Class BurstTensorData

Represents Burst-specific internal data storage for a Tensor.

Inheritance

object

BurstTensorData

Implements

ITensorData

IDisposable

IDependableMemoryResource

IConvertibleToComputeTensorData

IReadableTensorData

Inherited Members

object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.MemberwiseClone()

object.ReferenceEquals(object, object)

Namespace: Unity.Sentis

Assembly: Unity.Sentis.dll

Syntax

public class BurstTensorData : ITensorData, IDisposable, IDependableMemoryResource, IConvertibleToComputeTensorData, IReadableTensorData

Constructors

BurstTensorData(int, bool)

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

Declaration

public BurstTensorData(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.

BurstTensorData(NativeTensorArray)

Initializes and returns an instance of BurstTensorData from a NativeTensorArray.

Declaration

public BurstTensorData(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

Clone()

Returns a deep copy of the internal storage.

Declaration

public ITensorData Clone()

Returns

Type	Description
ITensorData	Cloned internal storage.

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 BurstTensorData and any associated memory.

Declaration

public void Dispose()

Download<T>(int, int)

Returns data from internal storage.

Declaration

public NativeArray<T> Download<T>(int dstCount, int srcOffset = 0) where T : unmanaged

Parameters

Type	Name	Description
int	dstCount	The number of elements to download.
int	srcOffset	The index of the first element in the data.

Returns

Type	Description
NativeArray<T>	The downloaded data as a native array.

Type Parameters

Name	Description
T	The data type of the elements.

~BurstTensorData()

Finalizes the BurstTensorData.

Declaration

protected ~BurstTensorData()

GetReadOnlyNativeArrayHandle<T>(int, int)

Returns a ReadOnlyNativeArray handle on the linear memory data.

Declaration

public NativeArray<T>.ReadOnly GetReadOnlyNativeArrayHandle<T>(int dstCount, int srcOffset = 0) where T : unmanaged

Parameters

Type	Name	Description
int	dstCount	The number of elements in the array.
int	srcOffset	The index of the first element in the data.

Returns

Type	Description
NativeArray<T>.ReadOnly	NativeArray of elements.

Type Parameters

Name	Description
T	The data type of the elements.

Get<T>(int)

Returns a data element.

Declaration

public T Get<T>(int index) where T : unmanaged

Parameters

Type	Name	Description
int	index	The index of the element.

Returns

Type	Description
T	Data element.

Type Parameters

Name	Description
T	The data type of the element.

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 BurstTensorData 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
BurstTensorData	The pinned BurstTensorData.

ReadbackRequest(Action<bool>)

Schedules asynchronous readback of the internal data.

Declaration

public void ReadbackRequest(Action<bool> callback = null)

Parameters

Type	Name	Description
Action<bool>	callback	Callback invoked when async readback is finished. Return value indicates if async readback is successful.

ReadbackRequestAsync()

Schedules awaitable asynchronous readback of the internal data.

See AsyncReadbackRequest for more info

Declaration

public Task<bool> ReadbackRequestAsync()

Returns

Type	Description
Task<bool>	Whether awaitable task for when readback is successful.

Set<T>(int, T)

Sets value data element at index.

Declaration

public void Set<T>(int index, T value) where T : unmanaged

Parameters

Type	Name	Description
int	index	The index of the element to set.
T	value	The value to set for the element.

Type Parameters

Name	Description
T	The data type of the element.

ToArray<T>(int, int)

Returns an array that is a copy of the linear memory data.

Declaration

public T[] ToArray<T>(int dstCount, int srcOffset = 0) where T : unmanaged

Parameters

Type	Name	Description
int	dstCount	The number of elements in the array.
int	srcOffset	The index of the first element in the data.

Returns

Type	Description
T[]	Array of elements.

Type Parameters

Name	Description
T	The data type of the elements.

ToReadOnlySpan<T>(int, int)

Returns a ReadOnlySpan on the linear memory data.

Declaration

public ReadOnlySpan<T> ToReadOnlySpan<T>(int dstCount, int srcOffset = 0) where T : unmanaged

Parameters

Type	Name	Description
int	dstCount	The number of elements to span.
int	srcOffset	The index of the first element in the data.

Returns

Type	Description
ReadOnlySpan<T>	Span of elements.

Type Parameters

Name	Description
T	The data type of the elements.

ToString()

Returns a string that represents the BurstTensorData.

Declaration

public override string ToString()

Returns

Type	Description
string	The string summary of the BurstTensorData.

Overrides

object.ToString()

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

Uploads data to internal storage.

Declaration

public void Upload<T>(NativeArray<T> data, int srcCount, int srcOffset = 0) where T : unmanaged

Parameters

Type	Name	Description
NativeArray<T>	data	The data to upload as a native array.
int	srcCount	The number of elements to upload.
int	srcOffset	The index of the first element in the native array.

Type Parameters

Name	Description
T	The data type of the elements.

Implements

ITensorData

IDisposable

IDependableMemoryResource

IConvertibleToComputeTensorData

IReadableTensorData