Autotuning PolyBench Benchmarks with LLVM Clang/Polly Loop Optimization Pragmas Using Bayesian Optimization

TL;DR

This paper presents an autotuning framework using Bayesian optimization to enhance LLVM Clang/Polly loop optimizations on PolyBench benchmarks, significantly reducing execution times by effectively exploring large parameter spaces.

Contribution

Developed a Bayesian optimization-based autotuning framework for LLVM Clang/Polly pragmas, optimizing loop parameters on complex benchmarks to improve performance.

Findings

Autotuning outperforms other methods in reducing execution time for most benchmarks.

Effective search over up to 170,368 configurations with 200 evaluations.

Polly heuristics can sometimes hinder performance, requiring additional compiler options.

Abstract

An autotuning is an approach that explores a search space of possible implementations/configurations of a kernel or an application by selecting and evaluating a subset of implementations/configurations on a target platform and/or use models to identify a high performance implementation/configuration. In this paper, we develop an autotuning framework that leverages Bayesian optimization to explore the parameter space search. We select six of the most complex benchmarks from the application domains of the PolyBench benchmarks (syr2k, 3mm, heat-3d, lu, covariance, and Floyd-Warshall) and apply the newly developed LLVM Clang/Polly loop optimization pragmas to the benchmarks to optimize them. We then use the autotuning framework to optimize the pragma parameters to improve their performance. The experimental results show that our autotuning approach outperforms the other compiling methods to provide the smallest execution time for the benchmarks syr2k, 3mm, heat-3d, lu, and covariance with two large datasets in 200 code evaluations for effectively searching the parameter spaces with up to 170,368 different configurations. We compare four different supervised learning methods within Bayesian optimization and evaluate their effectiveness. We find that the Floyd-Warshall benchmark did not benefit from autotuning because Polly uses heuristics to optimize the benchmark to make it run much slower. To cope with this issue, we provide some compiler option solutions to improve the performance.