On the Challenges of Energy-Efficiency Analysis in HPC Systems: Evaluating Synthetic Benchmarks and Gromacs

TL;DR

This paper examines the difficulties in assessing energy efficiency in HPC systems, focusing on synthetic benchmarks and Gromacs, using experiments on Intel and Nvidia hardware with profiling tools to identify challenges and best practices.

Contribution

It highlights specific challenges and pitfalls in energy-efficiency analysis of HPC workloads and proposes best practices for future studies.

Findings

Identified key challenges in energy-efficiency measurement

Demonstrated variability in profiling results across hardware

Provided recommendations for more reliable analysis

Abstract

This paper discusses the challenges encountered when analyzing the energy efficiency of synthetic benchmarks and the Gromacs package on the Fritz and Alex HPC clusters. Experiments were conducted using MPI parallelism on full sockets of Intel Ice Lake and Sapphire Rapids CPUs, as well as Nvidia A40 and A100 GPUs. The metrics and measurements obtained with the Likwid and Nvidia profiling tools are presented, along with the results. The challenges and pitfalls encountered during experimentation and analysis are revealed and discussed. Best practices for future energy efficiency analysis studies are suggested.