On the support of task-parallel algorithmic skeletons for multi-GPU computing

Fernando Alexandre, Hervé Paulino, Ricardo Marques

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

An emerging trend in the field of Graphics Processing Unit (GPU) computing is the harnessing of multiple devices to cope with scalability and performance requirements. However, multi-GPU execution adds new challenges to the already complex world of General Purpose computing on GPUs (GPGPU), such as the efficient problem decomposition, and dealing with device heterogeneity. To this extent, we propose the use of the Marrow algorithmic skeleton framework (ASkF) to abstract most of the details intrinsic to the programming of such platforms. To the best of our knowledge, Marrow is the first ASkF to support skeleton nesting on single and (now) multiple GPU systems. In this paper we present how it can transparently distribute the execution of skeleton compositions among a set of, possibly, heterogeneous devices. An experimental evaluation assesses the proposal's effectiveness, from a scalability and performance perspective, with good results.

Original languageEnglish
Title of host publicationProceedings of the 29th Annual ACM Symposium on Applied Computing, SAC 2014
PublisherAssociation for Computing Machinery
Pages880-885
Number of pages6
ISBN (Print)9781450324694
DOIs
Publication statusPublished - 2014
Event29th Annual ACM Symposium on Applied Computing, SAC 2014 - Gyeongju, Korea, Republic of
Duration: 24 Mar 201428 Mar 2014

Conference

Conference29th Annual ACM Symposium on Applied Computing, SAC 2014
CountryKorea, Republic of
CityGyeongju
Period24/03/1428/03/14

Keywords

  • Algorithmic Skeletons
  • Multi-GPU Computing
  • OpenCL

Fingerprint Dive into the research topics of 'On the support of task-parallel algorithmic skeletons for multi-GPU computing'. Together they form a unique fingerprint.

  • Cite this

    Alexandre, F., Paulino, H., & Marques, R. (2014). On the support of task-parallel algorithmic skeletons for multi-GPU computing. In Proceedings of the 29th Annual ACM Symposium on Applied Computing, SAC 2014 (pp. 880-885). Association for Computing Machinery. https://doi.org/10.1145/2554850.2555018