# Leveraging LLMs to Automate Energy-Aware Refactoring of Parallel Scientific Codes

arXiv: https://arxiv.org/abs/2505.02184 · HTML: https://mlsanity.com/paper/2505.02184/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 56 references that are in the map.
- First posted on arXiv 4 May 2025.

## Builds on (most cited first, 16 of 16)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [StarCoder 2 and The Stack v2: The Next Generation](https://mlsanity.com/paper/2402.19173/) (2024)
- [DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence](https://mlsanity.com/paper/2406.11931/) (2024)
- [KernelBench: Can LLMs Write Efficient GPU Kernels?](https://mlsanity.com/paper/2502.10517/) (2025)
- [Granite Code Models: A Family of Open Foundation Models for Code Intelligence](https://mlsanity.com/paper/2405.04324/) (2024)
- [Can Large Language Models Write Parallel Code?](https://mlsanity.com/paper/2401.12554/) (2024)
- [CLTune: A Generic Auto-Tuner for OpenCL Kernels](https://mlsanity.com/paper/1703.06503/) (2017)
- [Evaluation of OpenAI Codex for HPC Parallel Programming Models Kernel Generation](https://mlsanity.com/paper/2306.15121/) (2023)
- [CodeRosetta: Pushing the Boundaries of Unsupervised Code Translation for Parallel Programming](https://mlsanity.com/paper/2410.20527/) (2024)
- [ytopt: Autotuning Scientific Applications for Energy Efficiency at Large Scales](https://mlsanity.com/paper/2303.16245/) (2023)
- [LASSI: An LLM-based Automated Self-Correcting Pipeline for Translating Parallel Scientific Codes](https://mlsanity.com/paper/2407.01638/) (2024)
- [HPC-Coder-V2: Studying Code LLMs Across Low-Resource Parallel Languages](https://mlsanity.com/paper/2412.15178/) (2024)
- [LLM-Assisted Translation of Legacy FORTRAN Codes to C++: A Cross-Platform Study](https://mlsanity.com/paper/2504.15424/) (2025)
- [Utilizing Ensemble Learning for Performance and Power Modeling and Improvement of Parallel Cancer Deep Learning CANDLE Benchmarks](https://mlsanity.com/paper/2011.06654/) (2020)

## Built on by (most cited first, 3 of 3)

- [CATArena: Evaluating Evolutionary Capabilities of Code Agents via Iterative Tournaments](https://mlsanity.com/paper/2510.26852/) (2025)
- [An Agentic Evaluation Framework for AI-Generated Scientific Code in PETSc](https://mlsanity.com/paper/2603.15976/) (2026)
- [Exploring the Role of LLMs in HPC Programming: A Survey](https://mlsanity.com/paper/2608.26110/) (2026)

## Abstract (arXiv)

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.