Performance evaluation of multiple cloud data centers allocations for HPC

Eduardo Roloff; Emmanuell Diaz Carreño; Jimmy K.M. Valverde-Sánchez; Matthias Diener; Matheus Da Silva Serpa; Guillaume Houzeaux; Lucas M. Schnorr; Nicolas Maillard; Luciano Paschoal Gaspary; Philippe Navaux

doi:10.1007/978-3-319-57972-6_2

Performance evaluation of multiple cloud data centers allocations for HPC

Eduardo Roloff, Emmanuell Diaz Carreño, Jimmy K.M. Valverde-Sánchez, Matthias Diener, Matheus Da Silva Serpa, Guillaume Houzeaux, Lucas M. Schnorr, Nicolas Maillard, Luciano Paschoal Gaspary, Philippe Navaux

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper evaluates the behavior of the Microsoft Azure G5 cloud instance type over multiple Data Centers. The purpose is to identify if there are major differences between them and to help the users choose the best option for their needs. Our results show that there are differences in the network level for the same instance type in different locations and inside the same location at different times. The network performance causes interference in the applications level, as we could verify in our results.

Original language	English (US)
Title of host publication	High Performance Computing - 3rd Latin American Conference, CARLA 2016, Revised Selected Papers
Editors	Carlos Jaime Barrios Hernandez, Isidoro Gitler, Jaime Klapp
Publisher	Springer
Pages	18-32
Number of pages	15
ISBN (Print)	9783319579719
DOIs	https://doi.org/10.1007/978-3-319-57972-6_2
State	Published - 2017
Externally published	Yes
Event	3rd Latin American Conference on High Performance Computing, CARLA 2016 - Mexico City, Mexico Duration: Aug 29 2016 → Sep 2 2016

Publication series

Name	Communications in Computer and Information Science
Volume	697
ISSN (Print)	1865-0929

Conference

Conference	3rd Latin American Conference on High Performance Computing, CARLA 2016
Country/Territory	Mexico
City	Mexico City
Period	8/29/16 → 9/2/16

Keywords

Azure
Cloud Computing
HPC
MPI
NAS

ASJC Scopus subject areas

General Computer Science
General Mathematics

Online availability

10.1007/978-3-319-57972-6_2

Library availability

Discover UIUC Full Text

Cite this

Roloff, E., Carreño, E. D., Valverde-Sánchez, J. K. M., Diener, M., Da Silva Serpa, M., Houzeaux, G., Schnorr, L. M., Maillard, N., Gaspary, L. P., & Navaux, P. (2017). Performance evaluation of multiple cloud data centers allocations for HPC. In C. J. Barrios Hernandez, I. Gitler, & J. Klapp (Eds.), High Performance Computing - 3rd Latin American Conference, CARLA 2016, Revised Selected Papers (pp. 18-32). (Communications in Computer and Information Science; Vol. 697). Springer. https://doi.org/10.1007/978-3-319-57972-6_2

Performance evaluation of multiple cloud data centers allocations for HPC. / Roloff, Eduardo; Carreño, Emmanuell Diaz; Valverde-Sánchez, Jimmy K.M. et al.
High Performance Computing - 3rd Latin American Conference, CARLA 2016, Revised Selected Papers. ed. / Carlos Jaime Barrios Hernandez; Isidoro Gitler; Jaime Klapp. Springer, 2017. p. 18-32 (Communications in Computer and Information Science; Vol. 697).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Roloff, E, Carreño, ED, Valverde-Sánchez, JKM, Diener, M, Da Silva Serpa, M, Houzeaux, G, Schnorr, LM, Maillard, N, Gaspary, LP & Navaux, P 2017, Performance evaluation of multiple cloud data centers allocations for HPC. in CJ Barrios Hernandez, I Gitler & J Klapp (eds), High Performance Computing - 3rd Latin American Conference, CARLA 2016, Revised Selected Papers. Communications in Computer and Information Science, vol. 697, Springer, pp. 18-32, 3rd Latin American Conference on High Performance Computing, CARLA 2016, Mexico City, Mexico, 8/29/16. https://doi.org/10.1007/978-3-319-57972-6_2

Roloff E, Carreño ED, Valverde-Sánchez JKM, Diener M, Da Silva Serpa M, Houzeaux G et al. Performance evaluation of multiple cloud data centers allocations for HPC. In Barrios Hernandez CJ, Gitler I, Klapp J, editors, High Performance Computing - 3rd Latin American Conference, CARLA 2016, Revised Selected Papers. Springer. 2017. p. 18-32. (Communications in Computer and Information Science). doi: 10.1007/978-3-319-57972-6_2

Roloff, Eduardo ; Carreño, Emmanuell Diaz ; Valverde-Sánchez, Jimmy K.M. et al. / Performance evaluation of multiple cloud data centers allocations for HPC. High Performance Computing - 3rd Latin American Conference, CARLA 2016, Revised Selected Papers. editor / Carlos Jaime Barrios Hernandez ; Isidoro Gitler ; Jaime Klapp. Springer, 2017. pp. 18-32 (Communications in Computer and Information Science).

