GroupTuner: Efficient Group-Aware Compiler Auto-Tuning

TL;DR

GroupTuner is a novel compiler auto-tuning method that efficiently explores option groups to improve program performance, outperforming existing techniques with less tuning time and better results.

Contribution

It introduces a group-aware auto-tuning approach that avoids explicit critical option identification, enhancing efficiency and effectiveness in compiler optimization.

Findings

Achieves 12.39% average performance improvement over -O3.

Uses only 77.21% of the tuning time compared to random search.

Significantly outperforms state-of-the-art auto-tuning methods.

Abstract

Modern compilers typically provide hundreds of options to optimize program performance, but users often cannot fully leverage them due to the huge number of options. While standard optimization combinations (e.g., -O3) provide reasonable defaults, they often fail to deliver near-peak performance across diverse programs and architectures. To address this challenge, compiler auto-tuning techniques have emerged to automate the discovery of improved option combinations. Existing techniques typically focus on identifying critical options and prioritizing them during the search to improve efficiency. However, due to limited tuning iterations, the resulting data is often sparse and noisy, making it highly challenging to accurately identify critical options. As a result, these algorithms are prone to being trapped in local optima. To address this limitation, we propose GroupTuner, a group-aware auto-tuning technique that directly applies localized mutation to coherent option groups based on historically best-performing combinations, thus avoiding explicitly identifying critical options. By forgoing the need to know precisely which options are most important, GroupTuner maximizes the use of existing performance data, ensuring more targeted exploration. Extensive experiments demonstrate that GroupTuner can efficiently discover competitive option combinations, achieving an average performance improvement of 12.39% over -O3 while requiring only 77.21% of the time compared to the random search algorithm, significantly outperforming state-of-the-art methods.