cuda::experimental::cudaMemAllocationHandleType

enum class cuda::experimental::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 = 0x0

Does not allow any export mechanism.

enumerator cudaMemHandleTypePosixFileDescriptor = 0x1

Allows a file descriptor to be used for exporting.

enumerator cudaMemHandleTypeWin32 = 0x2

Allows a Win32 NT handle to be used for exporting. (HANDLE)

enumerator cudaMemHandleTypeWin32Kmt = 0x4

Allows a Win32 KMT handle to be used for exporting. (D3DKMT_HANDLE)

enumerator cudaMemHandleTypeFabric = 0x8

Allows a fabric handle to be used for exporting. (cudaMemFabricHandle_t)