HintPilot: LLM-based Compiler Hint Synthesis for Code Optimization

ACL ARR 2026 January Submission7558 Authors

Keywords: Code generation and understanding, Prompting, Compiler optimization

Abstract:

Code optimization remains a core objective in software development, yet modern compilers struggle to navigate the enormous optimization spaces. While recent research has looked into employing large language models (LLMs) to optimize source code directly, these techniques can introduce semantic errors and miss fine-grained compiler-level optimization opportunities. We present HintPilot, which bridges LLM-based reasoning with traditional compiler infrastructures via synthesizing \emph{compiler hints}—annotations that steer compiler behavior.
HintPilot employs retrieval-augmented synthesis over compiler documentation and applies profiling-guided iterative refinement to synthesize semantics-preserving and effective hints. Upon PolyBench and HumanEval-CPP benchmarks, HintPilot achieves up to 6.88$\times$ geometric mean speedup over \texttt{-Ofast} while preserving program correctness.

Paper Type: Long

Research Area: NLP Applications

Research Area Keywords: Code generation and understanding, Prompting, Information Extraction

Contribution Types: NLP engineering experiment

Languages Studied: natural language

Submission Number: 7558