Detecting Soft Errors in Stencil based Computations

Sharma, Vishal; Gopalkrishnan, G.; Bronevetsky, Greg

doi:10.2172/1184174

Cited by 9 publications

(7 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our work focuses on soft error detection for stencil programs. Application-independent approaches for iterative programs rely on observing the evolution of a value over time to detect anomalies (e.g., AID [17] uses curve fitting, SSD [46] uses support vector machines (SVM) regression, and Reference [42] uses a machine learning-based approach to build regression models for synthesizing low cost detectors). Gomez and Capello exploits multivariate interpolation to detect and correct corruption in stencil application [25].…”

Section: Additional Related Workmentioning

confidence: 99%

FPD etect

Das

Krishnamoorthy

Briggs

et al. 2020

ACM Trans. Archit. Code Optim.

View full text Add to dashboard Cite

We present FPDetect, a low-overhead approach for detecting logical errors and soft errors affecting stencil computations without generating false positives. We develop an offline analysis that tightly estimates the number of floating-point bits preserved across stencil applications. This estimate rigorously bounds the values expected in the data space of the computation. Violations of this bound can be attributed with certainty to errors. FPDetect helps synthesize error detectors customized for user-specified levels of accuracy and coverage. FPDetect also enables overhead reduction techniques based on deploying these detectors coarsely in space and time. Experimental evaluations demonstrate the practicality of our approach. CCS Concepts: • Hardware → Error detection and error correction; • Computer systems organization → Reliability; • Software and its engineering → Software verification; • Mathematics of computing → Numerical analysis;

show abstract

Section: Additional Related Workmentioning

confidence: 99%

FPD etect

Das

Krishnamoorthy

Briggs

et al. 2020

ACM Trans. Archit. Code Optim.

View full text Add to dashboard Cite

show abstract

“…This technique assumes immediate error detection. Sharma et al [32] proposed an error detection method for stencil-based applications using the predicted values by a regression model. Dubey et al [18] explored local recovery schemes for applications using structured adaptive mesh refinement (AMR).…”

Section: Related Workmentioning

confidence: 99%

Resilience for Stencil Computations with Latent Errors

Fang

Cavelan

Robert

et al. 2017

2017 46th International Conference on Parallel Processing (ICPP)

View full text Add to dashboard Cite

Projections and measurements of error rates in near-exascale and exascale systems suggest a dramatic growth, due to extreme scale (10 9 cores), concurrency, software complexity, and deep submicron transistor scaling. Such a growth makes resilience a critical concern, and may increase the incidence of errors that "escape", silently corrupting application state. Such errors can often be revealed by application software tests but with long latencies, and thus are known as latent errors. We explore how to efficiently recover from latent errors, with an approach called application-based focused recovery (ABFR). Specifically we present a case study of stencil computations, a widely useful computational structure, showing how ABFR focuses recovery effort where needed, using intelligent testing and pruning to reduce recovery effort, and enables recovery effort to be overlapped with application computation. We analyze and characterize the ABFR approach on stencils, creating a performance model parameterized by error rate and detection interval (latency). We compare projections from the model to experimental results with the Chombo stencil application, validating the model and showing that ABFR on stencil can achieve a significant reductions in error recovery cost (up to 400x) and recovery latency (up to 4x). Such reductions enable efficient execution at scale with high latent error rates.

show abstract

“…They convert the problem of detecting SDC into next-step prediction problem. Sharma et al [26] utilize temporal features of data (in addition to spatial features) and provide a tailored SDC detector for stencil applications where they use support vector machines as a linear function approximator. The main drawbacks of temporal data analytics are the memory overhead and the computation cost of maintaining snapshot data.…”

Section: Related Workmentioning

confidence: 99%

Spatial Support Vector Regression to Detect Silent Errors in the Exascale Era

Subaşi

Bautista-Gomez

et al. 2016

2016 16th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid)

View full text Add to dashboard Cite

Abstract-As the exascale era approaches, the increasing capacity of high-performance computing (HPC) systems with targeted power and energy budget goals introduces significant challenges in reliability. Silent data corruptions (SDCs) or silent errors are one of the major sources that corrupt the execution results of HPC applications without being detected.In this work, we explore a low-memory-overhead SDC detector, by leveraging epsilon-insensitive support vector machine regression, to detect SDCs that occur in HPC applications that can be characterized by an impact error bound. The key contributions are three fold. (1) Our design takes spatial features (i.e., neighbouring data values for each data point in a snapshot) into training data, such that little memory overhead (less than 1%) is introduced. (2) We provide an in-depth study on the detection ability and performance with different parameters, and we optimize the detection range carefully. (3) Experiments with eight real-world HPC applications show that our detector can achieve the detection sensitivity (i.e., recall) up to 99% yet suffer a less than 1% of false positive rate for most cases. Our detector incurs low performance overhead, 5% on average, for all benchmarks studied in the paper. Compared with other state-of-the-art techniques, our detector exhibits the best tradeoff considering the detection ability and overheads.

show abstract

Detecting Soft Errors in Stencil based Computations

Cited by 9 publications

References 37 publications

FPD etect

FPD etect

Resilience for Stencil Computations with Latent Errors

Spatial Support Vector Regression to Detect Silent Errors in the Exascale Era

Contact Info

Product

Resources

About