A Hybrid, Knowledge-Guided Evolutionary Framework for Personalized Compiler Auto-Tuning

2025-10-16

AI Summary

Compiler optimization pass sequence search is an NP-hard problem, and generic optimization flags (e.g., -O3/-Oz) fail to account for program-specific characteristics. To address this, we propose a hybrid evolutionary framework that synergistically combines offline knowledge mining with online personalized tuning. Our approach constructs a four-dimensional compilation knowledge base integrating behavioral vectors, clustering-based grouping, collaborative graphs, and prototype sequences. Furthermore, we design semantics-aware genetic operators—including knowledge-guided recombination and recovery-based mutation—to enhance search efficiency and solution quality. Evaluated on seven public benchmarks, our method reduces LLVM IR instruction count by 11.0% on average compared to the opt -Oz baseline, demonstrating substantial improvements in customized optimization effectiveness.

Technology Category

• Search and Optimization: Evolutionary Computation
• Machine Learning: Optimization
• Constraint Satisfaction and Optimization: Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Compiler pass auto-tuning is critical for enhancing software performance, yet finding the optimal pass sequence for a specific program is an NP-hard problem. Traditional, general-purpose optimization flags like -O3 and -Oz adopt a one-size-fits-all approach, often failing to unlock a program's full performance potential. To address this challenge, we propose a novel Hybrid, Knowledge-Guided Evolutionary Framework. This framework intelligently guides online, personalized optimization using knowledge extracted from a large-scale offline analysis phase. During the offline stage, we construct a comprehensive compilation knowledge base composed of four key components: (1) Pass Behavioral Vectors to quantitatively capture the effectiveness of each optimization; (2) Pass Groups derived from clustering these vectors based on behavior similarity; (3) a Synergy Pass Graph to model beneficial sequential interactions; and (4) a library of Prototype Pass Sequences evolved for distinct program types. In the online stage, a bespoke genetic algorithm leverages this rich knowledge base through specially designed, knowledge-infused genetic operators. These operators transform the search by performing semantically-aware recombination and targeted, restorative mutations. On a suite of seven public datasets, our framework achieves an average of 11.0% additional LLVM IR instruction reduction over the highly-optimized opt -Oz baseline, demonstrating its state-of-the-art capability in discovering personalized, high-performance optimization sequences.

Problem

• Finding optimal compiler pass sequences for specific programs is NP-hard
• General-purpose optimization flags fail to unlock full program performance potential
• Auto-tuning requires personalized optimization sequences for different program types

Innovation

• Hybrid evolutionary framework with offline knowledge base
• Knowledge-infused genetic operators for semantic recombination
• Personalized compiler optimization using behavioral pass groups