When FPGAs are better at floating-point than microprocessors

Abstract : It has been shown that FPGAs could outperform high-end microprocessors on floating-point computations thanks to massive parallelism. However, most previous studies re-implement in the FPGA the operators present in a processor. This is a safe and relatively straightforward approach, but it doesn't exploit the greater flexibility of the FPGA. This article is a survey of the many ways in which the FPGA implementation of a given floating-point computation can be not only faster, but also more accurate than its microprocessor counterpart. Techniques studied here include custom precision, specific accumulator design, dedicated architectures for coarser operators which have to be implemented in software in processors, and others. A real-world biomedical application illustrates these claims. This study also points to how current FPGA fabrics could be enhanced for better floating-point support.
Type de document :
Pré-publication, Document de travail
2007
Liste complète des métadonnées

Littérature citée [40 références]  Voir  Masquer  Télécharger

https://hal-ens-lyon.archives-ouvertes.fr/ensl-00174627
Contributeur : Florent De Dinechin <>
Soumis le : lundi 24 septembre 2007 - 16:39:22
Dernière modification le : mardi 24 avril 2018 - 13:52:42
Document(s) archivé(s) le : lundi 24 septembre 2012 - 12:45:52

Fichier

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

Identifiants

  • HAL Id : ensl-00174627, version 1

Collections

Citation

Florent De Dinechin, Jérémie Detrey, Octavian Creţ, Radu Tudoran. When FPGAs are better at floating-point than microprocessors. 2007. 〈ensl-00174627〉

Partager

Métriques

Consultations de la notice

1019

Téléchargements de fichiers

4001