Strong Scaling of OpenACC enabled Nek5000 on several GPU based HPC systems

TL;DR

This paper demonstrates the strong parallel scaling of an OpenACC-accelerated Nek5000 fluid dynamics solver on multiple GPU-based HPC systems, achieving significant speed-ups and illustrating high throughput potential for turbulent flow simulations.

Contribution

It provides new strong scaling results for GPU-accelerated Nek5000 across various HPC systems, highlighting improved performance and scalability compared to CPU implementations.

Findings

GPU version achieves 3-5x speed-up over CPU

Run-time for 20 timesteps reduces from 43.5 to 13.2 seconds with more GPUs

GPU strong scaling limit is significantly larger (2000-5000 elements per rank) than CPU (50-100)

Abstract

We present new results on the strong parallel scaling for the OpenACC-accelerated implementation of the high-order spectral element fluid dynamics solver Nek5000. The test case considered consists of a direct numerical simulation of fully-developed turbulent flow in a straight pipe, at two different Reynolds numbers $Re_\tau=360$ and $Re_\tau=550$, based on friction velocity and pipe radius. The strong scaling is tested on several GPU-enabled HPC systems, including the Swiss Piz Daint system, TACC's Longhorn, J\"ulich's JUWELS Booster, and Berzelius in Sweden. The performance results show that speed-up between 3-5 can be achieved using the GPU accelerated version compared with the CPU version on these different systems. The run-time for 20 timesteps reduces from 43.5 to 13.2 seconds with increasing the number of GPUs from 64 to 512 for $Re_\tau=550$ case on JUWELS Booster system. This illustrates the GPU accelerated version the potential for high throughput. At the same time, the strong scaling limit is significantly larger for GPUs, at about $2000-5000$ elements per rank; compared to about $50-100$ for a CPU-rank.