Predictive Modeling in a Polyhedral Optimization Space

Eunjung Park 1 John Cavazos 1 Louis-Noël Pouchet 2 Cédric Bastoul 3, 4 Albert Cohen 5 P. Sadayappan 6
3 CAMUS - Compilation pour les Architectures MUlti-coeurS
LSIIT - Laboratoire des Sciences de l'Image, de l'Informatique et de la Télédétection, Inria Nancy - Grand Est
5 Parkas - Parallélisme de Kahn Synchrone
DI-ENS - Département d'informatique de l'École normale supérieure, ENS Paris - École normale supérieure - Paris, Inria Paris-Rocquencourt, CNRS - Centre National de la Recherche Scientifique : UMR 8548
Abstract : High-level program optimizations, such as loop transformations, are critical for high performance on multi-core targets. However, complex sequences of loop transformations are often required to expose parallelism (both coarse-grain and fine-grain) and improve data locality. The polyhedral compilation framework has proved to be very effective at representing these complex sequences and restructuring compute-intensive applications, seamlessly handling perfectly and imperfectly nested loops. Nevertheless identifying the most effective loop transformations remains a major challenge. We address the problem of selecting the best polyhedral optimizations with dedicated machine learning models, trained specifically on the target machine. We show that these models can quickly select high-performance optimizations with very limited iterative search. Our end-to-end framework is validated using numerous benchmarks on two modern multi-core platforms. We investigate a variety of different machine learning algorithms and hardware counters, and we obtain performance improvements over productions compilers ranging on average from 3.2x to 8.7x, by running not more than 6 program variants from a polyhedral optimization space.
Type de document :
Article dans une revue
International Journal of Parallel Programming, Springer Verlag, 2013, 41 (5), pp.704--750. <10.1007/s10766-013-0241-1>
Liste complète des métadonnées


https://hal.inria.fr/hal-00918653
Contributeur : Cédric Bastoul <>
Soumis le : vendredi 13 décembre 2013 - 22:06:36
Dernière modification le : vendredi 3 février 2017 - 01:01:30
Document(s) archivé(s) le : mardi 18 mars 2014 - 13:10:11

Fichier

ijpp-article.13_3.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Eunjung Park, John Cavazos, Louis-Noël Pouchet, Cédric Bastoul, Albert Cohen, et al.. Predictive Modeling in a Polyhedral Optimization Space. International Journal of Parallel Programming, Springer Verlag, 2013, 41 (5), pp.704--750. <10.1007/s10766-013-0241-1>. <hal-00918653>

Partager

Métriques

Consultations de
la notice

394

Téléchargements du document

282