Report on workflow analysis for specific LAM applications

TL;DR

This report analyzes the workflow and energy consumption of the RMI-EPS weather prediction suite, highlighting the forecast component as the main energy consumer and suggesting optimization focus areas for performance and energy efficiency.

Contribution

It provides a detailed workflow analysis of the RMI-EPS suite and quantifies energy and time distribution across its components, guiding targeted optimization efforts.

Findings

Forecast accounts for 35% of total wall-clock time.

Forecast consumes up to 99% of total energy.

Energy optimizations in forecast yield proportional benefits.

Abstract

This document is one of the deliverable reports created for the ESCAPE project. ESCAPE stands for Energy-efficient Scalable Algorithms for Weather Prediction at Exascale. The project develops world-class, extreme-scale computing capabilities for European operational numerical weather prediction and future climate models. This is done by identifying Weather & Climate dwarfs which are key patterns in terms of computation and communication (in the spirit of the Berkeley dwarfs). These dwarfs are then optimised for different hardware architectures (single and multi-node) and alternative algorithms are explored. Performance portability is addressed through the use of domain specific languages. In this deliverable we focus on the RMI-EPS ensemble prediction suite. We first provide a detailed report on the workflow of the suite in which 5 main categories of jobs are defined; pre-processing, lateral boundary conditions (LBCs), data assimilation, forecast and post-processing. Combined Energy and wall-clock time measurements of the entire RMI-EPS suite were performed. They indicate that the wall-clock times are relatively spread between the various defined job categories, with the forecast accounting for the largest fraction at about 35%. As far as energy consumption is concerned, the forecast part dwarfs everything else and is responsible for up to 99% of the total energy consumption. This means that energy optimizations for the forecast part will translate almost proportionally into optimizations of the whole suite, while the maximum theoretical speed-up due to forecast optimizations cannot exceed a factor of about 3/2. Therefore, in terms of energy consumption, optimizations should first focus on the forecast part. For wall-clock time performance gains, however, optimizations (and possibly additional dwarfs) can be considered for the categories outside of the forecast part.