2010 IEEE/IFIP International Conference on Dependable Systems &Amp; Networks (DSN) 2010
DOI: 10.1109/dsn.2010.5544923
|View full text |Cite
|
Sign up to set email alerts
|

A numerical optimization-based methodology for application robustification: Transforming applications for error tolerance

Abstract: There have been several attempts at correcting process vari ation induced errors by identifying and masking these er rors at the circuit and architecture level [10,271. These ap proaches take up valuable die area and power on the chip. As an alternative, we explore the feasibility of an approach that allows these errors to occur freely, and handle them in software, at the algorithmic level. In this paper, we present a general approach to converting applications into an error tolerant form by recasting these ap… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
25
0

Year Published

2010
2010
2017
2017

Publication Types

Select...
5
3
1

Relationship

3
6

Authors

Journals

citations
Cited by 37 publications
(25 citation statements)
references
References 15 publications
0
25
0
Order By: Relevance
“…It is, therefore, essential to develop simulation and emulation infrastructures for UnO computing systems which are scalable while retaining variability modeling accuracy. The work in this direction has been somewhat limited (e.g., [77] in context of performance variability for a specific system or error emulation in [19], [63]) and a key challenge for UnO software methods is building such emulation platforms for large class of computing systems which model all manifestations (error, delay, power, aging, etc.) of variability.…”
Section: F Variability Simulation Challengesmentioning
confidence: 99%
See 1 more Smart Citation
“…It is, therefore, essential to develop simulation and emulation infrastructures for UnO computing systems which are scalable while retaining variability modeling accuracy. The work in this direction has been somewhat limited (e.g., [77] in context of performance variability for a specific system or error emulation in [19], [63]) and a key challenge for UnO software methods is building such emulation platforms for large class of computing systems which model all manifestations (error, delay, power, aging, etc.) of variability.…”
Section: F Variability Simulation Challengesmentioning
confidence: 99%
“…In context of erroneous UnO machines, several alternatives exist ranging from detecting and then correcting faults within the application as they arise (e.g., [61], [62]) to designing applications to be inherently error-tolerant (e.g., application robustification [63]). In addition, many applications have inherent algorithmic and cognitive error tolerance.…”
Section: B Software Adaptations For Quality-complexity Tradeoffsmentioning
confidence: 99%
“…2, [60] explored a variability-aware duty cycle scheduler where application modules specify a range of acceptable duty cycling ratios, and the scheduler selects the actual duty cycle based on run-time monitoring of operational parameters, and a powertemperature model that is learned off-line for the specific processor instance. In context of erroneous UnO machines, several alternatives exist ranging from detecting and then correcting faults within the application as they arise (e.g., [23,25]) to designing applications to be inherently error-tolerant (e.g., application robustification [55]). …”
Section: B Variability-aware Softwarementioning
confidence: 99%
“…Alternatively, separate processors can be employed to ensure correctness or enhance performance [7,8]. Other techniques, such as those described in [6] and [13], allow the propagation of errors up to the software, where they can either be ignored if the application is robust enough, or corrected through software error correction.…”
Section: Error Resiliency Techniquesmentioning
confidence: 99%