Compiler-R1: Towards Agentic Compiler Auto-tuning with Reinforcement Learning
This addresses performance optimization in compilers for developers and researchers, representing an incremental improvement by integrating RL with existing LLM approaches.
The paper tackles compiler auto-tuning by introducing Compiler-R1, a reinforcement learning framework that augments LLMs to optimize pass sequences, achieving an average 8.46% reduction in IR instruction count compared to baseline methods.
Compiler auto-tuning optimizes pass sequences to improve performance metrics such as Intermediate Representation (IR) instruction count. Although recent advances leveraging Large Language Models (LLMs) have shown promise in automating compiler tuning, two significant challenges still remain: the absence of high-quality reasoning datasets for agents training, and limited effective interactions with the compilation environment. In this work, we introduce Compiler-R1, the first reinforcement learning (RL)-driven framework specifically augmenting LLM capabilities for compiler auto-tuning. Compiler-R1 features a curated, high-quality reasoning dataset and a novel two-stage end-to-end RL training pipeline, enabling efficient environment exploration and learning through an outcome-based reward. Extensive experiments across seven datasets demonstrate Compiler-R1 achieving an average 8.46% IR instruction count reduction compared to opt -Oz, showcasing the strong potential of RL-trained LLMs for compiler optimization. Our code and datasets are publicly available at https://github.com/Panhaolin2001/Compiler-R1.