Highly scalable computational algorithms on emerging parallel machine multicore architectures: development and implementation in CFD context

• Published in: International journal for numerical methods in fluids Vol. 73; no. 10; pp. 869 - 882
• Main Authors: Kannan, R., Harrand, V., Lee, M., Przekwas, A. J.
• Format: Journal Article
• Language: English
• Published: Bognor Regis Blackwell Publishing Ltd 10.12.2013; Wiley Subscription Services, Inc
• Subjects: Algorithms; Categories; communication; Computation; Computational fluid dynamics; Computer simulation; HPC; Mathematical models; memory management; multicore; Partitioning; Partitions
• ISSN: 0271-2091; 1097-0363
• DOI: 10.1002/fld.3827

SUMMARYIn this paper, the first in a series, the authors have developed and implemented new computational algorithms for improving the scalability of CFD simulations on emerging architectures such as multicore high performance computing (HPC) platforms. These algorithmic developments and implementations are classified into three categories: (i) improved partition for multicore platforms, (ii) improved and optimized communication for HPC and (iii) enhancing scalability using computer science based methods. In the first category, the multilevel partitioning strategy was modified to reduce the number of out‐of‐core communications. This resulted in noticeable speedup even for small cases. In the second category, the authors came up with a next generation communication procedure optimized for the architecture and the partitioning. This next generation communication resulted in noticeable speedups. In the third category, improvements with respect to better management of memory were implemented. This again resulted in a speedup of nearly 10%. The overall scalability, as a result of the three algorithmic implementations, yielded ideal and at times superlinear scalability until 3000 processors. In general, the scalability results are very promising and indicate that the approach has a great potential for more complicated multidisciplinary problems such as fluid–structure interaction and aeroelastic simulations. Copyright © 2013 John Wiley & Sons, Ltd. This figure shows the scalability plot as a function of the number of partitions for both communication paradigms. PETSc refers to the original generic communication pattern (as employed by PETSc), the newly developed communication is ‘optimized communication’.