Efficient GPU Implementation of Particle Interactions with Cutoff Radius and Few Particles per Cell - Ecole Nationale du Génie de l'Eau et de l'Environnement de Strasbourg
Communication Dans Un Congrès Année : 2024

Efficient GPU Implementation of Particle Interactions with Cutoff Radius and Few Particles per Cell

Résumé

This paper presents novel approaches to parallelizing particle interactions on a GPU when there are few particles per cell and the interactions are limited by a cutoff distance. The paper surveys classical algorithms and then introduces two alternatives that aim to utilize shared memory. The first approach copies the particles of a sub-box, while the second approach loads particles in a pencil along the X-axis. The different implementations are compared on three GPU models using Cuda and Hip. The results show that the X-pencil approach can provide a significant speedup but only in very specific cases.
Fichier principal
Vignette du fichier
Efficient_GPU_Implementation_of_Particle_Interactions_with_Cutoff_Radius_and_Few_Particles_per_Cell_-1.pdf (529.25 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04621128 , version 1 (23-06-2024)

Licence

Identifiants

  • HAL Id : hal-04621128 , version 1

Citer

David Algis, Bérenger Bramas, Emmanuelle Darles, Lilian Aveneau. Efficient GPU Implementation of Particle Interactions with Cutoff Radius and Few Particles per Cell. International Symposium on Parallel Computing and Distributed Systems (PCDS2024), IEEE, Sep 2024, Singapore, Singapore. ⟨hal-04621128⟩
104 Consultations
25 Téléchargements

Partager

More