Complex Modeling of Matrix Parallel Algorithms

Peter Hanuliak

doi:doi:10.11648/j.ajnc.s.2014030501.11

| Peer-Reviewed

Complex Modeling of Matrix Parallel Algorithms

Peter Hanuliak

Published in American Journal of Networks and Communications (Volume 3, Issue 5-1)

Received: 14 July 2014 Accepted: 18 July 2014 Published: 31 July 2014

Views: Downloads:

Download PDF

Share This Article

Twitter
Linked In
Facebook

Abstract

Parallel principles are the most effective way how to increase performance in parallel computing (parallel computers and algorithms too). In this sense the paper is devoted to a complex performance evaluation of matrix parallel algorithms (MPA). At first the paper describes the typical matrix parallel algorithms and then it summarizes common properties of them to complex performance modeling of MPA. To complex performance analysis we are able to take into account all overheads influence performance of parallel algorithms (parallel computer architecture, parallel computation, communication etc.). To be le to analyze MPA in their abstract form we have defined needed decomposition models of MPA. For these decomposition strategies we derived analytical relation for defined complex performance criterions including isoefficiency functions, which allow us to predict performance although for hypothetical parallel computer. In its experimental part the paper considers the achieved results using defined complex performance criterions including issoefficiency function for performance prediction also for hypothetical future parallel computers. Such idea of common abstract analysis could be very useful in deriving complex performance criterions for groups of other similar parallel algorithms (PA) as for example numerical integration PA, optimization PA etc.

Published in	American Journal of Networks and Communications (Volume 3, Issue 5-1) This article belongs to the Special Issue Parallel Computer and Parallel Algorithms
DOI	10.11648/j.ajnc.s.2014030501.11
Page(s)	1-14
Creative Commons	This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.
Copyright	Copyright © The Author(s), 2014. Published by Science Publishing Group

Keywords

Parallel Computer, NOW, Grid, Parallel Algorithm (PA), Matrix PA, Decomposition Model, Performance Modeling, Optimization, Overhead Function H(S, P), Inter Process Communication IPC, Performance Prediction, Issoeficiency Function

