Abstract
This work describes the optimization process to improve the performance from a convection-diffusion equation from the HOPMOC method, on the Xeon architecture through the help Intel (r) tools, Vtune Amplifier, Compiler Reports and Intel Advisor. HOPMOC is a finite diffrence method to solve parabolic equations with convective dominance on a cluster with multiple multicore nodes. The method is based both on the modified method of characteristics and the Hopscotch method, it is implemented through an explicit-implicit operator splitting technique. This work studies the vectorization and parallelization version from HOPMOC under a Xeon processor architecture, and shows performance improvements up to 2 times per core, due to optimization via vectorization techniques and a gain up to 30 times on a 54 core environment, due to parallel strategies, compared to the sequential code.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Kischinhevsky, M.: An Operator Splitting for Optimal Message-passing Computation of Parabolic Equation with Hyperbolic Dominance. SIAM Annual Meeting, Missouri (1996)
Boonkkamp, J.H.M.T.J., Verwer, J.G.: On the odd-even hopscotch scheme for the numerical integration of time-dependent partial differential equations. Appl. Num. Math. 3(1), 183–193 (1987)
Hansen, J.P., Matthey, T., Sørevik, T.: A parallel split operator method for the time dependent Schrödinger equation. In: Dongarra, J., Laforenza, D., Orlando, S. (eds.) EuroPVM/MPI 2003. LNCS, vol. 2840, pp. 503–510. Springer, Heidelberg (2003)
Yanenko, N.N.: The Method of Fractional Steps. Springer, New York (1970)
Li, D., Zhou, Z., Wang, Q.: A hybrid MPI/OpenMP based on DDM for large-scale partial differential equations. In: IEEE 11th International Conference on Trust, Security and Privacy in Computing and Communications, Liverpool, pp. 1839–1843 (2012)
Jin, H., Jespersen, D., Mehrotra, P., Biswas, R., Huang, L., Chapman, B.: High performance computing using MPI and OpenMP on multi-core parallel systems. Parallel Comput. 37(9), 562–575 (2011)
Mininni, P.D., Rosenberg, D., Reddy, R., Poquet, A.: A hybrid MPI-OpenMP scheme for scalable parallel pseudospectral computations for fluid turbulence. Parallel Comput. 37, 316–326 (2011)
Kirk, D.B., Hwu, W.W.: Programming Massively Parallel Processors: A Hands-on Approach. Elsevier Inc., Philadelphia (2010)
Kischinhevsky, M.: A spatially decoupled alternating direction procedure for convection-diffusion equations. In: Proceedings of the XXth CILAMCE-Iberian Latin American Congress on Numerical Methods in Engineearing (1999)
Oliveira, S., Gonzaga, S.L., Kischinhevsky, M.: Convergence analysis of the HOPMOC method. Int. J. Comput. Math. 86, 1375–1393 (2009)
Cabral, F.L.: HOPMOC methods to solve convection-diffusion equations and its parallel implementation (in Portuguese). Master thesis, Instituto de Computação/Universidade Federal Fluminense, Brasil (2001)
Richtmyer, R.D., Morton, K.W.: Difference Methods for Initial-Value Problems Interscience. Interscience, New York (1967)
Harten, A.: On a class of high resolution total-variation-stable finite-difference schemes. SIAM J. Numer. Anal. 21, 1–23 (1984)
Rabeinsefner, R., Hager, G., Jost, G.: Hybrid MPI/OpenMP parallel programming on clusters of molti-core SMP nodes. In: 2009 17th Euromicro International Conference on Parallel, Distributed and Network-based Processing, pp. 427–436 (2009)
Cluster OpemMP for Intel Compilers. http://software.intel.com/en-us/articles/cluster-openmp-for-intel-compilers
Klemm, M., Duran, A., Tian, X., Saito, H., Caballero, D., Martorell, X.: Extending OpenMP* with vector constructs for modern multicore SIMD architectures. In: Chapman, B.M., Massaioli, F., Müller, M.S., Rorro, M. (eds.) IWOMP 2012. LNCS, vol. 7312, pp. 59–72. Springer, Heidelberg (2012)
Cabral, F.L., Osthoff, C., Kischinhevsky, M., Brandão. D.: Hybrid MPI/OpenMP/OpenACC Implementations for the Solution of Convection-Diffusion Equations with the HOPMOC Method. In: Proceedings of XXIV International Conference on Computational Science and Its Applications (2014)
Acknowledgments
This project was partially supported by cooperation agreement between LNCC and Intel Corporation.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Cabral, F.L., Osthoff, C., Brandão, D., Kischinhevsky, M. (2015). Fine-Tuning Xeon Architecture Vectorization and Parallelization of a Numerical Method for Convection-Diffusion Equations. In: Osthoff, C., Navaux, P., Barrios Hernandez, C., Silva Dias, P. (eds) High Performance Computing. CARLA 2015. Communications in Computer and Information Science, vol 565. Springer, Cham. https://doi.org/10.1007/978-3-319-26928-3_10
Download citation
DOI: https://doi.org/10.1007/978-3-319-26928-3_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-26927-6
Online ISBN: 978-3-319-26928-3
eBook Packages: Computer ScienceComputer Science (R0)