Energy-efficient software helps improve mobile device experiences and reduce the carbon footprint of data centers. However, energy goals are often de-prioritized in order to meet other requirements. We take inspiration from recent work exploring the use of large language models (LLMs) for different software engineering activities. We propose a novel application of LLMs: as code optimizers for energy efficiency. We describe and evaluate a prototype, finding that over 6 small programs our system can improve energy efficiency in 3 of them, up to 2x better than compiler optimizations alone. From our experience, we identify some of the challenges of energy-efficient LLM code optimization and propose a research agenda.
@article{arxiv.2410.09241,
title = {Large Language Models for Energy-Efficient Code: Emerging Results and Future Directions},
author = {Huiyun Peng and Arjun Gupte and Nicholas John Eliopoulos and Chien Chou Ho and Rishi Mantri and Leo Deng and Wenxin Jiang and Yung-Hsiang Lu and Konstantin Läufer and George K. Thiruvathukal and James C. Davis},
journal= {arXiv preprint arXiv:2410.09241},
year = {2024}
}