Repository navigation
Allow NumPy data types as arguments - #2335
Open
ndgrigorian wants to merge 2 commits into
Open
ndgrigorian wants to merge 2 commits into
ndgrigorian wants to merge 2 commits into
Conversation
|
View rendered docs @ https://intelpython.github.io/dpctl/pulls/2335/index.html |
Collaborator
|
coverage: 75.218% (+0.2%) from 74.989% — add-dpctl-dtypes into master |
ndgrigorian
force-pushed
the
add-dpctl-dtypes
branch
from
November 2, 2026 18:22
3038c6e to
453e2d4
Compare
Scalar kernel arguments are passed by size, so any numpy data type with plain-byte values works, including ml_dtypes types. copy, fill, LocalAccessor, WorkGroupMemory and SpecializationConstant accept any form numpy.dtype does. Adds a bfloat16 pybind11 type caster.
ndgrigorian
force-pushed
the
add-dpctl-dtypes
branch
from
November 2, 2026 21:41
453e2d4 to
3575f77
Compare
ndgrigorian
changed the title
ndgrigorian
marked this pull request as ready for review
November 2, 2026 21:55
ndgrigorian
requested review from
antonwolfy and
vlad-perevezentsev
as code owners
November 2, 2026 21:55
This branch has not been deployed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This PR proposes to let any NumPy data type whose values are plain bytes be used as a kernel argument type and wherever dpctl takes a data type. That includes structured data types and types other packages register with NumPy, notably
ml_dtypes(bfloat16,complex32,bcomplex32, the float8 types, etc.)Previously, complex scalars and float16 could not be passed to kernels, as ctypes lacks either of these constructs, and
LocalAccessor,WorkGroupMemory,SyclQueue.copyandSyclQueue.filleach accepted only their own fixed list of type strings.Additionally,
dpctl4pybind11.hppadds a type caster forsycl::ext::oneapi::bfloat16, defined when the compiler provides the appropriate extension.Closes #72