2009 24th IEEE International Symposium on Defect and Fault Tolerance in VLSI Systems 2009
DOI: 10.1109/dft.2009.38
|View full text |Cite
|
Sign up to set email alerts
|

Transient Error Detection and Recovery in Processor Pipelines

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
7
0

Year Published

2011
2011
2013
2013

Publication Types

Select...
3
2

Relationship

0
5

Authors

Journals

citations
Cited by 7 publications
(7 citation statements)
references
References 11 publications
0
7
0
Order By: Relevance
“…4 (e.g. [6]'s Checksum-based scheme). This simple strategy is not so efficient to sample the CED's results [15] [21], and then its recovery efficiency is moderate.…”
Section: Recovery Schemes For Dealing With Short and Long-duratimentioning
confidence: 99%
See 2 more Smart Citations
“…4 (e.g. [6]'s Checksum-based scheme). This simple strategy is not so efficient to sample the CED's results [15] [21], and then its recovery efficiency is moderate.…”
Section: Recovery Schemes For Dealing With Short and Long-duratimentioning
confidence: 99%
“…The current trend in solutions to cope with transient-fault effects is applying protection techniques at different abstraction levels of the design [3][4][5] [6]. The idea is thus to prevent the use of costly fault-tolerance mechanisms like the tripe modular redundancy, taking advantage of cheaper mitigation techniques that ensure satisfactory soft-error coverage for the system's most recurrent operations.…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation
“…The today's trend in efficient protections against transient faults is applying mitigation techniques at different abstraction levels of the design [3,4]. The idea behind is the avoidance of costly faulttolerance mechanisms like triple modular redundancy, taking advantage of cheaper mitigation techniques that ensure satisfactory soft error coverage for the system's most recurrent operations.…”
Section: Introductionmentioning
confidence: 99%
“…Concurrent error detection (CED) mechanisms are designed at lower abstraction levels while recovery-based error correction procedures (ECPs) at higher levels. This strategy takes advantage of recovery circuits that are already present in modern microprocessors to recompute instructions in case of branch misprediction [5] [6]. Then, only CED mechanisms need to be implemented, and as they are optimized at lower levels, they can monitor circuit's fault-prone nodes much closer than higher-level schemes could.…”
Section: Introductionmentioning
confidence: 99%