A high-level synthesis approach optimizing accumulations in floating-point programs using custom formats and operators - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

A high-level synthesis approach optimizing accumulations in floating-point programs using custom formats and operators

Résumé

High-level synthesis (HLS) is a big step forward in terms of design productivity. However, it restricts data-types and operators to those available in the C language supported by the compiler. The present work lifts this restriction: it is a case study of enhancing an HLS design flow with non-standard operators, which can then be automatically optimized for their application context. The focus here is on widely used summation-reduction patterns. A source-to-source compiler rewrites, inside critical loop nests of the input C code, selected floating-point additions into sequences of simpler operator using non-standard arithmetic formats. This enables hoisting floating-point management out the loop. What remains inside the loop is a sequence of fixed-point additions whose size is computed to enforce a user-specified, application-specific accuracy constraint on the result. Evaluation of this method demonstrates significant improvements in the speed/resource usage/accuracy trade-off.
Fichier principal
Vignette du fichier
2017-HLS-Accumulations.pdf (203.48 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01498357 , version 2 (24-02-2017)
hal-01498357 , version 1 (01-04-2017)

Identifiants

Citer

Yohann Uguen, Florent de Dinechin, Steven Derrien. A high-level synthesis approach optimizing accumulations in floating-point programs using custom formats and operators. 2017 IEEE 25th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM), Apr 2017, Napa, United States. pp.80-80, ⟨10.1109/FCCM.2017.41⟩. ⟨hal-01498357v2⟩
1105 Consultations
1104 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More