Software-Implemented Hardware Error Detection: Costs and Gains

Schiffel, Ute; Schmitt, André; Süßkraut, Martin; Fetzer, Christof

doi:10.1109/depend.2010.16

Cited by 10 publications

(21 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The failure probability of each task on a certain PE is randomly generated between 1 × 10 −5 and 1 × 10 −7 . We again use the exponential model in [18], i.e., the undetectable faults reduce exponentially with linear fault detection effort. Random fault detectors are generated following this law.…”

Section: Methodsmentioning

confidence: 99%

“…A software fault detector typically transforms the original program into an instrumented version, adding the capability to detect transient faults that occur at runtime of the program. The arithmetic codes [18] and critical variable technique [13] are examples of this kind. We assume that each task instance tries to implement the failsilent behavior, i.e., as long as the fault detector 1 reports a fault, this specific task instance will not produce any output.…”

Section: Fault Model and Fault Tolerancementioning

confidence: 99%

“…We reuse the result of [18] and assume that the rate of undetectable faults decreases exponentially with linear fault detection effort. We further assume the perfect fault detection (100% coverage) incurs 300% timing overhead (typical value in [18]). Several fault detectors with timing overhead ranging from 0% to 300% (corresponds to detection coverage from 0% to 100%) are tested.…”

Section: B Experimental Analysis On the Impact Of Imperfect Fault Dementioning

confidence: 99%

“…On the other hand, even if implementable, perfect detectors typically come with high resource and timing overheads. In recent work [12,18] it has been shown that the time needed for high-coverage fault detection may become much longer than the execution time of the task itself (e.g. the timing overhead could be 400% using techniques proposed in [12]).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Towards fault-tolerant embedded systems with imperfect fault detection

Huang

Raabe

et al. 2012

Proceedings of the 49th Annual Design Automation Conference

View full text Add to dashboard Cite

Many state-of-the-art approaches on fault-tolerant system design make the simplifying assumption that all faults are detected within a certain time interval. However, based on a detailed experimental analysis, we observe that perfect fault detection is not only an impractical assumption but even if implementable also a suboptimal design decision. This paper presents an approach that takes imperfect fault detection into account. Novel analysis and optimization techniques are developed, which distinguish detectable and undetectable faults in the overall workflow. Besides synthesizing the task schedules, our approach also decides which of the available fault detectors is selected for each task instance. Experimental results show that our approach finds solutions with several orders of magnitude higher reliability than current approaches.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Fault Model and Fault Tolerancementioning

confidence: 99%

Section: B Experimental Analysis On the Impact Of Imperfect Fault Dementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Towards fault-tolerant embedded systems with imperfect fault detection

Huang

Raabe

et al. 2012

Proceedings of the 49th Annual Design Automation Conference

View full text Add to dashboard Cite

show abstract

“…Others execute duplicates of the whole program using several threads, e. g., [16]. For all approaches that are based on replication, it is not possible to provide guarantees with respect to permanent hardware errors [13].…”

Section: Related Workmentioning

confidence: 99%

ANB- and ANBDmem-Encoding: Detecting Hardware Errors in Software

Schiffel

Schmitt

Süßkraut

et al. 2010

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. It is expected that commodity hardware is becoming less reliable because of the continuously decreasing feature sizes of integrated circuits. Nevertheless, more and more commodity hardware with insufficient error detection is used in critical applications. One possible solution is to detect hardware errors in software using arithmetic AN-codes. These codes detect hardware errors independent of the actual failure modes of the underlying hardware. However, measurements have shown that AN-codes still exhibit large rates of undetected silent data corruptions (SDC). These high rates of undetected SDCs are caused by the insufficient protection of control and data flow through AN-codes. In contrast, ANB-and ANBD-codes promise much higher error detection rates because they also detect errors in control and data flow. We present our encoding compiler that automatically applies either an AN-, ANBor ANBD-code to an application. Our error injections show that AN-, ANB-, and ANBD-codes successfully detect errors and more important that indeed ANB-and ANBD-codes reduce the SDC rate more effectively than AN-codes. The difference between ANBD-and ANB-codes is also visible but less pronounced.

show abstract