Power Efficiency in High Performance Computing

Overview

This paper provides power measurements for various computational loads on the largest scale HPC systems ever involved in such an assessment. This paper demonstrates clearly that, contrary to conventional wisdom, the power consumed while running the High Performance Linpack (HPL) benchmark is very close to the power consumed by any subset of a typical compute-intensive scientific workload. Therefore, HPL, which in most cases cannot serve as a suitable workload for performance measurements, can be used for the purposes of power measurement. Furthermore, they show through measurements on a large scale system that the power consumed by smaller subsets of the system can be projected straightforwardly and accurately to estimate the power consumption of the full system.