From Profiling to Optimization: Unveiling the Profile Guided Optimization

TL;DR

This survey reviews Profile Guided Optimization (PGO), highlighting its methods, benefits, challenges, and future directions in enhancing compiler performance through runtime profiling techniques.

Contribution

It systematically categorizes PGO research, analyzes key algorithms, and discusses performance impacts, providing a comprehensive overview of the field and identifying open challenges.

Findings

PGO achieves significant speedups in various applications.

Sampling overhead remains a key challenge.

Future research should focus on low-overhead profiling and cross-architecture support.

Abstract

Profile Guided Optimization (PGO) uses runtime profiling to direct compiler optimization decisions, effectively combining static analysis with actual execution behavior to enhance performance. Runtime profiles, collected through instrumentation or hardware- and software-assisted sampling, provide detailed insights into control flow, branch predictions, and memory access patterns. This survey systematically categorizes PGO research by profiling method (instrumentation vs. sampling), optimizations (compile time and link/post-link time), compiler integration (GCC, LLVM), and target architectures. Key algorithms and frameworks are shown in terms of design principles. Performance evaluation on representative examples demonstrates PGO's speedups, overheads, and integration maturity. Finally, we identify open challenges, such as reducing sampling overhead, dynamic input workloads, and supporting cross-architecture portability, and propose future research directions to low-overhead profiling and advanced compilers.