用知识与数据协同驱动的智能编译器，提升优化效率与性能。
AwareCompiler: Agentic Context-Aware Compiler Optimization via a Synergistic Knowledge-Data Driven Framework
- 构建结构化知识库与数据集，解决抽象表示与具体优化间的语义偏差。
- 基于知识自适应生成优化流程，在标准测试中性能超越现有方法。
- 适合编译器研究者与高性能计算开发者使用，可复用性强。
编译器优化通过调整优化步骤顺序来提升程序性能，同时保证正确性。尽管大语言模型（LLMs）在软件优化中展现出潜力，但自动化编译优化仍面临三大挑战：（1）程序抽象表示与具体优化步骤间存在语义错位；（2）智能体与编译环境交互效率低；（3）在大规模优化空间中决策过程奖励稀疏。本文提出 extbf{AwareCompiler}，一种面向编译优化的智能体框架，通过三项关键创新应对上述问题：结构化知识整合与数据集构建、知识驱动的自适应优化步骤生成、数据驱动的混合训练流程。在标准基准测试上的实验结果表明，AwareCompiler在性能和效率上均显著优于现有基线，验证了其知识-数据协同驱动方法的有效性。代码已公开于 https://github.com/LHY-24/AwareCompiler。
原文摘要 · Abstract (English)
Compiler optimization is crucial for enhancing program performance by transforming the sequence of optimization passes while maintaining correctness. Despite the promising potential of large language models (LLMs)-based agent for software optimization, automating compiler optimization remains challenging due to: (1) semantic misalignment between abstract program representations and concrete optimization passes, (2) inefficient interaction mechanisms between agents and compiler environments, and (3) reward sparsity from the extensive decision-making process within large optimization spaces. This paper introduces \textbf{AwareCompiler}, an agentic framework for compiler optimization that addresses these challenges through three key innovations: structured knowledge integration and dataset construction, knowledge-driven adaptive pass generation, and data-driven hybrid training pipeline. Experimental results on standard benchmarks demonstrate that AwareCompiler significantly outperforms existing baselines in both performance and efficiency, highlighting the effectiveness of our synergistic knowledge-data-driven approach. Our code is publicly available at https://github.com/LHY-24/AwareCompiler.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。