Spatial computing as intensional data parallelism

Antoine Spicher (1) , Olivier Michel (1) , Jean-Louis Giavitto (2)

1 LACL - Laboratoire d'Algorithmique Complexité et Logique
2 IBISC - Informatique, Biologie Intégrative et Systèmes Complexes

In this paper, we show that various concepts and tools developed in the 90's in the field of data-parallelism provide a relevant spatial programming framework. It allows high level spatial computation specifications to be translated into efficient low-level operations on processing units. We provide some short examples to illustrate this statement.

Mots clés: Collection; Data flow; Data parallelism; Data-fields; Declarative definition; Intensionnal programming; Spatial computing; Stream

Domaines: Langage de programmation [cs.PL]

Antoine Spicher, Olivier Michel, Jean-Louis Giavitto. Spatial computing as intensional data parallelism. 4th IEEE International Conference on Self-Adaptive and Self-Organizing Systems Workshop (SASOW 2010), Sep 2010, Budapest, Hungary. pp.196--205, ⟨10.1109/SASOW.2010.73⟩. ⟨hal-00869214⟩