Abstract
We investigate the numerical computation of the matrix sign function of large-scale dense matrices. This is a common task in various application areas. The main computational work in Newton’s iteration for the matrix sign function consits of matrix inversion. Therefore, we investigate the performance of two approaches for matrix inversion based on Gaussian (LU factorization) and Gauss-Jordan eliminations. The target architecture is a current general-purpose multi-core processor connected to a graphics processor. Parallelism is extracted in both processors by linking sequential versions of the codes with multi-threaded implementations of BLAS. Our results on a system with two Intel QuadCore processors and an nvidia Tesla C1060 illustrate the performance and scalability attained by the codes on this system.
Chapter PDF
Similar content being viewed by others
Keywords
References
Golub, G., Loan, C.V.: Matrix Computations, 3rd edn. The Johns Hopkins University Press, Baltimore (1996)
Petkov, P., Christov, N., Konstantinov, M.: Computational Methods for Linear Control Systems. Prentice Hall, Hertfordshire (1991)
Frommer, A., Lippert, T., Medeke, B., Schilling, K. (eds.): Numerical Challenges in Lattice Quantum Chromodynamics. Lecture Notes in Computational Science and Engineering, vol. 15. Springer, Heidelberg (2000)
Byers, R.: Solving the algebraic Riccati equation with the matrix sign function. Linear Algebra Appl. 85, 267–279 (1987)
IMTEK, Oberwolfach model reduction benchmark collection, http://www.imtek.de/simulation/benchmark/
Benner, P., Quintana-Ortí, E.: Solving stable generalized Lyapunov equations with the matrix sign function. Numer. Algorithms 20, 75–100 (1999)
Benner, P., Claver, J., Quintana-Ortí, E.: Parallel distributed solvers for large stable generalized Lyapunov equations. Parallel Processing Letters 9, 147–158 (1999)
Benner, P., Quintana-Ortí, E., Quintana-Ortí, G.: A portable subroutine library for solving linear control problems on distributed memory computers. In: Cooperman, G., Jessen, E., Michler, G. (eds.) Workshop on Wide Area Networks and High Performance Computing, Essen (Germany), September 1998. Lecture Notes in Control and Information, pp. 61–88. Springer, Heidelberg (1999)
Benner, P., Quintana-Ortí, E., Quintana-Ortí, G.: State-space truncation methods for parallel model reduction of large-scale systems. Parallel Comput. 29, 1701–1722 (2003)
Benner, P., Quintana-Ortí, E., Quintana-Ortí, G.: Solving linear-quadratic optimal control problems on parallel computers. Optimization Methods & Software 23, 879–909 (2008)
Lawson, C.L., Hanson, R.J., Kincaid, D.R., Krogh, F.T.: Basic linear algebra subprograms for Fortran usage. ACM Trans. Math. Soft. 5, 308–323 (1979)
Dongarra, J.J., Croz, J.D., Hammarling, S., Hanson, R.J.: An extended set of FORTRAN basic linear algebra subprograms. ACM Trans. Math. Soft. 14, 1–17 (1988)
Dongarra, J.J., Croz, J.D., Hammarling, S., Duff, I.: A set of level 3 basic linear algebra subprograms. ACM Trans. Math. Soft. 16, 1–17 (1990)
Anderson, E., Bai, Z., Demmel, J., Dongarra, J.E., DuCroz, J., Greenbaum, A., Hammarling, S., McKenney, A.E., Ostrouchov, S., Sorensen, D.: LAPACK Users’ Guide. SIAM, Philadelphia (1992)
Gerbessiotis, A.V.: Algorithmic and Practical Considerations for Dense Matrix Computations on the BSP Model. PRG-TR 32, Oxford University Computing Laboratory (1997)
Gunnels, J.A., Gustavson, F.G., Henry, G.M., van de Geijn, R.A.: FLAME: Formal linear algebra methods environment. ACM Trans. Math. Soft. 27, 422–455 (2001)
Bientinesi, P., Gunnels, J.A., Myers, M.E., Quintana-Ortí, E.S., van de Geijn, R.A.: The science of deriving dense linear algebra algorithms. ACM Trans. Math. Soft. 31, 1–26 (2005)
University of Texas, http://www.cs.utexas.edu/~flame/
Quintana-Ortí, E., Quintana-Ortí, G., Sun, X., van de Geijn, R.: A note on parallel matrix inversion. SIAM J. Sci. Comput. 22, 1762–1771 (2001)
Texas Advanced Computing Center, http://www.tacc.utexas.edu/~kgoto/
Intel Corporation, http://www.intel.com/
Nvidia Corporation, http://www.nvidia.com/cuda/
Nicholas, J.N.: Accuracy and stability of numerical algorithms, Philadelphia, PA, USA (1996)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Benner, P., Ezzatti, P., Quintana-Ortí, E.S., Remón, A. (2010). Using Hybrid CPU-GPU Platforms to Accelerate the Computation of the Matrix Sign Function. In: Lin, HX., et al. Euro-Par 2009 – Parallel Processing Workshops. Euro-Par 2009. Lecture Notes in Computer Science, vol 6043. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-14122-5_17
Download citation
DOI: https://doi.org/10.1007/978-3-642-14122-5_17
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-14121-8
Online ISBN: 978-3-642-14122-5
eBook Packages: Computer ScienceComputer Science (R0)