cuda.core.Program#

class cuda.core.Program(
code: str | bytes | bytearray,
str code_type: str,
options: ProgramOptions | None = None,
)#

Represent a compilation machinery to process programs into ObjectCode.

This object provides a unified interface to multiple underlying compiler libraries. Compilation support is enabled for a wide range of code types and compilation types.

Parameters:

  • code (str | bytes | bytearray) – The source code to compile. For C++ and PTX, must be a string. For NVVM IR, can be str, bytes, or bytearray.

  • code_type (str) – The type of source code. Must be one of "c++", "ptx", or "nvvm".

  • options (ProgramOptions, optional) – Options to customize the compilation process.

Methods

__init__(*args, **kwargs)#
close(self)#

Destroy this program.

compile(
self,
str target_type: str,
name_expressions: tuple | list = (),
logs=None,
) → ObjectCode#

Compile the program to the specified target type.

Parameters:

  • target_type (str) – The compilation target. Must be one of "ptx", "cubin", or "ltoir".

  • name_expressions (tuple | list, optional) – Sequence of name expressions to make accessible in the compiled code. Used for template instantiation and similar cases.

  • logs (object, optional) – Object with a write method to receive compilation logs.

Returns:

The compiled object code.

Return type:

ObjectCode

static driver_can_load_nvrtc_ptx_output() → bool#

Check if the CUDA driver can load PTX generated by NVRTC.

NVRTC generates PTX targeting a specific CUDA version. If the installed driver is older than the NVRTC version, it may not be able to load the generated PTX.

Returns:

True if the driver version is new enough to load PTX generated by the current NVRTC version, False otherwise.

Return type:

bool

Examples

>>> if Program.driver_can_load_nvrtc_ptx_output():
...     obj = program.compile("ptx")
...     kernel = obj.get_kernel("my_kernel")

Attributes