References

[1]	Arora S., Barak B., Computational complexity - A modern Approach, Cambridge University Press, pp. 573, 2009
[2]	Bahi J. H., Contasst-Vivier S., Couturier R., Parallel Iterative algorithms: From Sequential to Grid Computing, CRC Press, USA, 2007
[3]	Bronson R., Costa G. B., Saccoman J. T., Linear Algebra - Algorithms, Applications, and Techniques, 3rd Edition, Elsevier Science & Technology, Netherland, pp. 536, 2014
[4]	Casanova H., Legrand A., Robert Y., Parallel algorithms, CRC Press, USA, 2008
[5]	Dattatreya G. R., Performance analysis of queuing and computer network, University of Texas, Dallas, USA, pp.472, 2008
[6]	Davis T. A., Direct methods for sparse Linear Systems, Cambridge University Press, United Kingdom, pp. 184, 2006
[7]	Desel J., Esperza J., Free Choise Petri Nets, Cambridge University Press, United Kingdom, pp. 256, 2005
[8]	Dubois M., Annavaram M., Stenstrom P., Parallel Computer Organization and Design, Cambridge university press, United Kingdom, pp. 560, 2012
[9]	Dubhash D.P., Panconesi A., Concentration of measure for the analysis of randomized algorithms, Cambridge University Press, United Kingdom, 2009
[10]	Edmonds J., How to think about algorithms, Cambridge University Press, United Kingdom, pp. 472, 2010
[11]	Gelenbe E., Analysis and synthesis of computer systems, Imperial College Press, pp. 324,2010
[12]	Goldreich O., P, NP, and NP - Completeness, Cambridge University Press, United Kingdom, pp. 214, 2010
[13]	Hager G., Wellein G., Introduction to High Performance Computing for Scientists and Engineers, CRC Press, USA, pp. 356, 2010
[14]	Hanuliak P., Hanuliak J., Complex performance modeling of parallel algorithms , American J. of Networks and Communication, Science PG, Vol. 3, USA, 2014
[15]	Hanuliak M., Modeling of parallel computers based on network of computing nodes, American J. of Networks and Communication, Science PG, Vol. 3, USA, 2014
[16]	Hanuliak M., Hanuliak J., Decomposition models of parallel algorithms, American J. of Networks and Communication, Science PG, Vol. 3, USA, 2014
[17]	Hanuliak M., Hanuliak I., To the correction of analytical models for computer based communication systems, Kybernetes, Vol. 35, No. 9, UK, pp. 1492-1504, 2006
[18]	Hanuliak J., Modeling of communication complexity in parallel computing, American J. of Networks and Communication, Science PG, Vol. 3, USA, 2014
[19]	Hanuliak M., Unified analytical models in parallel and distributed computing, AJNC (Am. J. of Networks and Comm.), SciencePG, Vol. 3, No. 1, USA, pp. 1-12, 2014
[20]	Hanuliak J., Hanuliak I., To performance evaluation of distributed parallel algorithms, Kybernetes, Volume 34, No. 9/10, United Kingdom, pp. 1633-1650, 2005
[21]	Hillston J., A Compositional Approach to Performance Modeling, University of Edinburg, Cambridge University Press, United Kingdom, pp. 172 pages, 2005
[22]	Hwang K. and coll., Distributed and Parallel Computing, Morgan Kaufmann, USA, 472 pages, 2011
[23]	Kshemkalyani A. D., Singhal M., Distributed Computing, University of Illinois, Cambridge University Press, United Kingdom, pp. 756 pages, 2011
[24]	Kirk D. B., Hwu W. W., Programming massively parallel processors, Morgan Kaufmann, USA, pp. 280, 2010
[25]	Kostin A., Ilushechkina L., Modeling and simulation of distributed systems, Imperial College Press, United Kingdom, pp. 440, 2010,
[26]	Kshemkalyani A. D., Singhal M., Distributed Computing, University of Illinois, Cambridge University Press, UK, pp. 756, 2011
[27]	Kushilevitz E., Nissan N., Communication Complexity, Cambridge University Press, United Kingdom, pp. 208, 2006,
[28]	Le Boudec Jean-Yves, Performance evaluation of computer and communication systems, CRC Press, USA, pp. 300, 2011
[29]	Levesque John, High Performance Computing: Programming and applications, CRC Press, USA, pp. 244, 2010
[30]	Lilja D. J., Measuring Computer Performance, University of Minnesota, Cambridge University Press, United Kingdom, pp. 280, 2005
[31]	McCabe J., D., Network analysis, architecture, and design (3rd edition), Elsevier/ Morgan Kaufmann, USA, pp. 496, 2010
[32]	Meerschaert M., Mathematical modeling (4-th edition), Elsevier, pp. 384, 2013
[33]	Misra Ch. S.,Woungang I., Selected topics in communication network and distributed systems, Imperial college press, United Kingdom, pp. 808, United Kingdom
[34]	Peterson L. L., Davie B. C., Computer networks – a system approach, Morgan Kaufmann, USA, pp. 920, 2011
[35]	Resch M. M., Supercomputers in Grids, Int. J. of Grid and HPC, No.1, pp. 1 - 9, 2009
[36]	Riano l., McGinity T.M., Quantifying the role of complexity in a system´s performance, Evolving Systems, Springer Verlag, Germany, pp. 189 – 198, 2011
[37]	Shapira Y., Solving PDEs in C++ - Numerical Methods in a Unified Object-Oriented Approach (2nd edition), Cambridge University Press, United Kingdom, pp. 800, 2012
[38]	Wang L., Jie Wei., Chen J., Grid Computing: Infrastructure, Service, and Application, CRC Press, USA, 2009 www pages
[39]	www.top500.org.

