Multipliers for Floating-Point Double Precision and Beyond on FPGAs

Sebastian Banescu 1 Florent De Dinechin 2, 3 Bogdan Pasca 2, 3 Radu Tudoran 1
1 UTCN - Universitatea Tehnica din Cluj-Napoca
2 ARENAIRE - Computer arithmetic
Inria Grenoble - Rhône-Alpes, LIP - Laboratoire de l'Informatique du Parallélisme
3 LIP - Laboratoire de l'Informatique du Parallélisme
Abstract : The implementation of high-precision floating-point applications on reconfigurable hardware requires a variety of large multipliers: Standard multipliers are the core of floating-point multipliers; Truncated multipliers, trading resources for a well-controlled accuracy degradation, are useful building blocks in situations where a full multiplier is not needed. This work studies the automated generation of such multipliers using the embedded multipliers and adders present in DSP blocks of current FPGAs. The optimization of such multipliers is expressed as a tiling problem where a tile represents a hardware multiplier and super-tiles are the wiring of several hardware multipliers making efficient use of the DSP internal resources. This tiling technique is shown to adapt to full or truncated multipliers. It addresses arbitrary precisions including single, double but also in the quadruple precision introduced by the IEEE-754-2008 standard and currently unsupported by processor hardware. An open-source implementation is provided in the FloPoCo project.
keyword : Multiplier Truncated multiplier Floating-point Quadruple precision
Type de document :
Communication dans un congrès
Highly Efficient Accelerators and Reconfigurable Technologies, Jun 2010, Tsukuba, Japan. EIC, 2010
Liste complète des métadonnées

Littérature citée [14 références]  Voir  Masquer  Télécharger
https://hal-ens-lyon.archives-ouvertes.fr/ensl-00475781
Contributeur : Bogdan Pasca <>
Soumis le : lundi 1 novembre 2010 - 12:33:45
Dernière modification le : vendredi 20 avril 2018 - 15:44:24
Document(s) archivé(s) le : vendredi 2 décembre 2016 - 00:28:52

Fichier

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

Identifiants

  • HAL Id : ensl-00475781, version 2

Collections

INRIA | LIP | ENS-LYON | UNIV-LYON1 | INRIA-RENGRE

Citation

Sebastian Banescu, Florent De Dinechin, Bogdan Pasca, Radu Tudoran. Multipliers for Floating-Point Double Precision and Beyond on FPGAs. Highly Efficient Accelerators and Reconfigurable Technologies, Jun 2010, Tsukuba, Japan. EIC, 2010. 〈ensl-00475781v2〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

344

Téléchargements de fichiers

244

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD