Capturing Periodic I/O Using Frequency Techniques

Autor: Tarraf, Ahmad, Bandet, Alexis, Boito, Francieli, Pallez, Guillaume, Wolf, Felix

Many HPC applications perform their I/O in bursts that follow a periodic pattern. This allows for making predictions as to when a burst occurs. System providers can take advantage of such knowledge to reduce file-system contention by actively schedul

Externí odkaz: http://arxiv.org/abs/2306.08601

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Optimization Metrics for the Evaluation of Batch Schedulers in HPC

Autor: Boëzennec, Robin, Dufossé, Fanny, Pallez, Guillaume

Publikováno v: JSSPP 2023-26th edition of the workshop on Job Scheduling Strategies for Parallel Processing
JSSPP 2023-26th edition of the workshop on Job Scheduling Strategies for Parallel Processing, May 2023, St. Petersburg, Florida, United States. pp.1-19

International audience; Machine Learning techniques are taking a prominent position in the design of system softwares. In HPC, many work are proposing to use such techniques (specifically Reinforcement Learning) to improve the performance of batch sc

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::897d3a9f3fafa9ad01fedcfdac1b0284
https://hal.inria.fr/hal-04042591/document

Recommandations sur les « éditeurs de la zone grise »

Autor: Blanqui, Frédéric, Canteaut, Anne, de Jong, Hidde, Imperiale, Sébastien, Mitton, Nathalie, Pallez, Guillaume, Pennec, Xavier, Rival, Xavier, Thirion, Bertrand

Publikováno v: Inria. 2023, pp.1-3

Recommandations de la Commission d'Évaluation Inria, adoptées le 25 janvier 2023, sur certains éditeurs, notamment MDPI et Frontiers, qui prennent depuis quelques années une place significative dans les domaines de l'informatique et des mathémat

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::5f3542470d078c22465718d391105e4e
https://inria.hal.science/hal-04001505

The role of storage target allocation in applications' I/O performance with BeeGFS

Autor: Boito, Francieli, Pallez, Guillaume, Teylo, Luan

Publikováno v: CLUSTER 2022-IEEE International Conference on Cluster Computing
CLUSTER 2022-IEEE International Conference on Cluster Computing, Sep 2022, Heidelberg, Germany
2022 IEEE International Conference on Cluster Computing (CLUSTER)

International audience; Parallel file systems are at the core of HPC I/O infrastructures. Those systems minimize the I/O time of applications by separating files into fixed-size chunks and distributing them across multiple storage targets. Therefore,

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f5439a244e3aca9a74aeb8020b3622c4
https://inria.hal.science/hal-03753813/file/main.pdf