Skip to content

GitLab

  • Menu
Projects Groups Snippets
  • Help
    • Help
    • Support
    • Community forum
    • Submit feedback
    • Contribute to GitLab
  • Sign in
  • T Trilinos
  • Project information
    • Project information
    • Activity
    • Labels
    • Members
  • Repository
    • Repository
    • Files
    • Commits
    • Branches
    • Tags
    • Contributors
    • Graph
    • Compare
  • Issues 936
    • Issues 936
    • List
    • Boards
    • Service Desk
    • Milestones
  • Merge requests 22
    • Merge requests 22
  • CI/CD
    • CI/CD
    • Pipelines
    • Jobs
    • Schedules
  • Deployments
    • Deployments
    • Environments
    • Releases
  • Monitor
    • Monitor
    • Incidents
  • Analytics
    • Analytics
    • Value stream
    • CI/CD
    • Repository
  • Wiki
    • Wiki
  • Snippets
    • Snippets
  • Activity
  • Graph
  • Create a new issue
  • Jobs
  • Commits
  • Issue Boards
Collapse sidebar
  • James Willenbring
  • Trilinos
  • Issues
  • #424

Closed
Open
Created Jun 08, 2016 by James Willenbring@jmwilleMaintainer

Tpetra BlockCrsMatrix (BCRS): Overlap communication & computation in apply()

Created by: mhoemmen

@trilinos/tpetra

Epic: #767.

Tpetra::Experimental::BlockCrsMatrix's sparse matrix-vector multiply lives in its apply method (which implements Tpetra::Operator::apply). Its implementation does not currently overlap communication and computation. Doing so could improve performance, as well as robustness of that performance to random small performance variation between MPI processes.

The fix would take the same form as the proposed fix for #385 (which see).

Assignee
Assign to
Time tracking