KEDM: A Performance-portable Implementation of Empirical Dynamic Modeling using Kokkos

Keichi Takahashi, Wassapon Watanakeesuntorn, Kohei Ichikawa, Joseph Park, Ryousei Takano, Jason Haga, George Sugihara, Gerald M. Pao

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

1 Citation (Scopus)

Abstract

Empirical Dynamic Modeling (EDM) is a state-of-the-art non-linear time-series analysis framework. Despite its wide applicability, EDM was not scalable to large datasets due to its expensive computational cost. To overcome this obstacle, researchers have attempted and succeeded in accelerating EDM from both algorithmic and implementational aspects. In previous work, we developed a massively parallel implementation of EDM targeting HPC systems (mpEDM). However, mpEDM maintains different backends for different architectures. This design becomes a burden in the increasingly diversifying HPC systems, when porting to new hardware. In this paper, we design and develop a performance-portable implementation of EDM based on the Kokkos performance portability framework (kEDM), which runs on both CPUs and GPUs while based on a single codebase. Furthermore, we optimize individual kernels specifically for EDM computation, and use real-world datasets to demonstrate up to 5.5 × speedup compared to mpEDM in convergent cross mapping computation.

Original languageEnglish
Title of host publicationPEARC 2021 - Practice and Experience in Advanced Research Computing 2021
Subtitle of host publicationEvolution Across All Dimensions
PublisherAssociation for Computing Machinery
ISBN (Electronic)9781450382922
DOIs
Publication statusPublished - 2021 Jul 17
Externally publishedYes
Event5th Practice and Experience in Advanced Research Computing Conference: Evolution Across All Dimensions, PEARC 2021 - Virtual, Online, United States
Duration: 2021 Jul 192021 Jul 22

Publication series

NameACM International Conference Proceeding Series

Conference

Conference5th Practice and Experience in Advanced Research Computing Conference: Evolution Across All Dimensions, PEARC 2021
Country/TerritoryUnited States
CityVirtual, Online
Period21/7/1921/7/22

Keywords

  • Empirical Dynamic Modeling
  • GPU
  • High Performance Computing
  • Kokkos
  • Performance Portability

ASJC Scopus subject areas

  • Software
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'KEDM: A Performance-portable Implementation of Empirical Dynamic Modeling using Kokkos'. Together they form a unique fingerprint.

Cite this