Modeling the conflicting demands of parallelism and Temporal/Spatial locality in affine scheduling

Abstract : The construction of effective loop nest optimizers and par-allelizers remains challenging despite decades of work in the area. Due to the increasing diversity of loop-intensive applications and to the complex memory/computation hierarchies in modern processors, optimization heuristics are pulled towards conflicting goals, highlighting the lack of a systematic approach to optimizing locality and parallelism. Acknowledging these conflicting demands on loop nest optimization , we propose an algorithmic template capable of modeling the multi-level parallelism and the temporal/spatial locality of multiprocessors and accelerators. This algorithmic template orchestrates a collection of parameterizable, linear optimization problems over a polyhedral space of semantics-preserving transformations. While the overall problem is not convex, effective algorithms can be derived from this template delivering unprecedented performance portability over GPU and multicore CPU. We discuss the rationale for this algorithmic template and validate it on representative computational kernels/benchmarks.
Type de document :
Communication dans un congrès
CC'18 - 27th International Conference on Compiler Construction, Feb 2018, Vienna, Austria. ACM Press, 〈10.1145/3178372.3179507〉
Liste complète des métadonnées

Littérature citée [36 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01751823
Contributeur : Oleksandr Zinenko <>
Soumis le : jeudi 29 mars 2018 - 14:41:43
Dernière modification le : lundi 28 mai 2018 - 14:03:00

Fichier

paper.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Oleksandr Zinenko, Sven Verdoolaege, Chandan Reddy, Jun Shirako, Tobias Grosser, et al.. Modeling the conflicting demands of parallelism and Temporal/Spatial locality in affine scheduling. CC'18 - 27th International Conference on Compiler Construction, Feb 2018, Vienna, Austria. ACM Press, 〈10.1145/3178372.3179507〉. 〈hal-01751823〉

Partager

Métriques

Consultations de la notice

241

Téléchargements de fichiers

98