Contribution à l'amélioration des méthodes d'optimisation de la gestion de la mémoire dans le cadre du Calcul Haute Performance

Abstract : Current supercomputer architectures are subject to memory related issues. For instance we can observe slowdowns induced by memory management mecanisms and their implementation. In this context, we focus on the management of large memory segments for multi-core and NUMA supercomputers similar to Tera 100 and Curie. We discuss our work in three parts. We first study several paging policies (page coloring, huge pages...) from multiple operating systems. We demonstrate an interference between those policies and layout decisions taken by userspace allocators. Such interactions can significantly reduce cache efficiency depending on the application, particularly on multi-core architectures. This study extends existing works by studying interactions between the operating system, the allocator and caches. Then, we discuss performance issues when large memory segments are allocated. To do so, we consider the interaction between the OS and userspace allocators. We show that we can significantly improve some application performances (up to 50%) by controling the memory exchange rate with the OS and by taking care of memory topologies. We finally study page fault extensibility in current Linux kernel implementation. We obsere a large impact due to page zeroing which is a security requirement. We propose an improvement on memory allocation semantic aimed at avoiding page zeroing. It shows a new interest for huge pages to improve paging scalability without changing too much kernel algorithms.
Document type :
Theses
Performance et fiabilité [cs.PF]. University de Versaille Saint-Quentin en Yvelines, 2014. Français
Liste complète des métadonnées

Cited literature [115 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/tel-01253537
Contributor : Sébastien Valat <>
Submitted on : Monday, January 11, 2016 - 3:40:48 PM
Last modification on : Thursday, February 9, 2017 - 3:41:22 PM
Document(s) archivé(s) le : Tuesday, April 12, 2016 - 11:03:39 AM

Identifiers

  • HAL Id : tel-01253537, version 1

Collections

Citation

Sébastien Valat. Contribution à l'amélioration des méthodes d'optimisation de la gestion de la mémoire dans le cadre du Calcul Haute Performance. Performance et fiabilité [cs.PF]. University de Versaille Saint-Quentin en Yvelines, 2014. Français. 〈tel-01253537〉

Share

Metrics

Record views

221

Document downloads

349