28051

Machine Learning-Driven Adaptive OpenMP For Portable Performance on Heterogeneous Systems

Giorgis Georgakoudis, Konstantinos Parasyris, Chunhua Liao, David Beckingsale, Todd Gamblin, Bronis de Supinski
Lawrence Livermore National Laboratory, USA
arXiv:2303.08873 [cs.PL], (15 Mar 2023)

@misc{georgakoudis2023machine,

   title={Machine Learning-Driven Adaptive OpenMP For Portable Performance on Heterogeneous Systems},

   author={Giorgis Georgakoudis and Konstantinos Parasyris and Chunhua Liao and David Beckingsale and Todd Gamblin and Bronis de Supinski},

   year={2023},

   eprint={2303.08873},

   archivePrefix={arXiv},

   primaryClass={cs.PL}

}

Download Download (PDF)   View View   Source Source   

570

views

Heterogeneity has become a mainstream architecture design choice for building High Performance Computing systems. However, heterogeneity poses significant challenges for achieving performance portability of execution. Adapting a program to a new heterogeneous platform is laborious and requires developers to manually explore a vast space of execution parameters. To address those challenges, this paper proposes new extensions to OpenMP for autonomous, machine learning-driven adaptation. Our solution includes a set of novel language constructs, compiler transformations, and runtime support. We propose a producer-consumer pattern to flexibly define multiple, different variants of OpenMP code regions to enable adaptation. Those regions are transparently profiled at runtime to autonomously learn optimizing machine learning models that dynamically select the fastest variant. Our approach significantly reduces users’ efforts of programming adaptive applications on heterogeneous architectures by leveraging machine learning techniques and code generation capabilities of OpenMP compilation. Using a complete reference implementation in Clang/LLVM we evaluate three use-cases of adaptive CPU-GPU execution. Experiments with HPC proxy applications and benchmarks demonstrate that the proposed adaptive OpenMP extensions automatically choose the best performing code variants for various adaptation possibilities, in several different heterogeneous platforms of CPUs and GPUs.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2024 hgpu.org

All rights belong to the respective authors

Contact us: