Abstract
High performance of data-parallel applications on heterogeneous platforms can be achieved by partitioning the data in proportion to the speeds of processors. It has been proven that the speed functions built from a history of time measurements better reflect different aspects of heterogeneity of processors. However, existing data partitioning algorithms based on functional performance models impose some restrictions on the shape of speed functions, which are not always satisfied if we try to approximate the real-life measurements accurately enough. This paper presents a new data partitioning algorithm that applies multidimensional solvers to numerical solution of the system of non-linear equations formalizing the problem of optimal data partitioning. This algorithm relaxes the restrictions on the shape of speed functions and uses the Akima splines for more accurate and realistic approximation of the real-life speed functions. The better accuracy of the approximation in its turn results in a more optimal distribution of the computational load between the heterogeneous processors.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Lastovetsky, A., Reddy, R.: Data Partitioning with a Functional Performance Model of Heterogeneous Processors. Int. J. High Perform. Comput. Appl. 21, 76–90 (2007)
Lastovetsky, A., Reddy, R., Higgins, R.: Building the Functional Performance Model of a Processor. In: SAC 2006, pp. 746–753. ACM, New York (2006)
Lastovetsky, A., Reddy, R.: Distributed data partitioning for heterogeneous processors based on partial estimation of their functional performance models. In: Lin, H.-X., Alexander, M., Forsell, M., Knüpfer, A., Prodan, R., Sousa, L., Streit, A. (eds.) Euro-Par 2009. LNCS, vol. 6043, pp. 91–101. Springer, Heidelberg (2010)
Powell, M.J.D.: A Hybrid Method for Nonlinear Equations. In: Gordon, Breach (eds.) Numerical Methods for Nonlinear Algebraic Equations, pp. 87–114 (1970)
Akima, H.: A New Method of Interpolation and Smooth Curve Fitting Based on Local Procedures. J. ACM 17, 589–602 (1970)
Powell, M.J.D.: A Fortran Subroutine for Solving Systems on Nonlinear Algebraic Equations. In: Gordon, Breach (eds.) Numerical Methods for Nonlinear Algebraic Equations, pp. 115–161 (1970)
Bahi, J.M., Contassot-Vivier, S., Couturier, R.: Dynamic Load Balancing and Efficient Load Estimators for Asynchronous Iterative Algorithms. IEEE T. Parall. Distr. 16, 289–299 (2005)
Martínez, J.A., Garzón, E.M., Plaza, A., García, I.: Automatic tuning of iterative computation on heterogeneous multiprocessors with ADITHE. J. Supercomput.,1–9 (November 2009)
Galindo, I., Almeida, F., Badía-Contelles, J.M.: Dynamic load balancing on dedicated heterogeneous systems. In: Lastovetsky, A., Kechadi, T., Dongarra, J. (eds.) EuroPVM/MPI 2008. LNCS, vol. 5205, pp. 64–74. Springer, Heidelberg (2008)
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
Rychkov, V., Clarke, D., Lastovetsky, A. (2011). Using Multidimensional Solvers for Optimal Data Partitioning on Dedicated Heterogeneous HPC Platforms. In: Malyshkin, V. (eds) Parallel Computing Technologies. PaCT 2011. Lecture Notes in Computer Science, vol 6873. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-23178-0_29
Download citation
DOI: https://doi.org/10.1007/978-3-642-23178-0_29
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-23177-3
Online ISBN: 978-3-642-23178-0
eBook Packages: Computer ScienceComputer Science (R0)