Download PDFOpen PDF in browser

Accelerating pipeline implementation of dynamic programming on GPU

10 pagesPublished: November 24, 2022

Abstract

In this paper, we show the effectiveness of pipeline implementations of Dynamic Pro- gramming (DP) on Graphics Processing Unit (GPU). We deal with a simplified DP problem where each element of its solution table is calculated in order by semi-group operations among several of already computed elements in the table. We implement the DP program on GPU in a pipeline fashion, i.e., we use GPU cores for supporting pipeline-stages so that several elements of the solution tables are partially computed at one time. Further, to accelerate the pipeline implementation, we propose a p-fold pipeline technique, which enables larger parallelism more than the number of pipeline-stages.

Keyphrases: dynamic programming, GPGPU, parallel algorithm, Pipelining

In: Yan Shi, Gongzhu Hu, Krishna Kambhampaty and Takaaki Goto (editors). Proceedings of 35th International Conference on Computer Applications in Industry and Engineering, vol 89, pages 52--61

Links:
BibTeX entry
@inproceedings{CAINE2022:Accelerating_pipeline_implementation_of,
  author    = {Susumu Matsumae},
  title     = {Accelerating pipeline implementation of dynamic programming on GPU},
  booktitle = {Proceedings of 35th International Conference on Computer Applications in Industry and Engineering},
  editor    = {Yan Shi and Gongzhu Hu and Krishna Kambhampaty and Takaaki Goto},
  series    = {EPiC Series in Computing},
  volume    = {89},
  pages     = {52--61},
  year      = {2022},
  publisher = {EasyChair},
  bibsource = {EasyChair, https://easychair.org},
  issn      = {2398-7340},
  url       = {https://easychair.org/publications/paper/C59X},
  doi       = {10.29007/6mgp}}
Download PDFOpen PDF in browser