Abstract

Abstract. A study of the scalability of the Finite-volumE Sea ice–Ocean circulation Model, Version 2.0 (FESOM2), the first mature global model of its kind formulated on unstructured meshes, is presented. This study includes an analysis of the main computational kernels with a special focus on bottlenecks in parallel scalability. Several model enhancements improving this scalability for large numbers of processes are described and tested. Model grids at different resolutions are used on four high-performance computing (HPC) systems with differing computational and communication hardware to demonstrate the model's scalability and throughput. Furthermore, strategies for improvements in parallel performance are presented and assessed. We show that, in terms of throughput, FESOM2 is on a par with state-of-the-art structured ocean models and, in a realistic eddy-resolving configuration (1/10∘ resolution), can achieve about 16 years per day on 14 000 cores. This suggests that unstructured-mesh models are becoming very competitive tools in high-resolution climate modeling. We show that the main bottlenecks of FESOM2 parallel scalability are the two-dimensional components of the model, namely the computations of the external (barotropic) mode and the sea-ice model. It is argued that these bottlenecks are shared with other general ocean circulation models.

Highlights

  • Mesoscale eddies play a critical role in the general circulation of the ocean, strongly affect biogeochemical processes, and impact marine life

  • In terms of throughput, FESOM2 is on a par with state-of-the-art structured ocean models and, in a realistic eddy-resolving configuration (1/10◦ resolution), can achieve about 16 years per day on 14 000 cores

  • We systematically explored the scalability of FESOM2 for a set of meshes (0.13 million, 0.64 million, and 5.6 million surface vertices, 47 layers) on several high-performance computing (HPC) systems and found a nearly linear scalability of FESOM2 code to the limit of 300–400 surface mesh vertices per core

Read more

Summary

Introduction

Mesoscale eddies play a critical role in the general circulation of the ocean, strongly affect biogeochemical processes, and impact marine life. The main components of ocean circulation models limiting their scalability have been identified in the literature as the solver for the external (barotropic) mode (e.g., Huang et al, 2016; Prims et al, 2018) and the sea-ice model (e.g., Prims et al, 2018) They represent two-dimensional (2-D) stiff parts of the solution algorithm and require either linear solvers (usually iterative) or explicit pseudo-time-stepping with very small time steps (see the split-explicit method for the barotropic dynamic in Shchepetkin and McWilliams (2005) or elastic–viscous–plastic method for the sea ice in Hunke and Dukowicz (1997)). A discussion of results and strategies for future improvements of the parallel scaling of FESOM2 is presented in Sect. 6, followed by a brief conclusions section

Governing equations and solution procedure
Test cases and HPC systems used in the study
Scaling tests
Parallel code analysis using Intel Trace Analyzer and Collector
Overlapping computation with communication in the BiCGStab solver for the SSH
Speeding up the sea-ice model
Testing throughput in an operational configuration
Hierarchic mesh partitioning
Improving the network performance by underpopulating compute nodes
SSH strategy
Sea-ice model strategy
Need for more efficient 2-D computations
Conclusions
Sea surface height equation
Findings
Sea-ice dynamics equations
Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.