On issues concerning cloud environments in scope of scalable multi-projection methods

Byron E. Moutafis; Christos K. Filelis-Papadopoulos; George A. Gravvanis; John P. Morrison

doi:10.1109/SYNASC.2016.061

On issues concerning cloud environments in scope of scalable multi-projection methods

Byron E. Moutafis
, Christos K. Filelis-Papadopoulos
, George A. Gravvanis
, John P. Morrison

School of Computer Science and Information Technology

Democritus University of Thrace

Research output: Chapter in Book/Report/Conference proceedings › Conference proceeding › peer-review

Abstract

Over the last decade, Cloud environments have gained significant attention by the scientific community, due to their flexibility in the allocation of resources and the various applications hosted in such environments. Recently, high performance computing applications are migrating to Cloud environments. Efficient methods are sought for solving very large sparse linear systems occurring in various scientific fields such as Computational Fluid Dynamics, N-Body simulations and Computational Finance. Herewith, the parallel multi-projection type methods are reviewed and discussions concerning the implementation issues for IaaS-type Cloud environments are given. Moreover, phenomena occurring due to the 'noisy neighbor' problem, varying interconnection speeds as well as load imbalance are studied. Furthermore, the level of exposure of specialized hardware residing in modern CPUs through the different layers of software is also examined. Finally, numerical results concerning the applicability and effectiveness of multi-projection type methods in Cloud environments based on OpenStack are presented.

Original language	English
Title of host publication	Proceedings - 18th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing, SYNASC 2016
Editors	James Davenport, Dana Petcu, Tudor Jebelean, Viorel Negru, Stephen M. Watt, Tetsuo Ida, Daniela Zaharie
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	343-350
Number of pages	8
ISBN (Electronic)	9781509057078
DOIs	https://doi.org/10.1109/SYNASC.2016.061
Publication status	Published - 23 Jan 2017
Event	18th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing, SYNASC 2016 - Timisoara, Romania Duration: 24 Sep 2016 → 27 Sep 2016

Publication series

Name	Proceedings - 18th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing, SYNASC 2016

Conference

Conference	18th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing, SYNASC 2016
Country/Territory	Romania
City	Timisoara
Period	24/09/16 → 27/09/16

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

aggregation
algebraic domain decomposition
cloud computing
high performance computing
parallel hybrid solver
semi-coarsening
sparse and dense matrix computations

Access to Document

10.1109/SYNASC.2016.061

Cite this

Moutafis, B. E., Filelis-Papadopoulos, C. K., Gravvanis, G. A., & Morrison, J. P. (2017). On issues concerning cloud environments in scope of scalable multi-projection methods. In J. Davenport, D. Petcu, T. Jebelean, V. Negru, S. M. Watt, T. Ida, & D. Zaharie (Eds.), Proceedings - 18th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing, SYNASC 2016 (pp. 343-350). Article 7829633 (Proceedings - 18th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing, SYNASC 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SYNASC.2016.061

Moutafis, Byron E. ; Filelis-Papadopoulos, Christos K. ; Gravvanis, George A. et al. / On issues concerning cloud environments in scope of scalable multi-projection methods. Proceedings - 18th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing, SYNASC 2016. editor / James Davenport ; Dana Petcu ; Tudor Jebelean ; Viorel Negru ; Stephen M. Watt ; Tetsuo Ida ; Daniela Zaharie. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 343-350 (Proceedings - 18th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing, SYNASC 2016).

@inproceedings{65a16cbb07f04531881b4c3dbd01950d,

title = "On issues concerning cloud environments in scope of scalable multi-projection methods",

abstract = "Over the last decade, Cloud environments have gained significant attention by the scientific community, due to their flexibility in the allocation of resources and the various applications hosted in such environments. Recently, high performance computing applications are migrating to Cloud environments. Efficient methods are sought for solving very large sparse linear systems occurring in various scientific fields such as Computational Fluid Dynamics, N-Body simulations and Computational Finance. Herewith, the parallel multi-projection type methods are reviewed and discussions concerning the implementation issues for IaaS-type Cloud environments are given. Moreover, phenomena occurring due to the 'noisy neighbor' problem, varying interconnection speeds as well as load imbalance are studied. Furthermore, the level of exposure of specialized hardware residing in modern CPUs through the different layers of software is also examined. Finally, numerical results concerning the applicability and effectiveness of multi-projection type methods in Cloud environments based on OpenStack are presented.",

keywords = "aggregation, algebraic domain decomposition, cloud computing, high performance computing, parallel hybrid solver, semi-coarsening, sparse and dense matrix computations",

author = "Moutafis, \{Byron E.\} and Filelis-Papadopoulos, \{Christos K.\} and Gravvanis, \{George A.\} and Morrison, \{John P.\}",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 18th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing, SYNASC 2016 ; Conference date: 24-09-2016 Through 27-09-2016",

year = "2017",

month = jan,

day = "23",

doi = "10.1109/SYNASC.2016.061",

language = "English",

series = "Proceedings - 18th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing, SYNASC 2016",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "343--350",

