Quick and practical run-time evaluation of multiple program optimizations

Grigori Fursin 1 Albert Cohen 1 Michael O'Boyle 2 Olivier Temam 1
1 ALCHEMY - Architectures, Languages and Compilers to Harness the End of Moore Years
LRI - Laboratoire de Recherche en Informatique, UP11 - Université Paris-Sud - Paris 11, CNRS - Centre National de la Recherche Scientifique : UMR8623, Inria Saclay - Ile de France
Abstract : This article aims at making iterative optimization practical and usable by speeding up the evaluation of a large range of optimizations. Instead of using a full run to evaluate a single program optimization, we take advantage of periods of stable performance, called phases. For that purpose, we propose a low-overhead phase detection scheme geared toward fast optimization space pruning, using code instrumentation and versioning implemented in a production compiler. Our approach is driven by simplicity and practicality. We show that a simple phase detection scheme can be sufficient for optimization space pruning. We also show it is possible to search for complex optimizations at run-time without resorting to sophisticated dynamic compilation frameworks. Beyond iterative optimization, our approach also enables one to quickly design selftuned applications. Considering 5 representative SpecFP2000 benchmarks, our approach speeds up iterative search for the best program optimizations by a factor of 32 to 962. Phase prediction is 99.4% accurate on average, with an overhead of only 2.6%. The resulting self-tuned implementations bring an average speed-up of 1.4.
Type de document :
Article dans une revue
Transactions on High-Performance Embedded Architectures and Compilers, Springer Verlag, 2006, 1 (1)
Liste complète des métadonnées

https://hal.inria.fr/inria-00084110
Contributeur : Grigori Fursin <>
Soumis le : mercredi 5 juillet 2006 - 16:38:58
Dernière modification le : jeudi 5 avril 2018 - 12:30:12
Document(s) archivé(s) le : lundi 5 avril 2010 - 23:50:35

Fichier

Identifiants

  • HAL Id : inria-00084110, version 1

Collections

Citation

Grigori Fursin, Albert Cohen, Michael O'Boyle, Olivier Temam. Quick and practical run-time evaluation of multiple program optimizations. Transactions on High-Performance Embedded Architectures and Compilers, Springer Verlag, 2006, 1 (1). 〈inria-00084110〉

Partager

Métriques

Consultations de la notice

361

Téléchargements de fichiers

164