Cart (Loading....) | Create Account
Close category search window
 

High-performance linear algebra algorithms using new generalized data structures for matrices

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $31
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

1 Author(s)
Gustavson, F.G. ; IBM Research Division, Thomas J. Watson Research Center, P.O. Box 218, Yorktown Heights, New York 10598, USA

We present a novel way to produce dense linear algebra factorization algorithms. The current state-of-the-art (SOA) dense linear algebra algorithms have a performance inefficiency, and thus they give suboptimal performance for most LAPACK factorizations. We show that using standard Fortran and C two-dimensional arrays is the main source of this inefficiency. For the other standard format (packed one-dimensional arrays for symmetric and/or triangular matrices), the situation is much worse. We show how to correct these performance inefficiencies by using new data structures (NDS) along with so-called kernel routines. The NDS generalize the current storage layouts for both standard formats. We use the concept of Equivalence and Elementary Matrices along with coordinate (linear) transformations to prove that our method works for an entire class of dense linear algebra algorithms. Also, we use the Algorithms and Architecture approach to explain why our new method gives higher efficiency. The simplest forms of the new factorization algorithms are a direct generalization of the commonly used LINPACK algorithms. On IBM platforms they can be generated from simple, textbook-type codes by the XLF Fortran compiler. On the IBM POWER3 processor, our implementation of Cholesky factorization achieves 92% of peak performance, whereas conventional SOA full-format LAPACK DPOTRF achieves 77% of peak performance. All programming for our NDS can be accomplished in standard Fortran through the use of three- and four-dimensional arrays. Thus, no new compiler support is necessary. Finally, we describe block hybrid formats (BHF). BHF allow one to use no additional storage over conventional (full and packed) matrix storage. This means that new algorithms based on BHF can be used as a backward-compatible replacement for LAPACK or LINPACK algorithms.

Note: The Institute of Electrical and Electronics Engineers, Incorporated is distributing this Article with permission of the International Business Machines Corporation (IBM) who is the exclusive owner. The recipient of this Article may not assign, sublicense, lease, rent or otherwise transfer, reproduce, prepare derivative works, publicly display or perform, or distribute the Article.  

Published in:

IBM Journal of Research and Development  (Volume:47 ,  Issue: 1 )

Date of Publication:

Jan. 2003

Need Help?


IEEE Advancing Technology for Humanity About IEEE Xplore | Contact | Help | Terms of Use | Nondiscrimination Policy | Site Map | Privacy & Opting Out of Cookies

A not-for-profit organization, IEEE is the world's largest professional association for the advancement of technology.
© Copyright 2014 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.