On the performance of a highly-scalable Computational Fluid Dynamics code on AMD, ARM and Intel processors

TL;DR

This paper evaluates the performance and scalability of a state-of-the-art Computational Fluid Dynamics code across AMD, ARM, and Intel HPC clusters, revealing that AMD EPYC offers superior performance, while ARM-based systems show promising scalability.

Contribution

It provides a comparative analysis of CFD code performance on AMD, ARM, and Intel processors, highlighting the strengths and scalability of each architecture in HPC environments.

Findings

EPYC cluster outperforms others in all benchmarks.

Intel Skylake has better strong scalability.

ARM-based TX2 shows promising scalability.

Abstract

No area of computing is hungrier for performance than High Performance Computing (HPC), the demands of which continue to be a major driver for processor performance and adoption of accelerators, and also advances in memory, storage, and networking technologies. A key feature of the Intel processor domination of the past decade has been the extensive adoption of GPUs as coprocessors, whilst more recent developments have seen the increased availability of a number of CPU processors, including the novel ARM-based chips. This paper analyses the performance and scalability of a state-of-the-art Computational Fluid Dynamics (CFD) code on three HPC cluster systems equipped with AMD EPYC-Rome (EPYC, 4096 cores), ARM-based Marvell ThunderX2 (TX2, 8192 cores) and Intel Skylake (SKL, 8000 cores) processors. Three benchmark cases are designed with increasing computation-to-communication ratio and numerical complexity, namely lid-driven cavity flow, Taylor-Green vortex and a travelling solitary wave using the level-set method, adopted with $4^{th}$-order central-differences or a $5^{th}$-order WENO scheme. Our results show that the EPYC cluster delivers the best code performance for all the setups under consideration. In the first two benchmarks, the SKL cluster demonstrates faster computing times than the TX2 system, whilst in the solitary wave simulations, the TX2 cluster achieves good scalability and similar performance to the EPYC system, both improving on that obtained with the SKL cluster. These results suggest that while the Intel SKL cores deliver the best strong scalability, the associated cluster performance is lower compared to the EPYC system. The TX2 cluster performance is promising considering its recent addition to the HPC portfolio.