Parallel computation of echelon forms

Jean-Guillaume Dumas 1 Thierry Gautier 2 Clément Pernet 2, 3 Ziad Sultan 2, 1
2 MOAIS - PrograMming and scheduling design fOr Applications in Interactive Simulation
Inria Grenoble - Rhône-Alpes, LIG - Laboratoire d'Informatique de Grenoble
3 ARIC - Arithmetic and Computing
Inria Grenoble - Rhône-Alpes, LIP - Laboratoire de l'Informatique du Parallélisme
Abstract : We propose efficient parallel algorithms and implementations on shared memory architectures of LU factorization over a finite field. Compared to the corresponding numerical routines, we have identified three main difficulties specific to linear algebra over finite fields. First, the arithmetic complexity could be dominated by modular reductions. Therefore, it is mandatory to delay as much as possible these reductions while mixing fine-grain parallelizations of tiled iterative and recursive algorithms. Second, fast linear algebra variants, e.g., using Strassen-Winograd algorithm, never suffer from instability and can thus be widely used in cascade with the classical algorithms. There, trade-offs are to be made between size of blocks well suited to those fast variants or to load and communication balancing. Third, many applications over finite fields require the rank profile of the matrix (quite often rank deficient) rather than the solution to a linear system. It is thus important to design parallel algorithms that preserve and compute this rank profile. Moreover, as the rank profile is only discovered during the algorithm, block size has then to be dynamic. We propose and compare several block decomposition: tile iterative with left-looking, right-looking and Crout variants, slab and tile recursive. Experiments demonstrate that the tile recursive variant performs better and matches the performance of reference numerical software when no rank deficiency occur. Furthermore, even in the most heterogeneous case, namely when all pivot blocks are rank deficient, we show that it is possbile to maintain a high efficiency.
Type de document :
Communication dans un congrès
EuroPar-2014 - 20th International Conference on Parallel Processing, Aug 2014, Porto, Portugal. Springer, 8632, pp.499-510, 2014, Lecture Notes in Computer Science. 〈10.1007/978-3-319-09873-9_42〉
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-00947013
Contributeur : Jean-Guillaume Dumas <>
Soumis le : vendredi 14 février 2014 - 15:07:50
Dernière modification le : vendredi 20 avril 2018 - 15:44:26
Document(s) archivé(s) le : jeudi 15 mai 2014 - 10:41:49

Fichiers

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

Identifiants

Citation

Jean-Guillaume Dumas, Thierry Gautier, Clément Pernet, Ziad Sultan. Parallel computation of echelon forms. EuroPar-2014 - 20th International Conference on Parallel Processing, Aug 2014, Porto, Portugal. Springer, 8632, pp.499-510, 2014, Lecture Notes in Computer Science. 〈10.1007/978-3-319-09873-9_42〉. 〈hal-00947013〉

Partager

Métriques

Consultations de la notice

1035

Téléchargements de fichiers

363