Load-Store Optimization For Software Pipelining

Min Dai 1 Christine Eisenbeis 1 Sid Touati 1
1 A3 - Advanced analysis to code optimization
UP11 - Université Paris-Sud - Paris 11, Inria Saclay - Ile de France
Abstract : Software pipelining can generate efficient schedules for loop by overlapping the execution of operations from different iterations in order to exploit maximum Instruction Level Parallelism (ILP). Code optimization can decrease total number of calculations and memory related operations. As a result, instruction schedules can use freed resources to construct shorter schedules. Particularly, when the data is not presented in cache, the performance will be significantly degraded by memory references. Therefore, elimination of redundant load-store operations is most important for improving overall performance. This paper introduces a method for integrating software pipelining and load-store elimination techniques. Moreover, we demonstrate that integrated algorithm is more effective than other methods.
Type de document :
Article dans une revue
ACM SIGARCH Computer Architecture News, ACM, 2000, 28 (1), pp.3 - 10. 〈10.1145/346023.346027〉
Liste complète des métadonnées

Contributeur : Sid Touati <>
Soumis le : jeudi 1 décembre 2011 - 14:35:06
Dernière modification le : jeudi 9 février 2017 - 15:53:46
Document(s) archivé(s) le : vendredi 2 mars 2012 - 02:32:02


Fichiers produits par l'(les) auteur(s)




Min Dai, Christine Eisenbeis, Sid Touati. Load-Store Optimization For Software Pipelining. ACM SIGARCH Computer Architecture News, ACM, 2000, 28 (1), pp.3 - 10. 〈10.1145/346023.346027〉. 〈hal-00647085〉



Consultations de la notice


Téléchargements de fichiers