Cite This Article

Plain Text BibTeX RIS

APA Style

Peter Hanuliak. (2014). Complex Modeling of Matrix Parallel Algorithms. American Journal of Networks and Communications, 3(5-1), 1-14. https://doi.org/10.11648/j.ajnc.s.2014030501.11

Copy | Download

ACS Style

Peter Hanuliak. Complex Modeling of Matrix Parallel Algorithms. Am. J. Netw. Commun. 2014, 3(5-1), 1-14. doi: 10.11648/j.ajnc.s.2014030501.11

Copy | Download

AMA Style

Peter Hanuliak. Complex Modeling of Matrix Parallel Algorithms. Am J Netw Commun. 2014;3(5-1):1-14. doi: 10.11648/j.ajnc.s.2014030501.11

Copy | Download

@article{10.11648/j.ajnc.s.2014030501.11,
  author = {Peter Hanuliak},
  title = {Complex Modeling of Matrix Parallel Algorithms},
  journal = {American Journal of Networks and Communications},
  volume = {3},
  number = {5-1},
  pages = {1-14},
  doi = {10.11648/j.ajnc.s.2014030501.11},
  url = {https://doi.org/10.11648/j.ajnc.s.2014030501.11},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajnc.s.2014030501.11},
  abstract = {Parallel principles are the most effective way how to increase performance in parallel computing (parallel computers and algorithms too). In this sense the paper is devoted to a complex performance evaluation of matrix parallel algorithms (MPA). At first the paper describes the typical matrix parallel algorithms and then it summarizes common properties of them to complex performance modeling of MPA. To complex performance analysis we are able to take into account all overheads influence performance of parallel algorithms (parallel computer architecture, parallel computation, communication etc.). To be le to analyze MPA in their abstract form we have defined needed decomposition models of MPA. For these decomposition strategies we derived analytical relation for defined complex performance criterions including isoefficiency functions, which allow us to predict performance although for hypothetical parallel computer. In its experimental part the paper considers the achieved results using defined complex performance criterions including issoefficiency function for performance prediction also for hypothetical future parallel computers. Such idea of common abstract analysis could be very useful in deriving complex performance criterions for groups of other similar parallel algorithms (PA) as for example numerical integration PA, optimization PA etc.},
 year = {2014}
}

Copy | Download

TY  - JOUR
T1  - Complex Modeling of Matrix Parallel Algorithms
AU  - Peter Hanuliak
Y1  - 2014/07/31
PY  - 2014
N1  - https://doi.org/10.11648/j.ajnc.s.2014030501.11
DO  - 10.11648/j.ajnc.s.2014030501.11
T2  - American Journal of Networks and Communications
JF  - American Journal of Networks and Communications
JO  - American Journal of Networks and Communications
SP  - 1
EP  - 14
PB  - Science Publishing Group
SN  - 2326-8964
UR  - https://doi.org/10.11648/j.ajnc.s.2014030501.11
AB  - Parallel principles are the most effective way how to increase performance in parallel computing (parallel computers and algorithms too). In this sense the paper is devoted to a complex performance evaluation of matrix parallel algorithms (MPA). At first the paper describes the typical matrix parallel algorithms and then it summarizes common properties of them to complex performance modeling of MPA. To complex performance analysis we are able to take into account all overheads influence performance of parallel algorithms (parallel computer architecture, parallel computation, communication etc.). To be le to analyze MPA in their abstract form we have defined needed decomposition models of MPA. For these decomposition strategies we derived analytical relation for defined complex performance criterions including isoefficiency functions, which allow us to predict performance although for hypothetical parallel computer. In its experimental part the paper considers the achieved results using defined complex performance criterions including issoefficiency function for performance prediction also for hypothetical future parallel computers. Such idea of common abstract analysis could be very useful in deriving complex performance criterions for groups of other similar parallel algorithms (PA) as for example numerical integration PA, optimization PA etc.
VL  - 3
IS  - 5-1
ER  -

Copy | Download

Author Information

Peter Hanuliak

Dubnica Technical Institute, Sladkovicova 533/20, Dubnica nad Vahom, 018 41, Slovakia

Download PDF

Sections

Plain Text BibTeX RIS

APA Style

Peter Hanuliak. (2014). Complex Modeling of Matrix Parallel Algorithms. American Journal of Networks and Communications, 3(5-1), 1-14. https://doi.org/10.11648/j.ajnc.s.2014030501.11

Copy | Download

ACS Style

Peter Hanuliak. Complex Modeling of Matrix Parallel Algorithms. Am. J. Netw. Commun. 2014, 3(5-1), 1-14. doi: 10.11648/j.ajnc.s.2014030501.11

Copy | Download

AMA Style

Peter Hanuliak. Complex Modeling of Matrix Parallel Algorithms. Am J Netw Commun. 2014;3(5-1):1-14. doi: 10.11648/j.ajnc.s.2014030501.11

Copy | Download

@article{10.11648/j.ajnc.s.2014030501.11,
  author = {Peter Hanuliak},
  title = {Complex Modeling of Matrix Parallel Algorithms},
  journal = {American Journal of Networks and Communications},
  volume = {3},
  number = {5-1},
  pages = {1-14},
  doi = {10.11648/j.ajnc.s.2014030501.11},
  url = {https://doi.org/10.11648/j.ajnc.s.2014030501.11},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajnc.s.2014030501.11},
  abstract = {Parallel principles are the most effective way how to increase performance in parallel computing (parallel computers and algorithms too). In this sense the paper is devoted to a complex performance evaluation of matrix parallel algorithms (MPA). At first the paper describes the typical matrix parallel algorithms and then it summarizes common properties of them to complex performance modeling of MPA. To complex performance analysis we are able to take into account all overheads influence performance of parallel algorithms (parallel computer architecture, parallel computation, communication etc.). To be le to analyze MPA in their abstract form we have defined needed decomposition models of MPA. For these decomposition strategies we derived analytical relation for defined complex performance criterions including isoefficiency functions, which allow us to predict performance although for hypothetical parallel computer. In its experimental part the paper considers the achieved results using defined complex performance criterions including issoefficiency function for performance prediction also for hypothetical future parallel computers. Such idea of common abstract analysis could be very useful in deriving complex performance criterions for groups of other similar parallel algorithms (PA) as for example numerical integration PA, optimization PA etc.},
 year = {2014}
}

Copy | Download

TY  - JOUR
T1  - Complex Modeling of Matrix Parallel Algorithms
AU  - Peter Hanuliak
Y1  - 2014/07/31
PY  - 2014
N1  - https://doi.org/10.11648/j.ajnc.s.2014030501.11
DO  - 10.11648/j.ajnc.s.2014030501.11
T2  - American Journal of Networks and Communications
JF  - American Journal of Networks and Communications
JO  - American Journal of Networks and Communications
SP  - 1
EP  - 14
PB  - Science Publishing Group
SN  - 2326-8964
UR  - https://doi.org/10.11648/j.ajnc.s.2014030501.11
AB  - Parallel principles are the most effective way how to increase performance in parallel computing (parallel computers and algorithms too). In this sense the paper is devoted to a complex performance evaluation of matrix parallel algorithms (MPA). At first the paper describes the typical matrix parallel algorithms and then it summarizes common properties of them to complex performance modeling of MPA. To complex performance analysis we are able to take into account all overheads influence performance of parallel algorithms (parallel computer architecture, parallel computation, communication etc.). To be le to analyze MPA in their abstract form we have defined needed decomposition models of MPA. For these decomposition strategies we derived analytical relation for defined complex performance criterions including isoefficiency functions, which allow us to predict performance although for hypothetical parallel computer. In its experimental part the paper considers the achieved results using defined complex performance criterions including issoefficiency function for performance prediction also for hypothetical future parallel computers. Such idea of common abstract analysis could be very useful in deriving complex performance criterions for groups of other similar parallel algorithms (PA) as for example numerical integration PA, optimization PA etc.
VL  - 3
IS  - 5-1
ER  -

Copy | Download