Reliability is today one of the major issues for 2 computing devices from the embedded domain up to large high3 performance systems. To safely deploy a computing device in a 4 system, accurate measurements of the failure in time (FIT) rate 5 are required to ensure that the device complies with the project 6 reliability requirements. In this work, we present a method 7 to provide a more accurate device FIT rate estimation from 8 software fault injection. We use the technology sensitivity factor, 9 obtained from beam experiments, as well as architectural and 10 code features to significantly increase the FIT rate estimation 11 accuracy. We compare the estimated FIT rates with the ones 12 measured from radiation experiments of eight codes executed 13 on ARM Cortex-A5 and Cortex-A9. We show that, on average, 14 we can provide a FIT rate estimation accuracy of less than 20% 15 (overestimation) and 35% (underestimation) the expected FIT 16 rate for A5 and A9, respectively.

Accurate FIT Rate Estimation Through High-Level Software Fault Injection / Bodmann, Pablo R.; Oliveira, Daniel; Rech, Paolo. - In: IEEE TRANSACTIONS ON NUCLEAR SCIENCE. - ISSN 0018-9499. - 2022:(2022), pp. 2018-2026. [10.1109/TNS.2022.3195068]

Accurate FIT Rate Estimation Through High-Level Software Fault Injection

Rech, Paolo
2022-01-01

Abstract

Reliability is today one of the major issues for 2 computing devices from the embedded domain up to large high3 performance systems. To safely deploy a computing device in a 4 system, accurate measurements of the failure in time (FIT) rate 5 are required to ensure that the device complies with the project 6 reliability requirements. In this work, we present a method 7 to provide a more accurate device FIT rate estimation from 8 software fault injection. We use the technology sensitivity factor, 9 obtained from beam experiments, as well as architectural and 10 code features to significantly increase the FIT rate estimation 11 accuracy. We compare the estimated FIT rates with the ones 12 measured from radiation experiments of eight codes executed 13 on ARM Cortex-A5 and Cortex-A9. We show that, on average, 14 we can provide a FIT rate estimation accuracy of less than 20% 15 (overestimation) and 35% (underestimation) the expected FIT 16 rate for A5 and A9, respectively.
2022
Bodmann, Pablo R.; Oliveira, Daniel; Rech, Paolo
Accurate FIT Rate Estimation Through High-Level Software Fault Injection / Bodmann, Pablo R.; Oliveira, Daniel; Rech, Paolo. - In: IEEE TRANSACTIONS ON NUCLEAR SCIENCE. - ISSN 0018-9499. - 2022:(2022), pp. 2018-2026. [10.1109/TNS.2022.3195068]
File in questo prodotto:
File Dimensione Formato  
RADECS_full_paper_2021.pdf

accesso aperto

Tipologia: Post-print referato (Refereed author’s manuscript)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 901.87 kB
Formato Adobe PDF
901.87 kB Adobe PDF Visualizza/Apri
Accurate_FIT_Rate_Estimation_Through_High-Level_Software_Fault_Injection.pdf

Solo gestori archivio

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 979.6 kB
Formato Adobe PDF
979.6 kB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/352083
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact