cuda::experimental::mr::cudaMemAllocationHandleType
Defined in include/cuda/experimental/__memory_resource/device_memory_pool.cuh
-
enum class cuda::experimental::mr::cudaMemAllocationHandleType
Internal redefinition of
cudaMemAllocationHandleType
.Note
We need to define our own enum here because the earliest CUDA runtime version that supports asynchronous memory pools (CUDA 11.2) did not support these flags. See the cudaMemAllocationHandleType docs.
Values:
-
enumerator cudaMemHandleTypeNone
Does not allow any export mechanism.
-
enumerator cudaMemHandleTypePosixFileDescriptor
Allows a file descriptor to be used for exporting.
-
enumerator cudaMemHandleTypeWin32
Allows a Win32 NT handle to be used for exporting. (HANDLE)
-
enumerator cudaMemHandleTypeWin32Kmt
Allows a Win32 KMT handle to be used for exporting. (D3DKMT_HANDLE)
-
enumerator cudaMemHandleTypeFabric
Allows a fabric handle to be used for exporting. (cudaMemFabricHandle_t)
-
enumerator cudaMemHandleTypeNone