Abstract
The paper presents an efficient methodology for the parallel realization of FFT on multiprocessor architecture for larger data sets. FFT algorithm demands batch processing on data; large data sizes thus gives rise to performance related issues namely latency, execution time degradation triggered by cache misses, buffer management etc. The realization of FFT on multiprocessor platform presented here is based on two dimensional formulation, wherein an N point radix 2 FFT is re-ordered as a two dimensional matrix organization.The implementation employs data partitioning and parallelism so as to minimize the number of cache misses thereby ensuring cache friendliness.The implementation also employs parallel pipelined architecture. Parallel pipelined architecture and two dimensional formulation of FFT coupled with vectorization improves the performance figure of FFT realization of large data sets. A detailed analysis is presented in this paper.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Deb, D., Radhakrishna, P.: An Analysis Of Design Methodology Of Signal Processing Application On Multiprocessor Platform With Focus On Deterministic Execution Time And Algorithm Parallelizing. In: International Radar Symposium India (IRSI) Proceedings (December 2009)
Agarwal, R.C., Gustavson, F.G., Zubair, M.: A High Performance Parallel Algorithm for 1-D FFT. In: IEEE Proceedings. on SuperComputing, November 14-18, pp. 34–40 (1994)
Bhuyan, L.N., Agarwal, D.P.: Performance Analysis of FFT Algorithms on Multiprocessor Systems. IEEE Transactions on Software Engineering SE-9(4) (July 1983)
Abd-El-Barr, M., El-Rewini, H.: Fundamental of Computer Organization and Architecture. John Wiley & Sons Inc., Chichester (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Basil Morris, P.J., Chowdhury, S.R., Deb, D. (2011). An Efficent Methodology for Realization of Parallel FFT for Large Data Set. In: Abraham, A., Lloret Mauri, J., Buford, J.F., Suzuki, J., Thampi, S.M. (eds) Advances in Computing and Communications. ACC 2011. Communications in Computer and Information Science, vol 191. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-22714-1_59
Download citation
DOI: https://doi.org/10.1007/978-3-642-22714-1_59
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-22713-4
Online ISBN: 978-3-642-22714-1
eBook Packages: Computer ScienceComputer Science (R0)