Shoestring

Abstract

Aggressive technology scaling provides designers with an ever increasing budget of cheaper and faster transistors. Unfortunately, this trend is accompanied by a decline in individual device reliability as transistors become increasingly susceptible to soft errors. We are quickly approaching a new era where resilience to soft errors is no longer a luxury that can be reserved for just processors in high-reliability, mission-critical domains. Even processors used in mainstream computing will soon require protection. However, due to tighter profit margins, reliable operation for these devices must come at little or no cost. This paper presents Shoestring, a minimally invasive software solution that provides high soft error coverage with very little overhead, enabling its deployment even in commodity processors with "shoestring" reliability budgets. Leveraging intelligent analysis at compile time, and exploiting low-cost, symptom-based error detection, Shoestring is able to focus its efforts on protecting statistically-vulnerable portions of program code. Shoestring effectively applies instruction duplication to protect only those segments of code that, when subjected to a soft error, are likely to result in user-visible faults without first exhibiting symptomatic behavior. Shoestring is able to recover from an additional 33.9% of soft errors that are undetected by a symptom-only approach, achieving an overall user-visible failure rate of 1.6%. This reliability improvement comes at a modest performance overhead of 15.8%.

Data Error Detection and Recovery in Embedded Systems: a Literature Review

“…The introduced soft errors can corrupt the data of the program in execution. To counter this data corruption, a number of data flow error detection and recovery techniques have been proposed in literature [1,7,8,[12][13][14][15][16][17][19][20][21]. In previous work [4], we listed several data flow error detection techniques and discussed their reported results.…”

“…A number of data flow error detection techniques have been developed based on a unique duplication mechanism for better fault coverage or lower overhead in terms of memory consumption. The duplication can be applied at various levels such as a full duplication and selective duplication [1,4,7,8,[12][13][14][15]17,18]. Full duplication techniques and selective code duplication techniques are discussed in Sections 2.1 and 2.2 respectively.…”

“…Computers are expected to perform tasks not only quickly, but also correctly [1]. Recent trends in embedded systems attract industries to use them more and more in day-to-day life for an increasing number of applications.…”

“…Still these faults are categorized as systematic faults since given the exact same circumstances these faults will reappear in exactly the same way. Because the environment changes, transient faults don't occur continuously, unlike design and manufacturing faults [1,8,9].…”

“…Software redundancy increases the system's reliability but requires extra memory space and processing time to execute redundant instructions [15]. A number of software-based data error detection and recovery techniques have been proposed and implemented in literature for fault-tolerant embedded systems [1,7,8,[12][13][14][15][16][17][18][19][20][21][22].…”