Can Large-Language Models Help us Better Understand and Teach the Development of Energy-Efficient Software?

TL;DR

This paper explores using large language models to generate energy-efficient code variations and develop educational modules for teaching energy-efficient software engineering in undergraduate curricula.

Contribution

It introduces a novel approach leveraging LLMs to create energy-efficient code and proposes a new educational framework for teaching energy-aware software development.

Findings

LLMs can generate energy-efficient code variations for different architectures.

Energy expenditure reduced by 30-90% in toy examples.

Preliminary results support LLMs as tools for teaching energy-efficient programming.

Abstract

Computing systems are consuming an increasing and unsustainable fraction of society's energy footprint, notably in data centers. Meanwhile, energy-efficient software engineering techniques are often absent from undergraduate curricula. We propose to develop a learning module for energy-efficient software, suitable for incorporation into an undergraduate software engineering class. There is one major problem with such an endeavor: undergraduate curricula have limited space for mastering energy-related systems programming aspects. To address this problem, we propose to leverage the domain expertise afforded by large language models (LLMs). In our preliminary studies, we observe that LLMs can generate energy-efficient variations of basic linear algebra codes tailored to both ARM64 and AMD64 architectures, as well as unit tests and energy measurement harnesses. On toy examples suitable for classroom use, this approach reduces energy expenditure by 30-90%. These initial experiences give rise to our vision of LLM-based meta-compilers as a tool for students to transform high-level algorithms into efficient, hardware-specific implementations. Complementing this tooling, we will incorporate systems thinking concepts into the learning module so that students can reason both locally and globally about the effects of energy optimizations.