A Distributed and Parallel Asynchronous Unite and Conquer Method to Solve Large Scale Non-Hermitian Linear Systems

Abstract : Parallel Krylov Subspace Methods are commonly used for solving large-scale sparse linear systems. Facing the development of extreme scale platforms, the minimization of synchronous global communication becomes critical to obtain good efficiency and scal-ability. This paper highlights a recent development of a hybrid (unite and conquer) method, which combines three computation algorithms together with asynchronous communication to accelerate the resolution of non-Hermitian linear systems and to improve its fault tolerance and reusability. Experimentation shows that our method has an up to 5× speedup and better scalability than the conventional methods for the resolution on hierarchical clusters with hundreds of nodes.
Type de document :
Communication dans un congrès
HPC Asia 2018 - International Conference on High Performance Computing in Asia-Pacific Region, Jan 2018, Tokyo, Japan. 2018, 〈10.1145/3149457.3154481〉
Liste complète des métadonnées

Littérature citée [22 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01677110
Contributeur : Xinzhe Wu <>
Soumis le : lundi 8 janvier 2018 - 09:29:08
Dernière modification le : jeudi 11 janvier 2018 - 06:27:34

Fichier

HPCAsia2018_pap114_camera_read...
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Xinzhe Wu, Serge Petiton. A Distributed and Parallel Asynchronous Unite and Conquer Method to Solve Large Scale Non-Hermitian Linear Systems. HPC Asia 2018 - International Conference on High Performance Computing in Asia-Pacific Region, Jan 2018, Tokyo, Japan. 2018, 〈10.1145/3149457.3154481〉. 〈hal-01677110〉

Partager

Métriques

Consultations de la notice

47

Téléchargements de fichiers

12