Skip to content
GitLab
Projects Groups Topics Snippets
  • /
  • Help
    • Help
    • Support
    • Community forum
    • Submit feedback
    • Contribute to GitLab
  • Register
  • Sign in
  • mesa mesa
  • Project information
    • Project information
    • Activity
    • Labels
    • Members
  • Repository
    • Repository
    • Files
    • Commits
    • Branches
    • Tags
    • Contributor statistics
    • Graph
    • Compare revisions
  • Issues 3.2k
    • Issues 3.2k
    • List
    • Boards
    • Service Desk
    • Milestones
  • Merge requests 1k
    • Merge requests 1k
  • CI/CD
    • CI/CD
    • Pipelines
    • Jobs
    • Schedules
  • Deployments
    • Deployments
    • Releases
  • Packages and registries
    • Packages and registries
    • Container Registry
  • Analytics
    • Analytics
    • Value stream
    • CI/CD
    • Repository
  • Activity
  • Graph
  • Create a new issue
  • Jobs
  • Commits
  • Issue Boards
Collapse sidebar
  • MesaMesa
  • mesamesa
  • Merge requests
  • !3101

WIP: freedreno/ir3: post-RA sched pass

  • Review changes

  • Download
  • Patches
  • Plain diff
Closed Rob Clark requested to merge robclark/mesa:wip/post-sched into master Dec 14, 2019
  • Overview 1
  • Commits 10
  • Pipelines 34
  • Changes 15

looking at manhattan, even without RA doing round-robin register allocation, this is ~8% drop in instruction count with matching fps win.. looking at individual shaders, there are some wins but also some losses, so it is possible that the instruction selection or something else is still not optimal.

I expect if we had a good way to pick a target register usage to round-robin between in RA step, the post-ra sched pass would be more effective.

Edited Dec 20, 2019 by Rob Clark
Assignee
Assign to
Reviewers
Request review from
Time tracking
Source branch: wip/post-sched