Tag
Second post in a three-part Percona series explaining how Profile-Guided Optimization (PGO) works: instrumented two-pass builds, per-edge counter collection, and how the compiler uses that data to drive inlining, branch layout, hot/cold function splitting, and instruction-cache locality.
The author is developing Agent-PGO, a tool that profiles AI agent executions to dynamically substitute cheaper models for less critical tasks while maintaining quality through evaluation benchmarks.
Daniel Lemire benchmarks profile-guided optimization (PGO) in Go, showing modest speedups of 2-5% when parsing JSON, with the best gains when the training profile matches the workload.
A technical blog post demonstrating how Profile-Guided Optimization (PGO) with LLVM can significantly improve binary performance beyond standard -O3 and LTO, using SQLite as a benchmark.
This blog post explains how to build a host-tuned GCC compiler using profile-guided optimization, LTO, and -O3 to achieve faster compilation times, with detailed instructions and benchmarks.