Optimizing Code Runtime Performance through Context-Aware Retrieval-Augmented Generation
This addresses the gap in LLMs' ability to perform deep program analysis for software developers, offering an incremental advance in automated code refinement.
The paper tackles the problem of automated code optimization for runtime performance by introducing AUTOPATCH, an in-context learning approach that integrates historical examples and control flow graph analysis, achieving a 7.3% improvement in execution efficiency over GPT-4o on generated code.
Optimizing software performance through automated code refinement offers a promising avenue for enhancing execution speed and efficiency. Despite recent advancements in LLMs, a significant gap remains in their ability to perform in-depth program analysis. This study introduces AUTOPATCH, an in-context learning approach designed to bridge this gap by enabling LLMs to automatically generate optimized code. Inspired by how programmers learn and apply knowledge to optimize software, AUTOPATCH incorporates three key components: (1) an analogy-driven framework to align LLM optimization with human cognitive processes, (2) a unified approach that integrates historical code examples and CFG analysis for context-aware learning, and (3) an automated pipeline for generating optimized code through in-context prompting. Experimental results demonstrate that AUTOPATCH achieves a 7.3% improvement in execution efficiency over GPT-4o across common generated executable code, highlighting its potential to advance automated program runtime optimization.