MemoryPointer: ensure CUdeviceptr used with NVIDIA binding
#328
Conversation
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
|
Auto-sync is disabled for draft pull requests in this repository. Workflows must be run manually. Contributors can view more details about this message here. |
Contributor
Author
|
/ok to test |
Contributor
Author
|
/ok to test |
gmarkall
added
3 - Ready for Review
|
Auto-sync is disabled for ready for review pull requests in this repository. Workflows must be run manually. Contributors can view more details about this message here. |
The docs state that `pointer` should be a `c_void_p`, but the rest of the driver binding code expects the pointer to be represented as a `CUdeviceptr` when the NVIDIA bindings are in use. If we're given a `c_void_p` by the user when using the NVIDIA bindings, we can work around this by converting it to a `CUdeviceptr`. This was first noticed when testing PyArrow with Numba-CUDA. See apache/arrow#47128
gmarkall
force-pushed
the
memorypointer-type-fix
branch
from
e8f88e5 to
0f8ea88
Compare
Contributor
Author
|
/ok to test |
kkraus14
approved these changes
Jul 18, 2025
gmarkall
added a commit
to gmarkall/numba-cuda
that referenced
this pull request
Jul 18, 2025
- Add deadlock warnings to Stream.add_callback and Stream.async_done docstrings (NVIDIA#321) - `MemoryPointer`: ensure `CUdeviceptr` used with NVIDIA binding (NVIDIA#328) - Fix indexing GPUs with CUdevice object (NVIDIA#319) - Fix bindings: consistency of contexts, streams, and events, similar to NVIDIA#295 (NVIDIA#296) - Fix nvrtc resolution when CUDA_HOME env is set (NVIDIA#314)
Merged
gmarkall
added a commit
that referenced
this pull request
Jul 18, 2025
- Add deadlock warnings to Stream.add_callback and Stream.async_done docstrings (#321) - `MemoryPointer`: ensure `CUdeviceptr` used with NVIDIA binding (#328) - Fix indexing GPUs with CUdevice object (#319) - Fix bindings: consistency of contexts, streams, and events, similar to #295 (#296) - Fix nvrtc resolution when CUDA_HOME env is set (#314)
atmnp
pushed a commit
to atmnp/numba-cuda
that referenced
this pull request
Jul 21, 2025
…A#328) * `MmemoryPointer` ensure `CUdeviceptr` used with NVIDIA binding The docs state that `pointer` should be a `c_void_p`, but the rest of the driver binding code expects the pointer to be represented as a `CUdeviceptr` when the NVIDIA bindings are in use. If we're given a `c_void_p` by the user when using the NVIDIA bindings, we can work around this by converting it to a `CUdeviceptr`. This was first noticed when testing PyArrow with Numba-CUDA. See apache/arrow#47128 * Correct device pointer value usage in EMM test
atmnp
pushed a commit
to atmnp/numba-cuda
that referenced
this pull request
Jul 21, 2025
- Add deadlock warnings to Stream.add_callback and Stream.async_done docstrings (NVIDIA#321) - `MemoryPointer`: ensure `CUdeviceptr` used with NVIDIA binding (NVIDIA#328) - Fix indexing GPUs with CUdevice object (NVIDIA#319) - Fix bindings: consistency of contexts, streams, and events, similar to NVIDIA#295 (NVIDIA#296) - Fix nvrtc resolution when CUDA_HOME env is set (NVIDIA#314)
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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.
The docs state that
pointershould be ac_void_p, but the rest of the driver binding code expects the pointer to be represented as aCUdeviceptrwhen the NVIDIA bindings are in use.If we're given a
c_void_pby the user when using the NVIDIA bindings, we can work around this by converting it to aCUdeviceptr.This was first noticed when testing PyArrow with Numba-CUDA. See apache/arrow#47128