3D Tomography parallelization on FPGAs via HLS tools - SATIE-MOSS Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

3D Tomography parallelization on FPGAs via HLS tools

Résumé

This paper deals with the evaluation of FPGAs resurgence for hardware acceleration applied to computed to-mography on the back-projection operator used in iterative reconstruction algorithms. We focus our attention on the tools developed by FPGAs manufacturers, in particular the Intel FPGA SDK for OpenCL, that promises a new level of hardware abstraction from the developer's perspective, allowing a software-like programming of FPGAs. For this purpose, we start with evaluating different custom OpenCL implementations of the back-projection algorithm. With some clues on memory fetching and coalescing, we then further tune designs to improve performance. Finally, a comparison is made with GPU implementations, and a preliminary conclusion is drawn on FPGAs future in computed tomography.
Fichier principal
Vignette du fichier
DASIP_article.pdf (300.52 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01569320 , version 1 (18-02-2018)

Identifiants

Citer

Maxime Martelli, Nicolas Gac, Alain Mérigot, Cyrille Enderli. 3D Tomography parallelization on FPGAs via HLS tools. DASIP, Sep 2017, dresden, Germany. pp.1-6, ⟨10.1109/DASIP.2017.8122119⟩. ⟨hal-01569320⟩
241 Consultations
183 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More