Programming heterogeneous parallel machines using refactoring and Monte-Carlo tree search
Abstract
This paper presents a new technique for introducing and tuning parallelism for heterogeneous shared-memory systems (comprising a mixture of CPUs and GPUs), using a combination of algorithmic skeletons (such as farms and pipelines), Monte–Carlo tree search for deriving mappings of tasks to available hardware resources, and refactoring tool support for applying the patterns and mappings in an easy and effective way. Using our approach, we demonstrate easily obtainable, significant and scalable speedups on a number of case studies showing speedups of up to 41 over the sequential code on a 24-core machine with one GPU. We also demonstrate that the speedups obtained by mappings derived by the MCTS algorithm are within 5–15% of the best-obtained manual parallelisation.
Citation
Brown , C M , Janjic , V , Goli , M & McCall , J 2020 , ' Programming heterogeneous parallel machines using refactoring and Monte-Carlo tree search ' , International Journal of Parallel Programming , vol. 48 , no. 4 , pp. 583–602 . https://doi.org/10.1007/s10766-020-00665-z
Publication
International Journal of Parallel Programming
Status
Peer reviewed
ISSN
0885-7458Type
Journal article
Description
Funding: This work was supported by the EU Horizon 2020 project, TeamPlay, Grant Number 779882, and UK EPSRC Discovery, Grant Number EP/P020631/1.Collections
Items in the St Andrews Research Repository are protected by copyright, with all rights reserved, unless otherwise indicated.