Large Language Models for Energy-Efficient Code: Emerging Results and Future Directions
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910646317088768 |
|---|---|
| author | Peng, Huiyun Gupte, Arjun Eliopoulos, Nicholas John Ho, Chien Chou Mantri, Rishi Deng, Leo Jiang, Wenxin Lu, Yung-Hsiang Läufer, Konstantin Thiruvathukal, George K. Davis, James C. |
| author_facet | Peng, Huiyun Gupte, Arjun Eliopoulos, Nicholas John Ho, Chien Chou Mantri, Rishi Deng, Leo Jiang, Wenxin Lu, Yung-Hsiang Läufer, Konstantin Thiruvathukal, George K. Davis, James C. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_09241 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Large Language Models for Energy-Efficient Code: Emerging Results and Future Directions Peng, Huiyun Gupte, Arjun Eliopoulos, Nicholas John Ho, Chien Chou Mantri, Rishi Deng, Leo Jiang, Wenxin Lu, Yung-Hsiang Läufer, Konstantin Thiruvathukal, George K. Davis, James C. Software Engineering 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. |
| title | Large Language Models for Energy-Efficient Code: Emerging Results and Future Directions |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2410.09241 |