ECCO: Evidence-Driven Causal Reasoning for Compiler Optimization
This addresses compiler optimization for software developers and engineers, offering a novel hybrid approach that bridges semantic guidance with search methods.
The paper tackles the problem of compiler auto-tuning by introducing ECCO, a framework that combines interpretable reasoning with combinatorial search to improve optimization decisions, achieving an average 24.44% reduction in cycles compared to the LLVM opt -O3 baseline.
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.