Abstract
Many computationally intensive physics problems spend the majority of their time in multidimensional Fast Fourier Transforms. A case study for the IBM SP is presented based on an algorithm for sound propagation through a finite inhomogeneous medium. Techniques for improving the serial and parallel efficiency of such codes is described, and the use of software tools to aid the process are illustrated.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Bojarski, N. (1985). The k-space formulation of the scattering problem in the time domain: An improved single propagator formulation. J. Acoust. Soc. Am., 77(3):826–831
Foster, I. and Worley, P. (1997). Parallel algorithms for the spectral transform method. SIAM J. Sci. Comput., 18(3): 806–837.
Liu, D. and Waag, R. (1997). Solving the forward scattering problem by the k-space method. report draft.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1998 Springer Science+Business Media New York
About this chapter
Cite this chapter
Zollweg, J.A. (1998). Parallel Performance of a Code Using Multidimensional FFTs. In: Schaeffer, J. (eds) High Performance Computing Systems and Applications. The Springer International Series in Engineering and Computer Science, vol 478. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-5611-4_7
Download citation
DOI: https://doi.org/10.1007/978-1-4615-5611-4_7
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-7567-8
Online ISBN: 978-1-4615-5611-4
eBook Packages: Springer Book Archive