Analysis of Partitioning Models and Metrics in Parallel Sparse Matrix-Vector Multiplication

Abstract : Graph/hypergraph partitioning models and methods have been successfully used to minimize the communication among processors in several parallel computing applications. Parallel sparse matrix-vector multiplication (SpMxV) is one of the representative applications that renders these models and methods indispensable in many scientific com- puting contexts. We investigate the interplay of the partitioning metrics and execution times of SpMxV implementations in three libraries: Trilinos, PETSc, and an in-house one. We carry out experiments with up to 512 processors and investigate the results with regression analysis. Our experiments show that the partitioning metrics influence the perfor- mance greatly in a distributed memory setting. The regression analyses demonstrate which metric is the most influential for the execution time of the libraries.
Type de document :
Communication dans un congrès
Wyrzykowski, Roman and Dongarra, Jack and Karczewski, Konrad and Waśniewski, Jerzy. 10th PPAM - Parallel Processing and Applied Mathematics, Sep 2013, Varsovie, Poland. Springer, pp.174--184, 2014, 〈10.1007/978-3-642-55195-6_16〉
Liste complète des métadonnées

Littérature citée [15 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00923454
Contributeur : Equipe Roma <>
Soumis le : jeudi 2 janvier 2014 - 19:58:34
Dernière modification le : vendredi 20 avril 2018 - 15:44:26
Document(s) archivé(s) le : samedi 8 avril 2017 - 10:34:22

Fichier

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

Identifiants

Collections

Citation

Kamer Kaya, Bora Uçar, Umit Catalyurek. Analysis of Partitioning Models and Metrics in Parallel Sparse Matrix-Vector Multiplication. Wyrzykowski, Roman and Dongarra, Jack and Karczewski, Konrad and Waśniewski, Jerzy. 10th PPAM - Parallel Processing and Applied Mathematics, Sep 2013, Varsovie, Poland. Springer, pp.174--184, 2014, 〈10.1007/978-3-642-55195-6_16〉. 〈hal-00923454〉

Partager

Métriques

Consultations de la notice

652

Téléchargements de fichiers

381