Fine-Tuning Xeon Architecture Vectorization and Parallelization of a Numerical Method for Convection-Diffusion Equations

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.

[1]  Alejandro Duran,et al.  Extending OpenMP* with Vector Constructs for Modern Multicore SIMD Architectures , 2012, IWOMP.

[2]  Y. Raghu Reddy,et al.  A hybrid MPI-OpenMP scheme for scalable parallel pseudospectral computations for fluid turbulence , 2010, Parallel Comput..

[3]  Sanderson L. Gonzaga de Oliveira,et al.  Convergence analysis of the Hopmoc method , 2009, Int. J. Comput. Math..

[4]  N. N. Yanenko,et al.  The Method of Fractional Steps , 1971 .

[5]  Jan Verwer,et al.  On the odd-even hopscotch scheme for the numerical integration of time-dependent partial differential equations , 1987 .

[6]  Thierry Matthey,et al.  A Parallel Split Operator Method for the Time Dependent Schrödinger Equation , 2003, PVM/MPI.

[7]  Georg Hager,et al.  Hybrid MPI/OpenMP Parallel Programming on Clusters of Multi-Core SMP Nodes , 2009, 2009 17th Euromicro International Conference on Parallel, Distributed and Network-based Processing.

[8]  Zhangbing Zhou,et al.  A Hybrid MPI/OpenMP Model Based on DDM for Large-Scale Partial Differential Equations , 2012, 2012 IEEE 11th International Conference on Trust, Security and Privacy in Computing and Communications.

[9]  A. Harten,et al.  On a Class of High Resolution Total-Variation-Stable Finite-Difference Schemes , 2017 .

[10]  Rupak Biswas,et al.  High performance computing using MPI and OpenMP on multi-core parallel systems , 2011, Parallel Comput..

[11]  Diego N. Brandão,et al.  Hybrid MPI/OpenMP/OpenACC Implementations for the Solution of Convection-Diffusion Equations with the HOPMOC Method , 2014, 2014 14th International Conference on Computational Science and Its Applications.