Automatic Skleton-Driven Memory Affinity for Transactional Worklist Applications

Luís Fabrício Góes 1 Christiane Pousa Ribeiro 2 Marcio Bastos Castro 3 Jean-François Mehaut 4 Murray Cole 5 Marcelo Cintra 5
1 Pontifical Catholic University of Minas Gerais [Belo Horizonte]
2 UZH - University of Zürich [Zürich]
3 Laboratoire d'Informatique de Grenoble
LIG - Laboratoire d'Informatique de Grenoble
4 CORSE - Compiler Optimization and Run-time Systems
Inria Grenoble - Rhône-Alpes, LIG - Laboratoire d'Informatique de Grenoble
5 ICSA - Institute for Computing Systems Architecture School of Informatics - University of Edinburgh
Résumé : Memory affinity has become a key element to achieve scalable performance on multi-core platforms. Mechanisms such as thread scheduling, page allocation and cache prefetching are commonly employed to enhance memory affinity which keeps data close to the cores that access it. In particular, software transactional memory (STM) applications exhibit irregular memory access behavior that makes harder to determine which and when data will be needed by each core. Additionally, existing STM runtime systems are decoupled from issues such as thread and memory management. In this paper, we thus propose a skeleton-driven mechanism to improve memory affinity on STM applications that fit the worklist pattern employing a two-level approach. First, it addresses memory affinity in the DRAM level by automatic selecting page allocation policies. Then it employs data prefetching helper threads to improve affinity in the cache level. It relies on a skeleton framework to exploit the application pattern in order to provide automatic memory page allocation and cache prefetching. Our experimental results on the STAMP benchmark suite show that our proposed mechanism can achieve performance improvements of up to 46 %, with an average of 11 %, over a baseline version on two NUMA multi-core machines.
Keywords : Memory affinity Software transactional memory Parallel algorithmic skeleton Multi-core platforms
Type de document :
Article dans une revue
International Journal of Parallel Programming (IJPP), Springer, 2014, 42 (2), pp.365-382. 〈10.1007/s10766-013-0253-x〉
Liste complète des métadonnées
https://hal.inria.fr/hal-00953110
Contributeur : Gwenaël Delaval <>
Soumis le : vendredi 28 février 2014 - 10:41:19
Dernière modification le : lundi 30 avril 2018 - 15:02:01

Lien texte intégral

openaccess

Identifiants

Collections

LIG_SRCPR | LIG | UGA | INRIA | PERSYVAL-LAB | LIG-SRCPR-CORSE

Citation

Luís Fabrício Góes, Christiane Pousa Ribeiro, Marcio Bastos Castro, Jean-François Mehaut, Murray Cole, et al.. Automatic Skleton-Driven Memory Affinity for Transactional Worklist Applications. International Journal of Parallel Programming (IJPP), Springer, 2014, 42 (2), pp.365-382. 〈10.1007/s10766-013-0253-x〉. 〈hal-00953110〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

352

Contact


archive-ouverte@inria.fr