Skip to content

cuda.core.launch() improvements #150

Open
3 of 6 issues completed
Open

Description

@leofang
  • Support ctypes/numpy structs
    • make sure ctypes is deprioritized
  • Support converting arbitrary objects to StridedMemoryView
  • Benchmarking
    • measure launch() overhead
    • reimplement type dispatcher via dict lookup instead of conditional branching

Activity

  1. added
    enhancementAny code-related improvements
    P1Medium priority - Should do
    on Oct 10, 2024
  2. added this to the cuda.core beta 2 milestone on Oct 10, 2024
  3. self-assigned this
    on Oct 10, 2024
  4. added
    cuda.coreEverything related to the cuda.core module
    on Oct 10, 2024
  5. leofang commented on Dec 16, 2024

    @leofang
    MemberAuthor
    • Support converting arbitrary objects to StridedMemoryView

    If we make this a two-step approach, where the 1st step is to simply accept passing a StridedMemoryView object to launch() as a kernel launch argument, then this would be doable once #180 (comment) is done.

  6. added
    cuda.coreEverything related to the cuda.core module
    and removed
    cuda.coreEverything related to the cuda.core module
    on Apr 2, 2026
  7. removed this from the cuda.core backlog milestone on Apr 2, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

Labels

P1Medium priority - Should docuda.coreEverything related to the cuda.core moduleenhancementAny code-related improvements

Type

No type

Projects

No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions