Direct Numerical Simulation of Stratified Turbulent Flows and Passive Tracer Transport on HPC Systems: Comparison of CPU Architectures

被引：0

作者：

Mortikov E.V. ^{[1
,2
,3
]}

Debolskiy A.V. ^{[1
,3
,4
]}

机构：

[1] Lomonosov Moscow State University Research Computing Center, Moscow

[2] Marchuk Institute of Numerical Mathematics RAS, Moscow

[3] Moscow Center of Fundamental and Applied Mathematics, Moscow

[4] A.M. Obukhov Institute of Atmospheric Physics RAS, Moscow

来源：

Supercomputing Frontiers and Innovations | 2021年 / 8卷 / 04期

基金：

俄罗斯科学基金会;

关键词：

Arm; Direct numerical simulation; Supercomputing; Turbulence;

D O I：

10.14529/JSFI210405

中图分类号：

学科分类号：

摘要：

In this paper we assess the influence of CPU architectures commonly used in HPC systems on the efficiency of the implementation of algorithms used for direct numerical simulation (DNS) of turbulent flows. We consider a stably stratified turbulent plane Couette flow as a benchmark problem supplemented with the additional transport of passive substances. The comparison includes the Intel Xeon, AMD Rome x86 CPU architecture processors and the Huawei Kunpeng ARM CPU processor. We discuss the role of memory-oriented optimizations on the efficiency of tracer transport implementation on each platform. © The Authors 2021. This paper is published with open access at SuperFri.org

引用

页码：50 / 68

页数：18

共 31 条

[1]

Afanasyev I., Lichmanov D., Evaluating the performance of Kunpeng 920 processors on modern HPC applications, Parallel Computing Technologies 2021, Proceedings, pp. 301-321, (2021)

[2]

Ayala A., Tomov S., Haidar A., Dongarra J., heFFTe: Highly efficient FFT for exascale, Computational Science — ICCS 2020. ICCS 2020. Lecture Notes in Computer Science, pp. 262-275, (2020)

[3]

Besnard J., Malony A., Shende S., Et al., An MPI halo-cell implementation for zero-copy abstraction, EuroMPI ’15: Proceedings of the 22nd European MPI Users’ Group Meeting, pp. 1-9, (2015)

[4]

Brown D., Cortez R., Minion M., Accurate projection methods for the incompressible Navier-Stokes equations, J. Comp. Phys, 168, pp. 464-499, (2001)

[5]

Dongarra J., Heroux M., Luszczek P., A new metric for ranking high performance computing systems, Nat. Sci. Rev, 3, 1, pp. 30-35, (2016)

[6]

Gladskikh D., Stepanenko V., Mortikov E., The effect of the horizontal dimensions of inland water bodies on the thickness of the upper mixed layer, Water Res, 48, pp. 226-234, (2021)

[7]

Glazunov A., Mortikov E., Barskov K., Et al., Layered structure of stably stratified turbulent shear flows, Izv., Atmos. Ocean. Phys, 55, 4, pp. 312-323, (2019)

[8]

Ibeid H., Olson L., Gropp W., FFT, FMM, and multigrid on the road to exascale: Performance challenges and opportunities, J. Parallel Distrib. Comput, 136, pp. 63-74, (2020)

[9]

Kadantsev E., Mortikov E., Zilitinkevich S., The resistance law for stably stratified atmospheric planetary boundary layers, Q. J. R. Meteorol. Soc, 147, 737, pp. 2233-2243, (2021)

[10]

Larsson J., Lien F., Yee E., Conditional semicoarsening multigrid algorithm for the Poisson equation on anisotropic grids, J. Comp. Phys, 208, pp. 368-383, (2005)

← 1 2 3 4 →