Advertisement

The Impact of Multicore on Math Software

  • Alfredo Buttari
  • Jack Dongarra
  • Jakub Kurzak
  • Julien Langou
  • Piotr Luszczek
  • Stanimire Tomov
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4699)

Abstract

Power consumption and heat dissipation issues are pushing the microprocessors industry towards multicore design patterns. Given the cubic dependence between core frequency and power consumption, multicore technologies leverage the idea that doubling the number of cores and halving the cores frequency gives roughly the same performance reducing the power consumption by a factor of four. With the number of cores on multicore chips expected to reach tens in a few years, efficient implementations of numerical libraries using shared memory programming models is of high interest. The current message passing paradigm used in ScaLAPACK and elsewhere introduces unnecessary memory overhead and memory copy operations, which degrade performance, along with the making it harder to schedule operations that could be done in parallel. Limiting the use of shared memory to fork-join parallelism (perhaps with OpenMP) or to its use within the BLAS does not address all these issues.

Keywords

Distribute Memory System Core Frequency Panel Factorization Dense Linear Algebra Math Software 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Dongarra, J.J., Luszczek, P., Petitet, A.: The LINPACK Benchmark: Past, Present, and Future. Concurrency and Computation: Practice and Experience 15(9), 803–820 (2003), http://www.netlib.org/benchmark/hpl/ CrossRefGoogle Scholar
  2. 2.
    Kurzak, J., Dongarra, J.J.: Implementation of Linear Algebra Routines with Lookahead - LU, Cholesky, QR. In: Workshop on State-of-the-Art in Scientific and Parallel Computing, June, 2006, Umea, Sweden (2006)Google Scholar
  3. 3.
    Post, D.E., Votta, L.G.: Computational Science Demands a New Paradigm. Physics Today 58(1), 35–41 (2005)CrossRefGoogle Scholar
  4. 4.
    Sutter, H.: The Free Lunch Is Over: A Fundamental Turn Toward Concurrency in Software. Dr. Dobb’s Journal 30(3) (March 2005)Google Scholar
  5. 5.
    Asanovic, K., et al.: The Landscape of Parallel Computing Research: A View from Berkeley, Electrical Engineering and Computer Sciences, University of California at Berkeley, Technical Report No. UCB/EECS-2006-183 (December 18, 2006), http://www.eecs.berkeley.edu/Pubs/TechRpts/2006/EECS-2006-183.html

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Alfredo Buttari
    • 1
  • Jack Dongarra
    • 1
    • 2
  • Jakub Kurzak
    • 1
  • Julien Langou
    • 3
  • Piotr Luszczek
    • 1
  • Stanimire Tomov
    • 1
  1. 1.Innovative Computing Laboratory, University of Tennessee Knoxville, TN 37996USA
  2. 2.Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge National Laboratory, TN 37831USA
  3. 3.Department of Mathematical Sciences, University of Colorado at Denver and Health Sciences Center, Campus Box 170, P.O. Box 173364, CO 80217-3364USA

Personalised recommendations