GOPipe: A granularity-oblivious programming framework for pipelined stencil executions on GPU

Chanyoung Oh, Zhen Zheng, Xipeng Shen, Jidong Zhai, Youngmin Yi

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Recent studies have shown promising performance benefits of pipelined stencil applications. An important factor for the computing eficiency of such pipelines is the granularity of a task. We presents GOPipe, the first granularity-oblivious programming framework for eficient pipelined stencil executions. With GOPipe, programmers no longer need to specify the appropriate task granularity. GOPipe automatically finds it, and schedules tasks of that granularity while observing all inter-task and inter-stage data dependencies. In our experiments on four real-life applications, GOPipe outperforms the state-of-the-art by up to 4.57× with a much better programming productivity.

Original languageEnglish
Title of host publicationPPoPP 2019 - Proceedings of the 24th Principles and Practice of Parallel Programming
PublisherAssociation for Computing Machinery
Pages431-432
Number of pages2
ISBN (Electronic)9781450362252
DOIs
StatePublished - 16 Feb 2019
Event24th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPoPP 2019 - Washington, United States
Duration: 16 Feb 201920 Feb 2019

Publication series

NameProceedings of the ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPOPP

Conference

Conference24th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPoPP 2019
Country/TerritoryUnited States
CityWashington
Period16/02/1920/02/19

Keywords

  • Data dependence
  • GPU
  • Pipelined execution

Fingerprint

Dive into the research topics of 'GOPipe: A granularity-oblivious programming framework for pipelined stencil executions on GPU'. Together they form a unique fingerprint.

Cite this