Spatial computing as intensional data parallelism
Résumé
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.
Origine | Fichiers produits par l'(les) auteur(s) |
---|
Loading...