cuda.core.experimental
API Reference¶
All of the APIs listed (or cross-referenced from) below are considered experimental
and subject to future changes without deprecation notice. Once stablized they will be
moved out of the experimental
namespace.
CUDA runtime¶
|
Represent a GPU and act as an entry point for cuda.core features. |
|
Launches a |
|
Customizable |
|
Customizable |
|
Customizable launch options. |
CUDA compilation toolchain¶
|
Represent a compilation machinery to process programs into |
|
Represent a linking machinery to link one or multiple object codes into |
|
Customizable |
CUDA system information¶
- cuda.core.experimental.system.driver_version¶
Query the CUDA driver version.
Returns
- tuple of int
A 2-tuple of (major, minor) version numbers.
- cuda.core.experimental.system.num_devices¶
Query the number of available GPUs.
Returns
- int
The number of available GPU devices.
- cuda.core.experimental.system.devices¶
Query the available device instances.
Returns
- tuple of Device
A tuple containing instances of available devices.
Utility functions¶
Decorator to create proxy objects to |
|
|
A dataclass holding metadata of a strided dense array/tensor. |