@inproceedings{50a0da96189d44499011ba197de33f96,

title = "Performance evaluation of multiple cloud data centers allocations for HPC",

abstract = "This paper evaluates the behavior of the Microsoft Azure G5 cloud instance type over multiple Data Centers. The purpose is to identify if there are major differences between them and to help the users choose the best option for their needs. Our results show that there are differences in the network level for the same instance type in different locations and inside the same location at different times. The network performance causes interference in the applications level, as we could verify in our results.",

keywords = "Azure, Cloud Computing, HPC, MPI, NAS",

author = "Eduardo Roloff and Carre{\~n}o, {Emmanuell Diaz} and Valverde-S{\'a}nchez, {Jimmy K.M.} and Matthias Diener and {Da Silva Serpa}, Matheus and Guillaume Houzeaux and Schnorr, {Lucas M.} and Nicolas Maillard and Gaspary, {Luciano Paschoal} and Philippe Navaux",

note = "Funding Information: This research received funding from the EU H2020 Programme and from MCTI/RNP-Brazil under the HPC4E project, grant agreement no. 689772. Experiments presented in this paper were carried out using the Grid{\textquoteright}5000 testbed, supported by a scientific interest group hosted by Inria and including CNRS, RENATER and several Universities as well as other organizations (see https://www.grid5000.fr ). Additional funding was provided by CAPES and Microsoft. Publisher Copyright: {\textcopyright} Springer International Publishing AG 2017.; 3rd Latin American Conference on High Performance Computing, CARLA 2016 ; Conference date: 29-08-2016 Through 02-09-2016",

year = "2017",

doi = "10.1007/978-3-319-57972-6_2",

language = "English (US)",

isbn = "9783319579719",

series = "Communications in Computer and Information Science",

publisher = "Springer",

pages = "18--32",

editor = "{Barrios Hernandez}, {Carlos Jaime} and Isidoro Gitler and Jaime Klapp",

booktitle = "High Performance Computing - 3rd Latin American Conference, CARLA 2016, Revised Selected Papers",

address = "Germany",

}

TY - GEN

T1 - Performance evaluation of multiple cloud data centers allocations for HPC

AU - Roloff, Eduardo

AU - Carreño, Emmanuell Diaz

AU - Valverde-Sánchez, Jimmy K.M.

AU - Diener, Matthias

AU - Da Silva Serpa, Matheus

AU - Houzeaux, Guillaume

AU - Schnorr, Lucas M.

AU - Maillard, Nicolas

AU - Gaspary, Luciano Paschoal

AU - Navaux, Philippe

N1 - Funding Information: This research received funding from the EU H2020 Programme and from MCTI/RNP-Brazil under the HPC4E project, grant agreement no. 689772. Experiments presented in this paper were carried out using the Grid’5000 testbed, supported by a scientific interest group hosted by Inria and including CNRS, RENATER and several Universities as well as other organizations (see https://www.grid5000.fr ). Additional funding was provided by CAPES and Microsoft. Publisher Copyright: © Springer International Publishing AG 2017.

PY - 2017

Y1 - 2017

N2 - This paper evaluates the behavior of the Microsoft Azure G5 cloud instance type over multiple Data Centers. The purpose is to identify if there are major differences between them and to help the users choose the best option for their needs. Our results show that there are differences in the network level for the same instance type in different locations and inside the same location at different times. The network performance causes interference in the applications level, as we could verify in our results.

AB - This paper evaluates the behavior of the Microsoft Azure G5 cloud instance type over multiple Data Centers. The purpose is to identify if there are major differences between them and to help the users choose the best option for their needs. Our results show that there are differences in the network level for the same instance type in different locations and inside the same location at different times. The network performance causes interference in the applications level, as we could verify in our results.

KW - Azure

KW - Cloud Computing

KW - HPC

KW - MPI

KW - NAS

UR - http://www.scopus.com/inward/record.url?scp=85019065975&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85019065975&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-57972-6_2

DO - 10.1007/978-3-319-57972-6_2

M3 - Conference contribution

AN - SCOPUS:85019065975

SN - 9783319579719

T3 - Communications in Computer and Information Science

SP - 18

EP - 32

BT - High Performance Computing - 3rd Latin American Conference, CARLA 2016, Revised Selected Papers

A2 - Barrios Hernandez, Carlos Jaime

A2 - Gitler, Isidoro

A2 - Klapp, Jaime

PB - Springer

T2 - 3rd Latin American Conference on High Performance Computing, CARLA 2016

Y2 - 29 August 2016 through 2 September 2016

ER -

Performance evaluation of multiple cloud data centers allocations for HPC

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this