Autotuning PolyBench benchmarks with LLVM Clang/Polly loop optimization pragmas using Bayesian optimization

Wu, Xingfu; Kruse, Michael; Balaprakash, Prasanna; Finkel, Hal; Hovland, Paul; Taylor, Valerie; Hall, Mary

doi:10.1002/cpe.6683

Cited by 17 publications

(20 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a recent study, Wu et al [21] apply BO to a search space of LLVM Clang / Polly pragma configurations on the PolyBench Benchmark suite. Their method appears to be most successful with random forests.…”

Section: Related Workmentioning

confidence: 99%

Bayesian Optimization for auto-tuning GPU kernels

Willemsen¹,

Nieuwpoort²,

Werkhoven³

2021

Preprint

View full text Add to dashboard Cite

Finding optimal parameter configurations for tunable GPU kernels is a non-trivial exercise for large search spaces, even when automated. This poses an optimization task on a nonconvex search space, using an expensive to evaluate function with unknown derivative. These characteristics make a good candidate for Bayesian Optimization, which has not been applied to this problem before.However, the application of Bayesian Optimization to this problem is challenging. We demonstrate how to deal with the rough, discrete, constrained search spaces, containing invalid configurations. We introduce a novel contextual variance exploration factor, as well as new acquisition functions with improved scalability, combined with an informed acquisition function selection mechanism.By comparing the performance of our Bayesian Optimization implementation on various test cases to the existing search strategies in Kernel Tuner, as well as other Bayesian Optimization implementations, we demonstrate that our search strategies generalize well and consistently outperform other search strategies by a wide margin.

show abstract

Section: Related Workmentioning

confidence: 99%

Bayesian Optimization for auto-tuning GPU kernels

Willemsen¹,

Nieuwpoort²,

Werkhoven³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Runtime System: ytopt Auto-Tuning Framework. In the auto-tuning ytopt project [31], we use the new Clang loop tiling, interchange, packing, and/or jam pragmas as examples to illustrate the integration process about auto-tuning the pragma parameters to achieve the optimal performance. Figure 4 shows our auto-tuning framework.…”

Section: Co-tuning Compiler (Clang) Application Andmentioning

confidence: 99%

Toward an End-to-End Auto-tuning Framework in HPC PowerStack

Marathe

Jana

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Efficiently utilizing procured power and optimizing performance of scientific applications under power and energy constraints are challenging. The HPC PowerStack defines a software stack to manage power and energy of high-performance computing systems and standardizes the interfaces between different components of the stack. This survey paper presents the findings of a working group focused on the end-to-end tuning of the PowerStack. First, we provide a background on the PowerStack layer-specific tuning efforts in terms of their high-level objectives, the constraints and optimization goals, layer-specific telemetry, and control parameters, and we list the existing software solutions that address those challenges. Second, we propose the PowerStack end-to-end auto-tuning framework, identify the opportunities in co-tuning different layers in the PowerStack, and present specific use cases and solutions. Third, we discuss the research opportunities and challenges for collective auto-tuning of two or more management layers (or domains) in the PowerStack. This paper takes the first steps in identifying and aggregating the important R&D challenges in streamlining the optimization efforts across the layers of the PowerStack.

show abstract

“…ytopt is a Python package that uses scikit-optimize [20], autotune [1], and ytopt subpackage [31]. See our initial work [30] for the detailed installation and download information. It uses ConfigSpace [7] package to handle the algebraic constraints on the parameter configuration space.…”

Section: Parameter Space Searchmentioning

confidence: 99%

“…To cope with this situation, we provide three compiler option solutions to improve the performance. This autotuning framework is open source and is available from the link in [30].…”

Section: Summary and Future Workmentioning

confidence: 99%

“…Because of the large parameter space of these pragmas and related parameters, autotuning for automatic exploration of the parameter space is desirable. In our preliminary work with the Y-TUNE project [30], we worked on integrating the loop optimization pragmas within the ytopt package to autotune loop optimization pragmas for optimal performance. In this paper, we develop an autotuning framework to integrate the Clang/Polly loop optimization pragmas with the ytopt, and we apply the loop optimization pragmas to the PolyBench benchmarks [32] to evaluate the autotuning framework.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Kruse

Balaprakash

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Autotuning PolyBench benchmarks with LLVM Clang/Polly loop optimization pragmas using Bayesian optimization

Cited by 17 publications

References 37 publications

Bayesian Optimization for auto-tuning GPU kernels

Bayesian Optimization for auto-tuning GPU kernels

Toward an End-to-End Auto-tuning Framework in HPC PowerStack

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

Contact Info

Product

Resources

About