SYCL for Energy-Efficient Numerical Astrophysics: the case of DPEcho

TL;DR

This paper demonstrates how SYCL can be used to evaluate energy efficiency in numerical astrophysics applications across heterogeneous hardware, aiding informed hardware choices and emphasizing the importance of energy-aware KPIs.

Contribution

It introduces a portable, vendor-agnostic approach using the DPEcho SYCL benchmark to compare energy efficiency and performance across hardware for astrophysical computations.

Findings

GPUs offer higher energy efficiency for astrophysics workloads.

Energy-aware KPIs provide more informative device performance insights.

The developed energy-measuring pipeline is flexible and cross-platform.

Abstract

Energy awareness and efficiency policies are gaining more attention, over pure performance (time-to-solution) Key Performance Indicators (KPIs) when comparing the possibilities offered by accelerated systems. But in a field such as numerical astrophysics, which is struggling with code refactorings for GPUs, viable porting paths have to be shown before first. After summarizing the status and recurring problems of astrophysical code accelerations, we highlight how the field would benefit from portable, vendor-agnostic GPU portings. We then employ the DPEcho SYCL benchmark to compare raw performance and energy efficiency for heterogeneous hardware on a realistic application, with the goal of helping computational astrophysicists and HPC providers make informed decisions on the most suitable hardware. Aside from GPUs showing higher efficiency, we argue on the more informative nature of energy-aware KPIs, in that they convey the specific device performance in a data-driven way. We also present a convenient, flexible and cross-platform energy-measuring pipeline. Finally, we contextualize our results through measures with different compilers, presenting device (at the cores) versus node (at the plug) energy and comparing DPEcho with the High- Performance Linpack (HPL) benchmark.