Automatic Algorithm-Based Fault Tolerance (AABFT) of Stencil Computations - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Automatic Algorithm-Based Fault Tolerance (AABFT) of Stencil Computations

Résumé

In this work, we study fault tolerance of transient errors, such as those occurring due to cosmic radiation or hardware component aging and degradation, using Algorithm-Based Fault Tolerance (ABFT). ABFT methods typically work by adding some additional computation in the form of invariant checksums which, by definition, should not change as the program executes. By computing and monitoring checksums, it is possible to detect errors by observing differences in the checksum values. However, this is challenging for two key reasons: (1) it requires careful manual analysis of the input program, and (2) care must be taken to subsequently carry out the checksum computations efficiently enough for it to be worth it. Prior work has shown how to apply ABFT schemes with low overhead for a variety of input programs. Here, we focus on a subclass of programs called stencil applications, an important class of computations found widely in various scientific computing domains. We propose a new compilation scheme to automatically analyze and generate the checksum computations. To the best of our knowledge, this is the first work to do such a thing in a compiler. We show that low overhead code can be easily generated and provide a preliminary evaluation of the tradeoff between performance and effectiveness.
Fichier principal
Vignette du fichier
pact_2023_aabft.pdf (1.11 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04394874 , version 1 (15-01-2024)
hal-04394874 , version 2 (16-01-2024)

Licence

Paternité

Identifiants

  • HAL Id : hal-04394874 , version 2

Citer

Louis Narmour, Steven Derrien, Sanjay Rajopadhye. Automatic Algorithm-Based Fault Tolerance (AABFT) of Stencil Computations. PACT 2023 - International Conference on Parallel Architectures and Compilation Techniques, Oct 2023, Vienna, Austria. pp.1-12. ⟨hal-04394874v2⟩
34 Consultations
10 Téléchargements

Partager

Gmail Facebook X LinkedIn More