Reproducibility of simulations and High Performance Computing - Université Clermont Auvergne Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Reproducibility of simulations and High Performance Computing

Résumé

One of the major criteria for the scientificity of a research study is reproducibility. In this paper, we will present the main definitions around reproducibility. We will examine to what extent computer science and simulation works are concerned. Anyone wishing to produce quality scientific work will pay attention to the numerical reproducibility of his simulation results. Significant differences can be observed in the results if the practitioner does not apply best practices. In addition to reproducibility, we first need repeatability to debug our simulation software. We will see that even for parallel stochastic simulations, it is possible to reproduce the same numerical results by implementing a rigorous method tested with a billion threads. It is possible to check parallel results with their sequential counterpart before scaling, thus gaining confidence in the proposed simulation results.
Fichier principal
Vignette du fichier
Hill ESM Keynote 2022 v6.pdf (278.43 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04045230 , version 1 (24-03-2023)
hal-04045230 , version 2 (27-03-2023)

Identifiants

  • HAL Id : hal-04045230 , version 1

Citer

David R.C. Hill. Reproducibility of simulations and High Performance Computing. ESM 2022, European Simulation and Modelling Conference, Oct 2023, Porto, Portugal. pp.5-9. ⟨hal-04045230v1⟩
72 Consultations
189 Téléchargements

Partager

Gmail Facebook X LinkedIn More