Reproducible and Accurate Matrix Multiplication for High-Performance Computing - Université Pierre et Marie Curie Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

Reproducible and Accurate Matrix Multiplication for High-Performance Computing

Résumé

On modern multi-core, many-core, and heterogeneous architectures, floating-point computations may become non-deterministic and thus non-reproducible mainly due to non-associativity of floating-point operations. We introduce an algorithm to compute a product of two floating-point matrices that delivers reproducible results with the best possible accuracy. Our multi-level algorithm relies on fast vectorized floating-point expansions and as well as superaccumulators in a high-radix carry-save representation. We present implementations on recent Intel Xeon Phi accelerators and both AMD and NVIDIA GPUs.
Fichier principal
Vignette du fichier
scan14-1.pdf (192.74 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01215627 , version 1 (23-11-2016)

Identifiants

  • HAL Id : hal-01215627 , version 1

Citer

Caroline Collange, David Defour, Stef Graillat, Roman Iakymchuk. Reproducible and Accurate Matrix Multiplication for High-Performance Computing. SCAN: Scientific Computing, Computer Arithmetic and Validated Numerics, Sep 2014, Wuerzburg, Germany. pp.42-43. ⟨hal-01215627⟩
365 Consultations
87 Téléchargements

Partager

Gmail Facebook X LinkedIn More