Leveraging LLMs to Automate Energy-Aware Refactoring of Parallel Scientific Codes
By: Matthew T. Dearing , Yiheng Tao , Xingfu Wu and more
Potential Business Impact:
Makes computer code use less power.
While large language models (LLMs) are increasingly used for generating parallel scientific code, most current efforts emphasize functional correctness, often overlooking performance and energy considerations. In this work, we propose LASSI-EE, an automated LLM-based refactoring framework that generates energy-efficient parallel code on a target parallel system for a given parallel code as input. Through a multi-stage, iterative pipeline process, LASSI-EE achieved an average energy reduction of 47% across 85% of the 20 HeCBench benchmarks tested on NVIDIA A100 GPUs. Our findings demonstrate the broader potential of LLMs, not only for generating correct code but also for enabling energy-aware programming. We also address key insights and limitations within the framework, offering valuable guidance for future improvements.
Similar Papers
Benchmarking Energy Efficiency of Large Language Models Using vLLM
Software Engineering
Helps make AI use less electricity.
Energy-Aware LLMs: A step towards sustainable AI for downstream applications
Performance
Saves energy while making AI smarter.
Generating Energy-Efficient Code via Large-Language Models -- Where are we now?
Software Engineering
Human coders write greener computer programs.