Improving approximate-TMR using multi-objective optimization genetic algorithm

Albandes, Iuri; Serrano-Cases, Alejandro; Sanchez-Clemente, Antonio; Martins, Mayler G. A.; Martínez-Álvarez, Antonio; Cuenca-Asensi, Sergio; Kastensmidt, Fernanda Lima

doi:10.1109/latw.2018.8349665

Cited by 12 publications

(15 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various approximate/inexact TMR schemes have been proposed at the logic level [6], [7], [8]. They mainly aim at reducing the area required by the hardened circuit by tradingoff the precision of the detection/mitigation scheme.…”

Section: Related Workmentioning

confidence: 99%

A Neural Network Based Fault Management Scheme for Reliable Image Processing

Biasielli

Bolchini

Cassano

et al. 2020

IEEE Trans. Comput.

View full text Add to dashboard Cite

Traditional reliability approaches introduce relevant costs to achieve unconditional correctness during data processing. However, many application environments are inherently tolerant to a certain degree of inexactness or inaccuracy. In this paper, we focus on the practical scenario of image processing in space, a domain where faults are a threat, while the applications are inherently tolerant to a certain degree of errors. We first introduce the concept of usability of the processed image to relax the traditional requirement of unconditional correctness, and to limit the computational overheads related to reliability. We then introduce our new flexible and lightweight fault management methodology for inaccurate application environments. A key novelty of our scheme is the utilization of neural networks to reduce the costs associated with the occurrence and the detection of faults. Experiments on two aerospace image processing case studies show overall time savings of 14.89% and 34.72% for the two applications, respectively, as compared with the baseline classical Duplication with Comparison scheme.

show abstract

Section: Related Workmentioning

confidence: 99%

A Neural Network Based Fault Management Scheme for Reliable Image Processing

Biasielli

Bolchini

Cassano

et al. 2020

IEEE Trans. Comput.

View full text Add to dashboard Cite

show abstract

“…Several approaches defined approximate hardening schemes at the logic level, by enhancing TMR (e.g. [8], [9], [15]), or DWC (e.g., [16], [17]) or focusing on the specific voter/checker component [18]. The focus is on a combinational function having a single-bit output; the basic strategy these works adopt is to approximate the redundant circuit to minimize its area while limiting the error rate, i.e., the percentage of not detected/mitigated faults.…”

Section: Related Workmentioning

confidence: 99%

“…the of the nominal application. To reduce this impact, AC has been exploited to reduce the replica's computations in redundancy-based fault mitigation schemes, such as approximate/inexact Triple Modular Redundancy (TMR) [8], [9], [10], or fault detection ones [11], [12]. Common denominator to all these approaches is performing error checking/mitigation at the granularity of the single logic or scalar value, instead of considering the quality of the entire output image/signal as a whole to decide whether to trigger a re-execution or not.…”

Section: Introductionmentioning

confidence: 99%

Approximation-based Fault Tolerance in Image Processing Applications

Biasielli¹,

Bolchini

Cassano

et al. 2021

IEEE Trans. Emerg. Topics Comput.

View full text Add to dashboard Cite

Image processing applications exhibit an intrinsic degree of fault tolerance due to i) the redundant nature of images, and ii) the possible ability of the consumers of the application output to effectively carry out their task even when it is slightly corrupted. In this application scenario the classical Duplication with Comparison (DWC) scheme, that rejects images (and requires re-executions) when the two replicas' outputs differ in a per-pixel comparison, may be over-conservative. In this paper, we propose a novel lightweight fault tolerant scheme specifically tailored for image processing applications. The proposed scheme enhances the state-of-the-art by: i) improving the DWC scheme by replacing one of the two exact replicas with an approximated counterpart, and ii) allowing to distinguish between usable and unusable images instead of corrupted and uncorrupted ones by means of a Convolutional Neural Network-based checker.To tune the proposed scheme we introduce a specific design methodology that optimizes both execution time and fault detection capability of the hardened system. We report the results of the application of the proposed approach on two case studies; our proposal achieves an average execution time reduction larger than 30% w.r.t. the DWC with re-execution, and less than 4% misclassified unusable images.

show abstract

“…Experimental results obtained for several combinational circuits demonstrated that the evolutionary approach can produce better solutions, but the probabilistic approach is close. In the followup work, Albandes et al [21] propose another approach. GA has to find replacements for some gates according to a predefined library that specifies what transformations are valid for each logic gate.…”

Section: A Gate Level Approximationsmentioning

confidence: 99%

Evolutionary Algorithms in Approximate Computing: A Survey

Sekanina

2021

JICS

View full text Add to dashboard Cite

In recent years, many design automation methods have been developed to routinely create approximate implementations of circuits and programs that show excellent trade-offs between the quality of output and required resources. This paper deals with evolutionary approximation as one of the popular approximation methods. The paper provides the first survey of evolutionary algorithm (EA)-based approaches applied in the context of approximate computing. The survey reveals that EAs are primarily applied as multi-objective optimizers. We propose to divide these approaches into two main classes: (i) parameter optimization in which the EA optimizes a vector of system parameters, and (ii) synthesis and optimization in which EA is responsible for determining the architecture and parameters of the resulting system. The evolutionary approximation has been applied at all levels of design abstraction and in many different applications. The neural architecture search enabling the automated hardware-aware design of approximate deep neural networks was identified as a newly emerging topic in this area.

show abstract

Improving approximate-TMR using multi-objective optimization genetic algorithm

Cited by 12 publications

References 14 publications

A Neural Network Based Fault Management Scheme for Reliable Image Processing

A Neural Network Based Fault Management Scheme for Reliable Image Processing

Approximation-based Fault Tolerance in Image Processing Applications

Evolutionary Algorithms in Approximate Computing: A Survey

Contact Info

Product

Resources

About