Performance of an Astrophysical Radiation Hydrodynamics Code under Scalable Vector Extension Optimization

TL;DR

This study evaluates the performance of the astrophysical radiation hydrodynamics code V2D on Fujitsu's A64FX processor, revealing mixed results with SVE optimization and highlighting the need for deeper analysis.

Contribution

It provides an initial performance analysis of V2D on A64FX, demonstrating potential speedups with SVE and identifying areas for further optimization.

Findings

Simple sparse linear algebra routines showed significant speedup with SVE.

V2D's performance did not meet expectations under SVE optimization.

Further detailed analysis of the code is recommended.

Abstract

We present results of a performance study of an astrophysical radiation hydrodynamics code, V2D, on the Arm-based A64FX processor developed by Fujitsu. The code solves sparse linear systems, a task for which the A64FX architecture should be well suited. We performed the performance analysis study on Ookami, an Apollo 80 platform utilizing the A64FX processor. We explored several compilers and performance analysis packages and found the code did not perform as expected under scalable vector extension optimization, suggesting that a "deeper dive" into analyzing the code is worthwhile. However, a simple driver program that exercised basic sparse linear algebra routines used by V2D did show significant speedup with the use of the scalable vector extension optimization. We present the initial results from the study which used V2D on a relatively simple test problem that emphasized the repeated solution of sparse linear systems.