Implementing LNS using filtering units of GPUs

Mark G. Arnold (1) , David Defour (2) , Caroline Collange (2) , David Defour Eliaus

1 CSE - Computer Science & Engineering Department
2 ELIAUS - Electronique, Informatique, Automatique et Systèmes

Current GPUs offer specialized graphics hardware in addition to generic floating-point processing units. We propose a method which reuses specialized texture filtering units to perform piecewise polynomial evaluations, which helps accelerate LNS computations and can be used in combination with hardware-based transcendental functions.

Mots clés: Graphics processing units; logarithmic number system; texture filtering; polynomial approximation

Domaines: Arithmétique des ordinateurs; Calcul parallèle, distribué et partagé [cs.DC]

Mark G. Arnold, David Defour, Caroline Collange, David Defour Eliaus. Implementing LNS using filtering units of GPUs. International Conference on Acoustics Speech and Signal Processing (ICASSP), Mar 2010, Dallas, TX, United States. pp.1542--1545, ⟨10.1109/ICASSP.2010.5495516⟩. ⟨hal-00423434⟩