AUPY, Guillaume; BEAUMONT, Olivier; EYRAUD-DUBOIS, Lionel

doi:10.1109/IPDPS.2018.00075

Métadonnées

Afficher la notice complète

Licence d’utilisation du document

AUPY, Guillaume
Topology-Aware System-Scale Data Management for High-Performance Computing [TADAAM]

BEAUMONT, Olivier
Reformulations based algorithms for Combinatorial Optimization [Realopt]

EYRAUD-DUBOIS, Lionel
Reformulations based algorithms for Combinatorial Optimization [Realopt]

Langue

Communication dans un congrès

Ce document a été publié dans

International Parallel and Distributed Processing Symposium (IPDPS), 2018-05-20, Vancouver. 2018-05-21

IEEE

Résumé en anglais

Burst-Buffers are high throughput, small size intermediate storage systems typically based on SSDs or NVRAM that are designed to be used as a potential buffer between the computing nodes of a supercomputer and its main storage system consisting of hard drives. Their purpose is to absorb the bursts of I/O that many HPC applications experience (for example for saving checkpoints or data from intermediate results). In this paper, we propose a probabilistic model for evaluating the performance of Burst-Buffers. From a model of application and a data management strategy, we build a Markov chain based model of the system, that allows to quickly answer issues about dimensioning of the system: for a given set of applications, and for a given Burst-Buffer size and bandwidth, how often does the buffer overflow? We also provide extensive simulation results to validate our modeling approach.< Réduire

Mots clés en anglais

Models

Burst Buffers

I/O

Scheduling

URI

https://oskar-bordeaux.fr/handle/20.500.12278/193251

DOI

http://dx.doi.org/10.1109/IPDPS.2018.00075

Project ANR

Ordonnancement de données pour le calcul haute-performance - ANR-17-CE25-0004

Origine

Importé de hal

Unités de recherche

Institut de Mathématiques de Bordeaux (IMB) - UMR 5251