Coping with silent errors in HPC applications

Abstract : This chapter describes a unified framework for the detection and correction of silent errors, which constitute a major threat for scientific applications at extreme-scale. We first motivate the problem and explain why checkpointing must be combined with some verification mechanism. Then we introduce a general-purpose technique based upon computational patterns that periodically repeat over time. These patterns interleave verifications and checkpoints, and we show how to determine the pattern minimizing expected execution time. Then we move to application-specific techniques and review dynamic programming algorithms for linear chains of tasks, as well as ABFT-oriented algorithms for iterative methods in sparse linear algebra.
Type de document :
Chapitre d'ouvrage
Andy Adamatzky. Emergent Computation, Springer Verlag, 2016
Liste complète des métadonnées

Littérature citée [41 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01354892
Contributeur : Equipe Roma <>
Soumis le : vendredi 19 août 2016 - 20:39:11
Dernière modification le : mardi 16 janvier 2018 - 14:45:46
Document(s) archivé(s) le : dimanche 20 novembre 2016 - 10:48:57

Fichier

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

Identifiants

  • HAL Id : hal-01354892, version 1

Collections

Citation

Guillaume Aupy, Anne Benoit, Aurélien Cavelan, Massimiliano Fasi, Yves Robert, et al.. Coping with silent errors in HPC applications. Andy Adamatzky. Emergent Computation, Springer Verlag, 2016. 〈hal-01354892〉

Partager

Métriques

Consultations de la notice

164

Téléchargements de fichiers

45