NumaMMA: NUMA MeMory Analyzer

François Trahay 1 Manuel Selva 2 Lionel Morel 3 Kevin Marquet 4
2 CAMUS - Compilation pour les Architectures MUlti-coeurS
Inria Nancy - Grand Est, ICube - Laboratoire des sciences de l'ingénieur, de l'informatique et de l'imagerie
4 SOCRATE - Software and Cognitive radio for telecommunications
Inria Grenoble - Rhône-Alpes, CITI - CITI Centre of Innovation in Telecommunications and Integration of services
Abstract : Non Uniform Memory Access (NUMA) architectures are nowadays common for running High-Performance Computing (HPC) applications. In such architectures, several distinct physical memories are assembled to create a single shared memory. Nevertheless, because there are several physical memories, access times to these memories are not uniform depending on the location of the core performing the memory request and on the location of the target memory. Hence, threads and data placement are crucial to efficiently exploit such architectures. To help in taking decision about this placement, profiling tools are needed. In this work, we propose NUMA MeMory Ana-lyzer (NumaMMA), a new profiling tool for understanding the memory access patterns of HPC applications. NumaMMA combines efficient collection of memory traces using hardware mechanisms with original visualization means allowing to see how memory access patterns evolve over time. The information reported by NumaMMA allows to understand the nature of these access patterns inside each object allocated by the application. We show how NumaMMA can help understanding the memory patterns of several HPC applications in order to optimize them and get speedups up to 28% over the standard non optimized version.
Type de document :
Communication dans un congrès
ICPP 2018 - 47th International Conference on Parallel Processing, Aug 2018, Eugene, United States. 2018, 〈10.1145/3225058.3225094〉
Liste complète des métadonnées

Littérature citée [16 références]  Voir  Masquer  Télécharger

https://hal-cea.archives-ouvertes.fr/cea-01854072
Contributeur : Lionel Morel <>
Soumis le : lundi 6 août 2018 - 14:32:39
Dernière modification le : vendredi 10 août 2018 - 09:17:00

Fichier

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

Identifiants

Citation

François Trahay, Manuel Selva, Lionel Morel, Kevin Marquet. NumaMMA: NUMA MeMory Analyzer. ICPP 2018 - 47th International Conference on Parallel Processing, Aug 2018, Eugene, United States. 2018, 〈10.1145/3225058.3225094〉. 〈cea-01854072〉

Partager

Métriques

Consultations de la notice

27

Téléchargements de fichiers

21