Year: 2026
Type: preprint
Abstract: Compiler auto-tuning faces a dichotomy between traditional black-box search methods, which lack semantic guidance, and recent Large Language Model (LLM) approaches, which often suffer from superficial pattern matching and causal opacity. In this paper, we introduce ECCO, a framework that bridges interpretable reasoning with combinatorial search. We first propose a reverse engineering methodology to construct a Chain-of-Thought dataset, explicitly mapping static code features to verifiable performance evidence. This enables the model to learn the causal logic governing optimization decisions rather than merely imitating sequences. Leveraging this interpretable prior, we design a collaborative inference mechanism where the LLM functions as a strategist, defining optimization intents that dynamically guide the mutation operations of a genetic algorithm. Experimental results on seven datasets demonstrate that ECCO significantly outperforms the LLVM opt -O3 baseline, achieving an average 24.44% reduction in cycles.
Source: arXiv (Cornell University)
Authors: Pan, Haolin, Huang, Lianghong, Dong, Jinyuan, Xing, Mingjie, Wu, Yanjun
Subfield: Hardware and Architecture
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7127449719
Cites:
Cited by:
Related to: