Class CPUTensorData

Represents Burst-specific internal data storage for a Tensor.

Inheritance

object

CPUTensorData

Implements

ITensorData

IDisposable

Inherited Members

object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.MemberwiseClone()

object.ReferenceEquals(object, object)

Namespace: Unity.InferenceEngine

Assembly: Unity.InferenceEngine.dll

Syntax

[MovedFrom("Unity.Sentis")]
public class CPUTensorData : ITensorData, IDisposable

Constructors

CPUTensorData(int, bool)

Initializes and returns an instance of CPUTensorData, and allocates storage for a tensor with the shape of shape.

Declaration

public CPUTensorData(int count, bool clearOnInit = false)

Parameters

Type	Name	Description
int	count	The number of elements.
bool	clearOnInit	Whether to zero the data on allocation. The default value is false.

CPUTensorData(NativeTensorArray)

Initializes and returns an instance of CPUTensorData from a NativeTensorArray.

Declaration

public CPUTensorData(NativeTensorArray data)

Parameters

Type	Name	Description
NativeTensorArray	data	The elements of the tensor data as a NativeTensorArray.

Properties

array

The NativeTensorArray managed array containing the Tensor data.

Declaration

public NativeTensorArray array { get; }

Property Value

Type	Description
NativeTensorArray

backendType

On what backend are the data elements stored.

Declaration

public BackendType backendType { get; }

Property Value

Type	Description
BackendType

fence

A read fence job handle. You can use fence as a dependsOn argument when you schedule a job that reads data. The job will start when the tensor data is ready for read access.

Declaration

public JobHandle fence { get; set; }

Property Value

Type	Description
JobHandle

maxCapacity

The maximum count of the stored data elements.

Declaration

public int maxCapacity { get; }

Property Value

Type	Description
int

rawPtr

The raw memory pointer for the resource.

Declaration

public void* rawPtr { get; }

Property Value

Type	Description
void*

reuse

A write fence job handle. You can use reuse as a dependsOn argument when you schedule a job that reads data. The job will start when the tensor data is ready for write access.

Declaration

public JobHandle reuse { get; set; }

Property Value

Type	Description
JobHandle

Methods

CompleteAllPendingOperations()

Blocking call to make sure that internal data is correctly written to and available for CPU read back.

Declaration

public void CompleteAllPendingOperations()

ConvertToComputeTensorData(int)

Implement this method to convert to ComputeTensorData.

Declaration

public ComputeTensorData ConvertToComputeTensorData(int count)

Parameters

Type	Name	Description
int	count

Returns

Type	Description
ComputeTensorData	Converted ComputeTensorData.

Dispose()

Disposes of the CPUTensorData and any associated memory.

Declaration

public void Dispose()

DownloadAsync<T>(int)

Awaitable contiguous block of data from internal storage.

Declaration

public Awaitable<NativeArray<T>> DownloadAsync<T>(int dstCount) where T : unmanaged

Parameters

Type	Name	Description
int	dstCount	The number of elements to download.

Returns

Type	Description
Awaitable<NativeArray<T>>	A awaitable native array of downloaded elements.

Type Parameters

Name	Description
T	The data type of the elements.

Download<T>(int)

Blocking call that returns a contiguous block of data from internal storage.

Declaration

public NativeArray<T> Download<T>(int dstCount) where T : unmanaged

Parameters

Type	Name	Description
int	dstCount	The number of elements to download.

Returns

Type	Description
NativeArray<T>	A native array of downloaded elements.

Type Parameters

Name	Description
T	The data type of the elements.

~CPUTensorData()

Finalizes the CPUTensorData.

Declaration

protected ~CPUTensorData()

IsReadbackRequestDone()

Checks if asynchronous readback request is done.

Declaration

public bool IsReadbackRequestDone()

Returns

Type	Description
bool	Whether async readback is successful.

Pin(Tensor, bool)

Moves a tensor into memory on the CPU backend device.

Declaration

public static CPUTensorData Pin(Tensor X, bool clearOnInit = false)

Parameters

Type	Name	Description
Tensor	X	The Tensor to move to the CPU.
bool	clearOnInit	Whether to initialize the backend data. The default value is true.

Returns

Type	Description
CPUTensorData	The pinned CPUTensorData.

ReadbackRequest()

Schedules asynchronous readback of the internal data.

Declaration

public void ReadbackRequest()

ToString()

Returns a string that represents the CPUTensorData.

Declaration

public override string ToString()

Returns

Type	Description
string	The string summary of the CPUTensorData.

Overrides

object.ToString()

Upload<T>(NativeArray<T>, int)

Uploads a contiguous block of tensor data to internal storage.

Declaration

public void Upload<T>(NativeArray<T> data, int srcCount) where T : unmanaged

Parameters

Type	Name	Description
NativeArray<T>	data	The data to upload.
int	srcCount	The number of elements to upload.

Type Parameters

Name	Description
T	The type of data to upload.

Implements

ITensorData

IDisposable