Coping with recall and precision of soft error detectors

Abstract : Many methods are available to detect silent errors in high-performance computing (HPC) applications. Each method comes with a cost, a recall (fraction of all errors that are actually detected, i.e., false negatives), and a precision (fraction of true errors amongst all detected errors, i.e., false positives). The main contribution of this paper is to characterize the optimal computing pattern for an application: which detector(s) to use, how many detectors of each type to use, together with the length of the work segment that precedes each of them. We first prove that detectors with imperfect precisions offer limited usefulness. Then we focus on detectors with perfect precision , and we conduct a comprehensive complexity analysis of this optimization problem, showing NP-completeness and designing an FPTAS (Fully Polynomial-Time Approximation Scheme). On the practical side, we provide a greedy algorithm, whose performance is shown to be close to the optimal for a realistic set of evaluation scenarios. Extensive simulations illustrate the usefulness of detectors with false negatives, which are available at a lower cost than the guaranteed detectors.
Type de document :
Article dans une revue
Journal of Parallel and Distributed Computing, Elsevier, 2016, 98, pp.8-24. 〈10.1016/j.jpdc.2016.07.007〉
Liste complète des métadonnées

Littérature citée [42 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01354888
Contributeur : Equipe Roma <>
Soumis le : vendredi 19 août 2016 - 19:13:10
Dernière modification le : vendredi 20 avril 2018 - 15:44:27
Document(s) archivé(s) le : dimanche 20 novembre 2016 - 10:32:17

Fichier

jpdc.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Leonardo Bautista-Gomez, Anne Benoit, Aurélien Cavelan, Yves Robert, Hongyang Sun. Coping with recall and precision of soft error detectors. Journal of Parallel and Distributed Computing, Elsevier, 2016, 98, pp.8-24. 〈10.1016/j.jpdc.2016.07.007〉. 〈hal-01354888〉

Partager

Métriques

Consultations de la notice

276

Téléchargements de fichiers

57