Leveraging LLMs to Automate Energy-Aware Refactoring of Parallel Scientific Codes
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909028621221888 |
|---|---|
| author | Dearing, Matthew T. Tao, Yiheng Wu, Xingfu Lan, Zhiling Taylor, Valerie |
| author_facet | Dearing, Matthew T. Tao, Yiheng Wu, Xingfu Lan, Zhiling Taylor, Valerie |
| contents | Large language models (LLMs) are increasingly used for generating parallel scientific codes, with a primary focus on generating functionally correct code. Recent work has focused on generating performant code, with an emphasis on its execution time. However, energy efficiency is now recognized as a critical objective, given the significant power demands of large-scale compute systems. This paper addresses the research question of whether LLMs can generate energy-efficient parallel scientific codes when guided by empirical execution feedback. To answer this question, we propose LASSI-EE, an automated LLM-based refactoring framework that generates energy-efficient parallel codes through a multi-stage, iterative approach integrating runtime power profiling, energy-aware prompting, self-correcting feedback loops, and an LLM-as-a-Judge agent for screening generated code. We evaluate LASSI-EE using twenty-two representative scientific benchmarks and applications on NVIDIA A100 and AMD MI100 GPUs. The results indicate an average energy reduction of 36% for MI100 and 34% for A100, across trials that produced passing energy-reducing refactorings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_02184 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Leveraging LLMs to Automate Energy-Aware Refactoring of Parallel Scientific Codes Dearing, Matthew T. Tao, Yiheng Wu, Xingfu Lan, Zhiling Taylor, Valerie Artificial Intelligence Distributed, Parallel, and Cluster Computing Programming Languages Software Engineering Large language models (LLMs) are increasingly used for generating parallel scientific codes, with a primary focus on generating functionally correct code. Recent work has focused on generating performant code, with an emphasis on its execution time. However, energy efficiency is now recognized as a critical objective, given the significant power demands of large-scale compute systems. This paper addresses the research question of whether LLMs can generate energy-efficient parallel scientific codes when guided by empirical execution feedback. To answer this question, we propose LASSI-EE, an automated LLM-based refactoring framework that generates energy-efficient parallel codes through a multi-stage, iterative approach integrating runtime power profiling, energy-aware prompting, self-correcting feedback loops, and an LLM-as-a-Judge agent for screening generated code. We evaluate LASSI-EE using twenty-two representative scientific benchmarks and applications on NVIDIA A100 and AMD MI100 GPUs. The results indicate an average energy reduction of 36% for MI100 and 34% for A100, across trials that produced passing energy-reducing refactorings. |
| title | Leveraging LLMs to Automate Energy-Aware Refactoring of Parallel Scientific Codes |
| topic | Artificial Intelligence Distributed, Parallel, and Cluster Computing Programming Languages Software Engineering |
| url | https://arxiv.org/abs/2505.02184 |