editor = "James Davenport and Dana Petcu and Tudor Jebelean and Viorel Negru and Watt, \{Stephen M.\} and Tetsuo Ida and Daniela Zaharie",

booktitle = "Proceedings - 18th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing, SYNASC 2016",

address = "United States",

}

Moutafis, BE, Filelis-Papadopoulos, CK, Gravvanis, GA & Morrison, JP 2017, On issues concerning cloud environments in scope of scalable multi-projection methods. in J Davenport, D Petcu, T Jebelean, V Negru, SM Watt, T Ida & D Zaharie (eds), Proceedings - 18th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing, SYNASC 2016., 7829633, Proceedings - 18th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing, SYNASC 2016, Institute of Electrical and Electronics Engineers Inc., pp. 343-350, 18th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing, SYNASC 2016, Timisoara, Romania, 24/09/16. https://doi.org/10.1109/SYNASC.2016.061

On issues concerning cloud environments in scope of scalable multi-projection methods. / Moutafis, Byron E.; Filelis-Papadopoulos, Christos K.; Gravvanis, George A. et al.
Proceedings - 18th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing, SYNASC 2016. ed. / James Davenport; Dana Petcu; Tudor Jebelean; Viorel Negru; Stephen M. Watt; Tetsuo Ida; Daniela Zaharie. Institute of Electrical and Electronics Engineers Inc., 2017. p. 343-350 7829633 (Proceedings - 18th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing, SYNASC 2016).

Research output: Chapter in Book/Report/Conference proceedings › Conference proceeding › peer-review

TY - GEN

T1 - On issues concerning cloud environments in scope of scalable multi-projection methods

AU - Moutafis, Byron E.

AU - Filelis-Papadopoulos, Christos K.

AU - Gravvanis, George A.

AU - Morrison, John P.

PY - 2017/1/23

Y1 - 2017/1/23

N2 - Over the last decade, Cloud environments have gained significant attention by the scientific community, due to their flexibility in the allocation of resources and the various applications hosted in such environments. Recently, high performance computing applications are migrating to Cloud environments. Efficient methods are sought for solving very large sparse linear systems occurring in various scientific fields such as Computational Fluid Dynamics, N-Body simulations and Computational Finance. Herewith, the parallel multi-projection type methods are reviewed and discussions concerning the implementation issues for IaaS-type Cloud environments are given. Moreover, phenomena occurring due to the 'noisy neighbor' problem, varying interconnection speeds as well as load imbalance are studied. Furthermore, the level of exposure of specialized hardware residing in modern CPUs through the different layers of software is also examined. Finally, numerical results concerning the applicability and effectiveness of multi-projection type methods in Cloud environments based on OpenStack are presented.

AB - Over the last decade, Cloud environments have gained significant attention by the scientific community, due to their flexibility in the allocation of resources and the various applications hosted in such environments. Recently, high performance computing applications are migrating to Cloud environments. Efficient methods are sought for solving very large sparse linear systems occurring in various scientific fields such as Computational Fluid Dynamics, N-Body simulations and Computational Finance. Herewith, the parallel multi-projection type methods are reviewed and discussions concerning the implementation issues for IaaS-type Cloud environments are given. Moreover, phenomena occurring due to the 'noisy neighbor' problem, varying interconnection speeds as well as load imbalance are studied. Furthermore, the level of exposure of specialized hardware residing in modern CPUs through the different layers of software is also examined. Finally, numerical results concerning the applicability and effectiveness of multi-projection type methods in Cloud environments based on OpenStack are presented.

KW - aggregation

KW - algebraic domain decomposition

KW - cloud computing

KW - high performance computing

KW - parallel hybrid solver

KW - semi-coarsening

KW - sparse and dense matrix computations

UR - https://www.scopus.com/pages/publications/85013868410

U2 - 10.1109/SYNASC.2016.061

DO - 10.1109/SYNASC.2016.061

M3 - Conference proceeding

AN - SCOPUS:85013868410

T3 - Proceedings - 18th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing, SYNASC 2016

SP - 343

EP - 350

BT - Proceedings - 18th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing, SYNASC 2016

A2 - Davenport, James

A2 - Petcu, Dana

A2 - Jebelean, Tudor

A2 - Negru, Viorel

A2 - Watt, Stephen M.

A2 - Ida, Tetsuo

A2 - Zaharie, Daniela

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 18th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing, SYNASC 2016

Y2 - 24 September 2016 through 27 September 2016

ER -

Moutafis BE, Filelis-Papadopoulos CK, Gravvanis GA, Morrison JP. On issues concerning cloud environments in scope of scalable multi-projection methods. In Davenport J, Petcu D, Jebelean T, Negru V, Watt SM, Ida T, Zaharie D, editors, Proceedings - 18th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing, SYNASC 2016. Institute of Electrical and Electronics Engineers Inc. 2017. p. 343-350. 7829633. (Proceedings - 18th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing, SYNASC 2016). doi: 10.1109/SYNASC.2016.061

On issues concerning cloud environments in scope of scalable multi-projection methods

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this