Citation: Nikseresht, M.;
Vankeirsbilck, J.; Boydens, J. A Study
on Selective Implementation
Approaches for Soft Error Detection
Using S-SWIFT-R. Electronics 2022, 11,
3380. https://doi.org/10.3390/
electronics11203380
Academic Editors: Sanjay Misra,
Robertas Damaševiˇcius and
Bharti Suri
Received: 23 August 2022
Accepted: 14 October 2022
Published: 19 October 2022
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2022 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Article
A Study on Selective Implementation Approaches for Soft Error
Detection Using S-SWIFT-R
Mohaddaseh Nikseresht * , Jens Vankeirsbilck * and Jeroen Boydens *
Department of Computer Science, KU Leuven, Spoorwegstraat 12, 8200 Bruges, Belgium
* mohaddaseh.nikseresht@kuleuven.be (M.N.); jens.vankeirsbilck@kuleuven.be (J.V.);
jeroen.boydens@kuleuven.be (J.B.)
Abstract:
This article analyzes diverse criteria for effectively implementing selective hardening
against soft errors through software-based strategies. The goal is to obtain maximum fault coverage
with the least amount of overhead for each specific application. To achieve this objective, the analysis
is conducted based on two important phases, pre-selection and selective hardening of registers.
In the pre-selection phase, the impact of the two most used selection metrics has been examined:
(1) selecting registers based on their memory interaction vs. (2) selecting registers depending on fault
injection vulnerability. Toward the selective hardening phase, the impact of gradually increasing the
number of registers to protect is examined. Experiments have been conducted on 8 academic case
studies and 1 industrial case study. Faults have been injected into the case studies using our in-house
fault injector. The results indicate that selecting registers based on the fault injected into the system
has an overall 10% better performance in comparison to selecting registers based on the memory
interaction in 6 out of 8 academic case studies and also the industrial case study. Additionally, there
is a significant improvement in reliability when increasing the number of registers to protect at the
expense of rising overhead. In this work, these comparisons and analyses are presented.
Keywords:
fault tolerance; reliability; embedded systems; soft errors; single event upset (SEU);
selective implementation
1. Introduction
An embedded system is a combination of computer hardware and software that is
intended to perform a particular function inside a larger system [
1
]. A wide range of em-
bedded systems can be found in different applications, from digital watches and cameras
to medical systems, autonomous systems, and avionics [
2
]. Microprocessors are the heart
of embedded systems. Over the last few decades, there have been significant scientific
advancements in the creation of microprocessors. Some of these advancements include
a huge boost in their performance, as well as an ever increasing integration density. Most
of these improvements are thanks to advancements toward microtechnology; electronic
components have become smaller, which has made it feasible to achieve these significant
outcomes. However, as a result of these modifications, transistor sizes are diminishing,
and voltage source levels and noise margins have also been reduced [3]. The result is that
electronic devices became less reliable, and thus microprocessors became more suscep-
tible to various types of faults, particularly those caused by radiation [
4
]. This matters
since, in mission-critical systems, radiation impact on electronic components could have
devastating repercussions.
These negative impacts are caused by high-energy particles influencing electronic
components, which may result in the ionization of their internal silicon structures, either
directly or indirectly. These incidents might have a long-term effect on the functioning of the
component (permanent faults) or just have a short-term effect (transient faults). In contrast
to permanent faults, transient faults may cause the system’s behavior to change briefly
Electronics 2022, 11, 3380. https://doi.org/10.3390/electronics11203380 https://www.mdpi.com/journal/electronics
