Understanding Power and Energy Utilization in Large Scale Production Physics Simulation Codes

TL;DR

This paper investigates the actual power and energy consumption of large-scale physics simulation codes, revealing they are more efficient than traditional TDP estimates suggest, which is crucial for energy-aware exascale computing.

Contribution

It provides empirical measurements of power usage in large-scale simulations, challenging the reliance on TDP as a power proxy and offering insights into actual energy efficiency.

Findings

Large-scale simulation codes are more energy-efficient than TDP estimates.

Empirical measurements show significant differences from TDP-based assumptions.

Results inform better energy management for exascale computing.

Abstract

Power is an often-cited reason for the move to advanced architectures on the path to Exascale computing. This is due to practical considerations related to delivering enough power to successfully site and operate these machines, as well as concerns about energy usage while running large simulations. Since obtaining accurate power measurements can be challenging, it may be tempting to use the processor thermal design power (TDP) as a surrogate due to its simplicity and availability. However, TDP is not indicative of typical power usage while running simulations. Using commodity and advanced technology systems at Lawrence Livermore and Sandia National Labs, we performed a series of experiments to measure power and energy usage in running simulation codes. These experiments indicate that large scale Lawrence Livermore simulation codes are significantly more efficient than a simple processor TDP model might suggest.