A Simple Compressive Sensing Algorithm for Parallel Many-Core Architectures

Alexandre Borghi (1) , Jérome Darbon (2) , Sylvain Peyronnet (3) , Tony F. Chan , Stanley Osher (4)

1 LRI - Laboratoire de Recherche en Informatique
2 LRDE - Laboratoire de Recherche et de Développement de l'EPITA
3 Equipe AMACC - Laboratoire GREYC - UMR6072
4 Departament of Mathematics

In this paper we consider the l 1-compressive sensing problem. We propose an algorithm specifically designed to take advantage of shared memory, vectorized, parallel and many-core microprocessors such as the Cell processor, new generation Graphics Processing Units (GPUs) and standard vectorized multi-core processors (e.g. quad-core CPUs). Besides its implementation is easy. We also give evidence of the efficiency of our approach and compare the algorithm on the three platforms, thus exhibiting pros and cons for each of them.

Mots clés: Image Processing and Computer Vision; Electrical Engineering; Circuits and Systems; Signal; Image and Speech Processing; Pattern Recognition; Computer Imaging; Vision; Pattern Recognition and Graphics

Domaines: Informatique [cs]; Algorithme et structure de données [cs.DS]

Alexandre Borghi, Jérome Darbon, Sylvain Peyronnet, Tony F. Chan, Stanley Osher. A Simple Compressive Sensing Algorithm for Parallel Many-Core Architectures. Journal of Signal Processing Systems, 2013, pp.1-20. ⟨10.1007/s11265-012-0671-9⟩. ⟨hal-01086454⟩