|
This article is cited in 5 scientific papers (total in 5 papers)
Performance of Elbrus-8C processor in supercomputer CFD simulations
A. V. Gorobetsa, M. I. Neiman-zadeb, S. K. Okunevb, A. A. Kalyakinb, S. A. Soukova a Keldysh Institute of Applied Mathematics of RAS, Moscow
b MCST, Moscow
Abstract:
The present work is devoted to performance evaluation of a multicore CPU Elbrus-8C in supercomputer computational fluid dynamics (CFD) applications. Parallel simulation codes based on higher-accuracy methods on unstructured meshes for modelling of turbulent flows are considered. Main features of the Elbrus architecture are described, approaches for adaptation and optimization of computing software are presented. Performance has been investigated for the whole algorithms and for their main operations separately. Benchmarking results in comparison with various Intel and AMD multicore CPUs are presented.
Keywords:
CFD, HPC, Elbrus processor, supercomputer simulations, performance.
Received: 09.08.2018 Revised: 09.08.2018 Accepted: 22.10.2018
Citation:
A. V. Gorobets, M. I. Neiman-zade, S. K. Okunev, A. A. Kalyakin, S. A. Soukov, “Performance of Elbrus-8C processor in supercomputer CFD simulations”, Matem. Mod., 31:4 (2019), 17–32; Math. Models Comput. Simul., 11:6 (2019), 914–923
Linking options:
https://www.mathnet.ru/eng/mm4062 https://www.mathnet.ru/eng/mm/v31/i4/p17
|
Statistics & downloads: |
Abstract page: | 371 | Full-text PDF : | 202 | References: | 64 | First page: | 13 |
|