The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Un centre de données conventionnel constitué de serveurs monolithiques est confronté à des limitations, notamment un manque de flexibilité opérationnelle, une faible utilisation des ressources, une faible maintenabilité, etc. La désagrégation des ressources est une solution prometteuse pour résoudre les problèmes ci-dessus. Nous proposons un concept d'architecture de centre de données cloud désagrégée appelé Flow-in-Cloud (FiC) qui permet à un système informatique en cluster existant d'étendre un pool d'accélérateurs via un réseau à haut débit. FlowOS-RM gère l'intégralité des ressources du pool et déploie une tâche utilisateur sur une tranche construite dynamiquement en fonction d'une demande de l'utilisateur. Cette tranche se compose de nœuds de calcul et d'accélérateurs, chaque accélérateur étant attaché au nœud de calcul correspondant. Cet article démontre la faisabilité de FiC dans une expérience de preuve de concept exécutant une application d'apprentissage profond distribuée sur le système prototype. Le résultat garantit avec succès l’applicabilité du système proposé.
Ryousei TAKANO
National Institute of Advanced Industrial Science and Technology (AIST)
Kuniyasu SUZAKI
National Institute of Advanced Industrial Science and Technology (AIST)
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Ryousei TAKANO, Kuniyasu SUZAKI, "Disaggregated Accelerator Management System for Cloud Data Centers" in IEICE TRANSACTIONS on Information,
vol. E104-D, no. 3, pp. 465-468, March 2021, doi: 10.1587/transinf.2020EDL8040.
Abstract: A conventional data center that consists of monolithic-servers is confronted with limitations including lack of operational flexibility, low resource utilization, low maintainability, etc. Resource disaggregation is a promising solution to address the above issues. We propose a concept of disaggregated cloud data center architecture called Flow-in-Cloud (FiC) that enables an existing cluster computer system to expand an accelerator pool through a high-speed network. FlowOS-RM manages the entire pool resources, and deploys a user job on a dynamically constructed slice according to a user request. This slice consists of compute nodes and accelerators where each accelerator is attached to the corresponding compute node. This paper demonstrates the feasibility of FiC in a proof of concept experiment running a distributed deep learning application on the prototype system. The result successfully warrants the applicability of the proposed system.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2020EDL8040/_p
Copier
@ARTICLE{e104-d_3_465,
author={Ryousei TAKANO, Kuniyasu SUZAKI, },
journal={IEICE TRANSACTIONS on Information},
title={Disaggregated Accelerator Management System for Cloud Data Centers},
year={2021},
volume={E104-D},
number={3},
pages={465-468},
abstract={A conventional data center that consists of monolithic-servers is confronted with limitations including lack of operational flexibility, low resource utilization, low maintainability, etc. Resource disaggregation is a promising solution to address the above issues. We propose a concept of disaggregated cloud data center architecture called Flow-in-Cloud (FiC) that enables an existing cluster computer system to expand an accelerator pool through a high-speed network. FlowOS-RM manages the entire pool resources, and deploys a user job on a dynamically constructed slice according to a user request. This slice consists of compute nodes and accelerators where each accelerator is attached to the corresponding compute node. This paper demonstrates the feasibility of FiC in a proof of concept experiment running a distributed deep learning application on the prototype system. The result successfully warrants the applicability of the proposed system.},
keywords={},
doi={10.1587/transinf.2020EDL8040},
ISSN={1745-1361},
month={March},}
Copier
TY - JOUR
TI - Disaggregated Accelerator Management System for Cloud Data Centers
T2 - IEICE TRANSACTIONS on Information
SP - 465
EP - 468
AU - Ryousei TAKANO
AU - Kuniyasu SUZAKI
PY - 2021
DO - 10.1587/transinf.2020EDL8040
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E104-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2021
AB - A conventional data center that consists of monolithic-servers is confronted with limitations including lack of operational flexibility, low resource utilization, low maintainability, etc. Resource disaggregation is a promising solution to address the above issues. We propose a concept of disaggregated cloud data center architecture called Flow-in-Cloud (FiC) that enables an existing cluster computer system to expand an accelerator pool through a high-speed network. FlowOS-RM manages the entire pool resources, and deploys a user job on a dynamically constructed slice according to a user request. This slice consists of compute nodes and accelerators where each accelerator is attached to the corresponding compute node. This paper demonstrates the feasibility of FiC in a proof of concept experiment running a distributed deep learning application on the prototype system. The result successfully warrants the applicability of the proposed system.
ER -