HintPilot: LLM-based Compiler Hint Synthesis for Code Optimization
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913038347534336 |
|---|---|
| author | Jiang, Hanyun Yao, Peisen Li, Kaiyue Lin, Tingting Wang, Chengpeng Ren, Kui |
| author_facet | Jiang, Hanyun Yao, Peisen Li, Kaiyue Lin, Tingting Wang, Chengpeng Ren, Kui |
| contents | 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 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 6.88x geometric mean speedup over -Ofast while preserving program correctness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_15041 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | HintPilot: LLM-based Compiler Hint Synthesis for Code Optimization Jiang, Hanyun Yao, Peisen Li, Kaiyue Lin, Tingting Wang, Chengpeng Ren, Kui Software Engineering 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 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 6.88x geometric mean speedup over -Ofast while preserving program correctness. |
| title | HintPilot: LLM-based Compiler Hint Synthesis for Code Optimization |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2604.15041 |