Abstract
With the increasing use of large image and video archives and high-resolution multimedia data streams in many of today’s research and application areas, there is a growing need for multimedia-oriented high-performance computing. As a consequence, a need for algorithms, methodologies, and tools that can serve as support in the (automatic) parallelization of multimedia applications is rapidly emerging.
This paper discusses the parallelization of Householder bidiagonalization, a matrix factorization method which is an integral part of full Singular Value Decomposition (SVD) — an important algorithm for many multimedia problems. Householder bidiagonalization is hard to parallelize efficiently because the total number of matrix elements taking part in the calculations reduces during runtime. To overcome the growing negative performance impact of load imbalances and overprovisioning of compute resources, we apply adaptive runtime techniques of periodic matrix remapping and process reduction for improved performance. Results show that our adaptive parallel execution approach provides a significant improvement in efficiency, even when applying a set of compute resources which is (initially) very large.
This research is supported by the Netherlands Organization for Scientific Research (NWO) under NWO-GLANCE grant no. 643.000.602.
Chapter PDF
Similar content being viewed by others
Keywords
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.
References
Seinstra, F., et al.: High-Performance Distributed Video Content Analysis with Parallel-Horus. IEEE Multimedia 14(4), 64–75 (2007)
Chu, E., George, J.: Gaussian Elimination with Partial Pivoting and Load Balancing on a Multiprocessor. Parallel Computing 5(1), 65–74 (1987)
Dongarra, J., Sorensen, D.: A Fully Parallel Algorithm for the Symmetric Eigenvalue Problem. SIAM J. Sci. Stat. Comput. 8(2), 139–154 (1987)
Egecioglu, O., et al.: Givens and Householder Reductions for Linear Least Squares on a Cluster of Workstations. In: Proc. HiPC 1995, December 1995, pp. 734–739 (1995)
Groser, B., Lang, B.: Efficient Parallel Reduction to Bidiagonal Form. Parallel Computing 25(8), 969–986 (1999)
Rabani, E., Toledo, S.: Out-of-core SVD and QR Decompositions. In: Proceedings of PPSC 2001, Portsmouth, USA (March 2001)
Koelma, D., et al.: Horus C++ Reference, v. 1.1. Technical report, University of Amsterdam, The Netherlands (January 2002)
Morrow, P., et al.: Efficient Implementation of a Portable Parallel Programming Model for Image Processing. Concur. Pract. Exp. 11, 671–685 (1999)
Seinstra, F., et al.: User Transparent Parallel Processing of the 2004 NIST TRECVID Data Set. In: Proceedings of IPDPS 2005, Denver, USA (April 2005)
Snoek, C., et al.: The Semantic Pathfinder: Using an Authoring Metaphor for Ge- neric Multimedia Indexing. IEEE Trans. Pat. Anal. Mach. Intel. 28(10), 1678–1689 (2006)
Snoek, C., et al.: MediaMill: Exploring News Video Archives based on Learned Semantics. In: ACM Multimedia 2005, Singapore (November 2005)
Geusebroek, J., Seinstra, F.: Color-Based Object Recognition by a Grid-Connected Robot Dog. In: AAAI 2007 - Video Competition, Vancouver, Canada (July 2007)
Seinstra, F., et al.: Scalable Wall-Socket Multimedia Grid Computing, First IEEE International Scalable Computing Challenge, First Prize Winner (May 2008)
Golub, G., Reinsch, C.: Singular Value Decomposition and Least Squares Solutions. Numerische Mathematik 14(5), 403–420 (1970)
Evans, D., Gusev, M.: Systolic SVD and QR Decomposition by Householder Reflections. Int. J. Comp. Math. 79(4), 417–439 (2002)
Seinstra, F., et al.: Finite State Machine-Based Optimization of Data Parallel Regular Domain Problems Applied in Low-Level Image Processing. IEEE Transactions on Parallel and Distributed Systems 15(10), 865–877 (2004)
Seinstra, F., et al.: A Software Architecture for User Transparent Parallel Image Processing. Parallel Computing 28(7-8), 967–993 (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Liu, F., Seinstra, F.J. (2009). Adaptive Parallel Householder Bidiagonalization. In: Sips, H., Epema, D., Lin, HX. (eds) Euro-Par 2009 Parallel Processing. Euro-Par 2009. Lecture Notes in Computer Science, vol 5704. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-03869-3_76
Download citation
DOI: https://doi.org/10.1007/978-3-642-03869-3_76
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-03868-6
Online ISBN: 978-3-642-03869-3
eBook Packages: Computer ScienceComputer Science (R0)