2005
DOI: 10.1109/tns.2005.860689
|View full text |Cite
|
Sign up to set email alerts
|

Single-event-upset-like fault injection: a comprehensive framework

Abstract: INTERNATIONAL STANDARD SERIAL NUMBERS (Translation and Original): 0018-9499International audienceAn approach to reproduce radiation ground testing results for the study of microprocessors vulnerability to single event upset (SEU) is described in this paper. Resulting cross-sections fit very well with measured ones

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
3
0

Year Published

2007
2007
2020
2020

Publication Types

Select...
4
4
1

Relationship

0
9

Authors

Journals

citations
Cited by 19 publications
(4 citation statements)
references
References 12 publications
0
3
0
Order By: Relevance
“…A great deal of experiments have proved that such an estimation is very close to real measure as well as that the strategy can be successfully applied to advanced processors [63].…”
Section: Simulated Fault Injection Experimentsmentioning
confidence: 78%
“…A great deal of experiments have proved that such an estimation is very close to real measure as well as that the strategy can be successfully applied to advanced processors [63].…”
Section: Simulated Fault Injection Experimentsmentioning
confidence: 78%
“…Such tests constitute a very popular technique to verify designs running in FPGAs. However, an actual environment should be emulated in such a way that bitflips must be injected in random cells following a temporal pattern compatible with a Poisson distribution with a specific mean time between failures (MTBF) [37]. Unfortunately, to the authors' knowledge, errors are typically just injected as SBUs since it is unusual to know the relation between logic and physical addresses to flip adjacent bits.…”
Section: B Applications On Seu Injection Testsmentioning
confidence: 99%
“…An exponential distribution describes the time between events in a Poisson process, which occur continuously and independently at a constant average rate. This is very suitable for modeling fault injection times [7] as transient errors are infrequent and independent of earlier errors. During the simulation, the processor model iteratively injects transient faults based on the exponential distribution.…”
Section: Fault Injectionmentioning
confidence: 99%