Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[FEA] Allow libraries that implement __array_ufunc__ to override CUDAUFuncDispatcher #36

Closed
gmarkall opened this issue Aug 1, 2024 · 1 comment
Labels
duplicate This issue or pull request already exists feature request New feature or request

Comments

@gmarkall
Copy link
Collaborator

gmarkall commented Aug 1, 2024

Details / notes:

From Allow libraries that implement array_ufunc to override CUDAUFuncDispatcher on the Numba Discourse.

There was a PR implementing this for the CPU target: numba/numba#8995

A related issue on the Awkward issue tracker: scikit-hep/awkward#3179

This is to support using Coffea on CUDA.

cc @ianna @lgray

Initial thoughts:

I am not able to dig deep into this right now, but there are a couple of additional potential hurdles for the CUDA target:

  • The CUDA Ufunc mechanism doesn't yet support dynamic Ufuncs, which seem to be a part of the implementation of the PR for the CPU target.
  • The __array_ufunc__ mechanism seems CPU-centric - will we need to define a new __cuda_array_ufunc__ mechanism for this to be practical? c.f. __cuda_array_interface__ vs. __array_interface__.
@gmarkall gmarkall added the feature request New feature or request label Aug 1, 2024
@gmarkall gmarkall added the duplicate This issue or pull request already exists label Aug 1, 2024
@gmarkall
Copy link
Collaborator Author

gmarkall commented Aug 1, 2024

See #37, which is a better-written request.

@gmarkall gmarkall closed this as completed Aug 1, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
duplicate This issue or pull request already exists feature request New feature or request
Projects
None yet
Development

No branches or pull requests

1 participant