Skip to main content
SpringerLink
Log in

Matching high performance approximate inverse preconditioning to architectural platforms

  • Published:
The Journal of Supercomputing Aims and scope Submit manuscript

Abstract

In this paper we examine the performance of parallel approximate inverse preconditioning for solving finite element systems, using a variety of clusters containing the Message Passing Interface (MPI) communication library, the Globus toolkit and the Open MPI open-source software. The techniques outlined in this paper contain parameters that can be varied so as to tune the execution to the underlying platform. These parameters include the number of CPUs, the order of the linear system (n) and the “retention parameter” (δ l) of the approximate inverse used as a preconditioner. Numerical results are presented for solving finite element sparse linear systems on platforms with various CPU types and number, different compilers, different File System types, different MPI implementations and different memory sizes.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Buyya R (1999) High performance cluster computing: architectures and systems, vol 1. Prentice-Hall

  2. Foster I, Kesselman C (2005) The grid: blueprint for a new computing infrastructure. Morgan Kaufmann

  3. Foster I, Kesselman C (1997) Globus: a metacomputing infrastructure toolkit. Int J Supercomput Appl 11(2):115–128

    Article  Google Scholar 

  4. Foster I, Kesselman C, Tuecke S (2001) The anatomy of the grid: enabling scalable virtual organizations. Int J High Perform Comput Appl 15(3):200–222

    Article  Google Scholar 

  5. Gabriel E, Fagg GE, Bosilca G, Angskun T, Dongarra JJ, Squyres JM, Sahay V, Kambadur P, Barrett B, Lumsdaine A, Castain RH, Daniel DJ, Graham RL, Timothy S (2004) Open MPI: goals, concept, and design of a next generation MPI implementation, Woodall. In: Proceedings, 11th European PVM/MPI users’ group meeting, Budapest, Hungary, September 2004

  6. Gravvanis GA (1998) Parallel matrix techniques. In: Papailiou K, Tsahalis D, Periaux J, Hirsch C, Pandolfi M (eds) Computational fluid dynamics. Wiley, vol I, pp 472–477

  7. Gravvanis GA, Giannoutakis KM (2004) Normalized explicit finite element approximate inverse preconditioning. Int J Comput Struct 82(28):2377–2388

    Article  MathSciNet  Google Scholar 

  8. Gravvanis GA, Giannoutakis KM (2004) Parallel approximate finite element inverse preconditioning on distributed systems. In: Proceedings of the third international symposium on parallel and distributed computing 2004 (ISPDC 2004) and the third international workshop on algorithms, models and tools for parallel computing on heterogeneous networks (HeteroPar 2004). IEEE Computer Society Press, IEEE, pp 277–283

  9. Gravvanis GA, Giannoutakis KM, Bekakos MP (2004) Parallel finite element approximate inverse preconditioning on symmetric multiprocessor systems. In: Proceedings of the international conference on parallel and distributed processing techniques and applications, Arabnia HR (ed). CSREA Press, vol I, pp 168–175

  10. Gropp W, Lusk E, Doss N, Skjellum A (1996) A high-performance, portable implementation of the MPI message passing interface standard. Parallel Comput J 22(6):789–828

    Article  MATH  Google Scholar 

  11. Karohis NT, Toonen B, Foster I (2003) MPICH-G2: A grid-enabled implementation of the message passing interface. J Parallel Distrib Comput 63(5):551–563

    Article  Google Scholar 

  12. Lipitakis EA (1989) Numerical solution of three-dimensional boundary-value problems by generalized approximate inverse matrix techniques. Int J Comput Math 31:69–89

    Article  MATH  Google Scholar 

  13. Lipitakis EA (1983) A normalized sparse linear equation solver. J Comput Appl Math 9:287–298

    Article  MATH  Google Scholar 

  14. Lipitakis EA, Evans DJ (1987) Explicit semi-direct methods based on approximate inverse matrix techniques for solving boundary value problems on parallel processors. Math Comput Simul 29:1–17

    Article  MATH  Google Scholar 

  15. Lipitakis EA, Evans DJ (1984) Solving linear finite element systems by normalized approximate matrix factorization semi-direct methods. Comput Method Appl Mech Eng 43:1–19

    Article  MATH  MathSciNet  Google Scholar 

  16. Lipitakis EA, Gravvanis GA (1992) A class of explicit preconditioned conjugate gradient methods for solving large finite element systems. Int J Comput Math 44:189–206

    Article  MATH  Google Scholar 

  17. Morrison JP, Coghlan B, Shearer A, Foley S, Power DA, Perrott R (2006) WebCom-G: a candidate middleware for grid-Ireland, accepted for publication, Int J High Perform Comput Appl

  18. MPICH2, http://www-unix.mcs.anl.gov/mpi/mpich1/

  19. Open MPI, http://www.open-mpi.org/

Download references

Author information

Authors and Affiliations

  1. Department of Electrical and Computer Engineering, School of Engineering, Democritus University of Thrace, 67100, Xanthi, Greece

    K. M. Giannoutakis & G. A. Gravvanis

  2. Centre for Unified Computing, Department of Computer Science, University College Cork, Cork, Ireland

    B. Clayton, A. Patil, T. Enright & J. P. Morrison

Authors
  1. K. M. Giannoutakis
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. G. A. Gravvanis
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. B. Clayton
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. A. Patil
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. T. Enright
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. J. P. Morrison
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to G. A. Gravvanis.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Giannoutakis, K.M., Gravvanis, G.A., Clayton, B. et al. Matching high performance approximate inverse preconditioning to architectural platforms. J Supercomput 42, 145–163 (2007). https://doi.org/10.1007/s11227-007-0129-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11227-007-0129-1

Keywords

Search

Navigation