Skip to content

Implement light-weight K register ExtractMostSignificantBits for Vector512 #80820

Closed

Description

@anthonycanino

On Intel arch, ExtractMostSignificantBits for 512 bit vectors requires the use of the AVX512 opmask (K) registers. This task is to implement the capability of ExtractMostSignificantBits for Vector512 using a single opmask register. This is to allow Vector512 to be used in optimization, but without the implementation overhead of implementing full opmask register support in the register allocator, which will come at a later date.

Activity

  1. ghost added
    area-CodeGen-coreclrCLR JIT compiler in src/coreclr/src/jit and related components such as SuperPMI
    on Jan 18, 2023
  2. ghost added
    untriagedNew issue has not been triaged by the area owner
    on Jan 18, 2023
  3. added this to the 8.0.0 milestone on Jan 19, 2023
  4. ghost removed
    untriagedNew issue has not been triaged by the area owner
    on Jan 19, 2023
  5. added
    untriagedNew issue has not been triaged by the area owner
    avx512Related to the AVX-512 architecture
    and removed
    untriagedNew issue has not been triaged by the area owner
    on Jan 19, 2023
  6. anthonycanino commented on Feb 9, 2023

    @anthonycanino
    ContributorAuthor

    @JulieLeeMSFT you may assign me for tracking purposes.

  7. teo-tsirpanis commented on Mar 12, 2023

    @teo-tsirpanis
    Contributor

    Fixed by #82731.

  8. ghost locked as resolved and limited conversation to collaborators on Apr 11, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

Labels

area-CodeGen-coreclrCLR JIT compiler in src/coreclr/src/jit and related components such as SuperPMIavx512Related to the AVX-512 architecture

Type

No type

Projects

No projects

    Milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions