Parallel and distributed task-based Kirchhoff seismic pre-stack depth migration application - INRIA - Institut National de Recherche en Informatique et en Automatique Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Parallel and distributed task-based Kirchhoff seismic pre-stack depth migration application

Résumé

Since the middle of the 1990s, message passing libraries are the most used technology to implement parallel and distributed scientific applications. However, they may not be a solution efficient enough on exascale machines since scalability issues will appear due to the increase in computing resources. Task-based programming models can be used to avoid collective communications like reductions, broadcast, or gather by transforming them into multiple operations on tasks. Then, these operations can be scheduled by the programming scheduler to place the data and computations in a way that optimizes and reduces the data communications. These properties could help to solve some MPI and exascale computing challenges. The oil and gas applications could also benefit from taskbased programming properties. We developed a simplified version of the Kirchhoff seismic pre-stack depth migration, a subsurface exploration application, to experiment with HPX, a task-based programming model as well and MPI and MPI+OpenMP. Then, we perform strong scaling and weak scaling experiments on Pangea, Total supercomputer. We also study the variation of the number of OpenMP threads per MPI process. We show that the current task-based programming model schedulers lack the capability to completely manage the memory used and are not efficient enough to reduce the data migrations.
Fichier principal
Vignette du fichier
paper.pdf (1.35 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03450299 , version 1 (26-11-2021)

Identifiants

Citer

Jerome Gurhem, Henri Calandra, Serge G Petiton. Parallel and distributed task-based Kirchhoff seismic pre-stack depth migration application. ISPDC 2021 - 20th International Symposium on Parallel and Distributed Computing, Jul 2021, Cluj-Napoca, Romania. pp.65-72, ⟨10.1109/ISPDC52870.2021.9521599⟩. ⟨hal-03450299⟩
101 Consultations
100 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More