Abstract
We propose general static block and block-cyclic heterogeneous decomposition of multidimensional data over processes of parallel program mapped onto multidimensional process grid. The decomposition is compared with decomposition of two-dimensional data over two-dimensional process grid of Beaumont et al and with natural decomposition of three-dimensional data over three-dimensional process grid.
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
Beaumont, O., Boudet, V., Petitet, A., Rastello, F., Robert, Y.: A Proposal for a Heterogeneous Cluster ScaLAPACK (Dense Linear Solvers). IEEE Trans. Computers. 50(10), 1052–1070 (2001)
Dovolnov, Y., Kalinov, A., Klimov, S.: Natural Block Data Decomposition for Heterogeneous Clusters. In: Proceedings of HCW 2003, April 22, 2003, IEEE CS Press, Nice (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kalinov, A., Klimov, S. (2004). Multidimensional Static Block Data Decomposition for Heterogeneous Clusters. In: Wyrzykowski, R., Dongarra, J., Paprzycki, M., Waśniewski, J. (eds) Parallel Processing and Applied Mathematics. PPAM 2003. Lecture Notes in Computer Science, vol 3019. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24669-5_117
Download citation
DOI: https://doi.org/10.1007/978-3-540-24669-5_117
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-21946-0
Online ISBN: 978-3-540-24669-5
eBook Packages: Springer Book Archive