Benchmarking optimization algorithms for auto-tuning GPU kernels

TL;DR

This paper benchmarks various optimization algorithms for auto-tuning GPU kernels, analyzing their performance across multiple GPU architectures and kernel spaces, and introduces a new metric to assess problem difficulty.

Contribution

It provides a comprehensive experimental comparison of 16 optimization algorithms for GPU kernel auto-tuning and proposes a novel PageRank-based metric to evaluate problem complexity.

Findings

Certain algorithms outperform others depending on the time budget.

The PageRank-based metric correlates strongly with tuning performance.

The study offers insights into the difficulty of GPU kernel optimization problems.

Abstract

Recent years have witnessed phenomenal growth in the application, and capabilities of Graphical Processing Units (GPUs) due to their high parallel computation power at relatively low cost. However, writing a computationally efficient GPU program (kernel) is challenging, and generally only certain specific kernel configurations lead to significant increases in performance. Auto-tuning is the process of automatically optimizing software for highly-efficient execution on a target hardware platform. Auto-tuning is particularly useful for GPU programming, as a single kernel requires re-tuning after code changes, for different input data, and for different architectures. However, the discrete, and non-convex nature of the search space creates a challenging optimization problem. In this work, we investigate which algorithm produces the fastest kernels if the time-budget for the tuning task is varied. We conduct a survey by performing experiments on 26 different kernel spaces, from 9 different GPUs, for 16 different evolutionary black-box optimization algorithms. We then analyze these results and introduce a novel metric based on the PageRank centrality concept as a tool for gaining insight into the difficulty of the optimization problem. We demonstrate that our metric correlates strongly with observed tuning performance.