ECCO: Evidence-Driven Causal Reasoning for Compiler Optimization

TL;DR

ECCO introduces an evidence-driven, interpretable causal reasoning framework for compiler optimization, combining LLMs and genetic algorithms to outperform traditional methods by leveraging explicit performance evidence.

Contribution

The paper presents ECCO, a novel framework that integrates causal reasoning with combinatorial search, bridging interpretability and effectiveness in compiler auto-tuning.

Findings

Achieves 24.44% average cycle reduction over LLVM -O3.

Constructs a Chain-of-Thought dataset linking code features to performance evidence.

Demonstrates superior performance across seven datasets.

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.