile: Top 13%
Radiation Effects in Electronics
2.19
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Selective hardening of RISCV soft-processors for space applications — Corrado De Sio, L. Sterpone, et al. · Microelectronics Reliability (2025) | TGRS Research Map | TGRS