Class BurstTensorData

Represents Burst-specific internal data storage for a Tensor.

Inheritance
Object
BurstTensorData
Inherited Members
Namespace: Unity.Sentis
Syntax
public class BurstTensorData : ITensorData, IDisposable, IDependableMemoryResource, IConvertibleToComputeTensorData, IConvertibleToArrayTensorData

Constructors

BurstTensorData(ArrayTensorData)

Initializes and returns an instance of BurstTensorData from an ArrayTensorData.

Declaration
public BurstTensorData(ArrayTensorData sharedArray)
Parameters
Type Name Description
ArrayTensorData sharedArray

The ArrayTensorData to convert.

BurstTensorData(SharedArrayTensorData)

Initializes and returns an instance of BurstTensorData from a SharedArrayTensorData.

Declaration
public BurstTensorData(SharedArrayTensorData sharedArray)
Parameters
Type Name Description
SharedArrayTensorData sharedArray

The SharedArrayTensorData to convert.

BurstTensorData(TensorShape, Array)

Initializes and returns an instance of BurstTensorData from a TensorShape and an Array.

Declaration
public BurstTensorData(TensorShape shape, Array data)
Parameters
Type Name Description
TensorShape shape

The shape of the tensor data.
Array data

The values of the tensor data as an Array.

BurstTensorData(TensorShape, Boolean)

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

Declaration
public BurstTensorData(TensorShape shape, bool clearOnInit = true)
Parameters
Type Name Description
TensorShape shape

The shape of the tensor data to allocate.
Boolean clearOnInit

Whether to zero the data on allocation. The default value is true.

BurstTensorData(TensorShape, NativeTensorArray, Int32)

Initializes and returns an instance of BurstTensorData from a NativeTensorArray and an offset.

Declaration
public BurstTensorData(TensorShape shape, NativeTensorArray data, int offset = 0)
Parameters
Type Name Description
TensorShape shape

The shape of the tensor data.
NativeTensorArray data

The values of the tensor data as a NativeTensorArray.
Int32 offset

The integer offset for the backing data.

Properties

array

The NativeTensorArray managed array containing the Tensor data.

Declaration
public NativeTensorArray array { get; }
Property Value
Type Description
NativeTensorArray

count

The length of the tensor using this data.

Declaration
public int count { get; }
Property Value
Type Description
Int32

deviceType

On what device backend are the data elements stored

Declaration
public virtual DeviceType deviceType { get; }
Property Value
Type Description
DeviceType
Implements

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
Implements

maxCapacity

The maximum count of the stored data elements.

Declaration
public int maxCapacity { get; }
Property Value
Type Description
Int32
Implements

offset

The integer offset for the backing data.

Declaration
public int offset { get; }
Property Value
Type Description
Int32

rawPtr

The raw memory pointer for the resource.

Declaration
public void *rawPtr { get; }
Property Value
Type Description
Void*
Implements

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
Implements

shape

The shape of the tensor using this data as a TensorShape.

Declaration
public TensorShape shape { get; }
Property Value
Type Description
TensorShape

Methods

ConvertToArrayTensorData(TensorShape)

Implement this method to convert to ArrayTensorData.

Declaration
public ArrayTensorData ConvertToArrayTensorData(TensorShape shape)
Parameters
Type Name Description
TensorShape shape
Returns
Type Description
ArrayTensorData
Implements

ConvertToComputeTensorData(TensorShape)

Implement this method to convert to ComputeTensorData.

Declaration
public ComputeTensorData ConvertToComputeTensorData(TensorShape shape)
Parameters
Type Name Description
TensorShape shape
Returns
Type Description
ComputeTensorData
Implements

Dispose()

Disposes of the BurstTensorData and any associated memory.

Declaration
public void Dispose()
Implements

Download<T>(Int32, Int32)

Returns data from internal storage.

Declaration
public T[] Download<T>(int dstCount, int srcOffset = 0)
    where T : struct
Parameters
Type Name Description
Int32 dstCount
Int32 srcOffset
Returns
Type Description
T[]
Type Parameters
Name Description
T
Implements

Finalize()

Finalizes the BurstTensorData.

Declaration
protected void Finalize()

Pin(Tensor, Boolean)

Moves a tensor into memory on the CPU backend device.

Declaration
public static BurstTensorData Pin(Tensor X, bool uploadCache = true)
Parameters
Type Name Description
Tensor X

The Tensor to move to the CPU.
Boolean uploadCache

Whether to also move the existing tensor data to the CPU. The default value is true.
Returns
Type Description
BurstTensorData

Reserve(Int32)

Reserves storage for count elements.

Declaration
public void Reserve(int count)
Parameters
Type Name Description
Int32 count
Implements

ScheduleAsyncDownload()

Schedules asynchronous download of internal data.

Declaration
public bool ScheduleAsyncDownload()
Returns
Type Description
Boolean

true if the download has finished.
Implements

SharedAccess(out Int32)

Returns the backing data and outputs the offset.

Declaration
public NativeTensorArray SharedAccess(out int offset)
Parameters
Type Name Description
Int32 offset

The integer offset in the backing data.
Returns
Type Description
NativeTensorArray

The internal NativeTensorArray backing data.

ToString()

Returns a string that represents the BurstTensorData.

Declaration
public override string ToString()
Returns
Type Description
String
Overrides

Upload<T>(T[], Int32, Int32)

Uploads data to internal storage.

Declaration
public void Upload<T>(T[] data, int srcCount, int srcOffset = 0)
    where T : struct
Parameters
Type Name Description
T[] data
Int32 srcCount
Int32 srcOffset
Type Parameters
Name Description
T
Implements