Skip to main navigation Skip to search Skip to main content

Extreme-scale multigrid components within PETSc

  • Swiss Federal Institute of Technology Zurich
  • Università della Svizzera italiana
  • Argonne National Laboratory

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

36 Scopus citations

Abstract

Elliptic partial differential equations (PDEs) frequently arise in continuum descriptions of physical processes relevant to science and engineering. Multilevel preconditioners represent a family of scalable techniques for solving discrete PDEs of this type and thus are the method of choice for high-resolution simulations. The scalability and time-tosolution of massively parallel multilevel preconditioners can be adversely affected by using a coarse-level solver with suboptimal algorithmic complexity. To maintain scalability, agglomeration techniques applied to the coarse level have been shown to be necessary. In this work, we present a new software component introduced within the Portable Extensible Toolkit for Scientific computation (PETSc) which permits agglomeration. We provide an overview of the design and implementation of this functionality, together with several use cases highlighting the benefits of agglomeration. Lastly, we demonstrate via numerical experiments employing geometric multigrid with structured meshes, the exibility and performance gains possible using our MPI-rank agglomeration implementation.

Original languageEnglish
Title of host publicationPASC 2016 - Proceedings of the Platform for Advanced Scientific Computing Conference
PublisherAssociation for Computing Machinery, Inc
ISBN (Electronic)9781450341264
DOIs
StatePublished - Jun 8 2016
Event3rd Conference on Platform for Advanced Scientific Computing, PASC 2016 - Lausanne, Switzerland
Duration: Jun 8 2016Jun 10 2016

Publication series

NamePASC 2016 - Proceedings of the Platform for Advanced Scientific Computing Conference

Conference

Conference3rd Conference on Platform for Advanced Scientific Computing, PASC 2016
Country/TerritorySwitzerland
CityLausanne
Period06/8/1606/10/16

Keywords

  • Agglomeration
  • Coarse-level solver
  • GPU
  • HPC
  • Multigrid
  • Parallel computing
  • Preconditioning

Fingerprint

Dive into the research topics of 'Extreme-scale multigrid components within PETSc'. Together they form a unique fingerprint.

Cite this