Skip to content

[cuda.compute]: fix alignment not being set properly for gpu_struct types #6995

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.

Sign up for GitHub

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

Merged
NaderAlAwar merged 1 commit into from
Dec 16, 2025
Merged

[cuda.compute]: fix alignment not being set properly for gpu_struct types #6995

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 11 additions & 1 deletion python/cuda_cccl/cuda/compute/_cccl_interop.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -94,7 +94,17 @@ def _numpy_type_to_info(numpy_type: np.dtype) -> TypeInfo:
def _device_array_to_cccl_iter(array: DeviceArrayLike) -> Iterator:
if not is_contiguous(array):
raise ValueError("Non-contiguous arrays are not supported.")
info = _numpy_type_to_info(get_dtype(array))
dtype = get_dtype(array)

# Handle structured dtypes by creating a proper gpu_struct
if dtype.type == np.void:
from .struct import gpu_struct

numba_type = as_numba_type(gpu_struct(dtype))
info = _numba_type_to_info(numba_type)
else:
info = _numpy_type_to_info(dtype)

state_info = _numpy_type_to_info(np.intp)
return Iterator(
state_info.alignment,
Expand Down
Loading