cuda.bindings._v2.driver.mem_import_from_shareable_handle#

cuda.bindings._v2.driver.mem_import_from_shareable_handle( intptr_t os_handle, int sh_handle_type, ) → uint64_t#

Imports an allocation from a requested shareable handle type.

If the current process cannot support the memory described by this shareable handle, this API will error as CUDA_ERROR_NOT_SUPPORTED. If sh_handle_type is CU_MEM_HANDLE_TYPE_FABRIC and the importer process has not been granted access to the same IMEX channel as the exporter process, this API will error as CUDA_ERROR_NOT_PERMITTED.

Parameters:

os_handle (intptr_t) – Shareable Handle representing the memory allocation that is to be imported.
sh_handle_type (MemAllocationHandleType) – handle type of the exported handle CUmemAllocationHandleType.

Returns:

CUDA Memory handle for the memory allocation.

Return type:

uint64_t

Note

Importing shareable handles exported from some graphics APIs(VUlkan, OpenGL, etc) created on devices under an SLI group may not be supported, and thus this API will return CUDA_ERROR_NOT_SUPPORTED. There is no guarantee that the contents of handle will be the same CUDA memory handle for the same given OS shareable handle, or the same underlying allocation.