Hierarchical Approach for Deriving a Reproducible LU factorization on GPUs - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

Hierarchical Approach for Deriving a Reproducible LU factorization on GPUs

Résumé

We propose a reproducible variant of the unblocked LU factorization for graphics processor units (GPUs). For this purpose, we provide Level-1/2 BLAS kernels that deliver correctly-rounded and reproducible results for the dot (inner) product, vector scaling, and the matrix-vector product. In addition, we draw a strategy to enhance the accuracy of the triangular solve via inexpensive iterative refinement. Following a bottom-up approach, we finally construct a reproducible implementation of the LU factorization for GPUs, which can easily accommodate partial pivoting for stability and be eventually integrated into a (blocked) high performance and stable algorithm for the LU factorization.
Fichier principal
Vignette du fichier
reprolu.abstract.pdf (162.28 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01382645 , version 1 (17-10-2016)

Identifiants

  • HAL Id : hal-01382645 , version 1

Citer

Roman S Iakymchuk, Stef S Graillat, David Defour, Enrique S Quintana-Ortí. Hierarchical Approach for Deriving a Reproducible LU factorization on GPUs. The Numerical Reproducibility at Exascale (NRE16) workshop held as part of the Supercomputing Conference (SC16), Nov 2016, Salt Lake City, UT, United States. ⟨hal-01382645⟩
324 Consultations
117 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More