Class ComputeTensorData

Tensor data storage for GPU backends

Inheritance
Object
UniqueResource
ComputeTensorData
Inherited Members
Namespace: Unity.Barracuda
Syntax
public class ComputeTensorData : UniqueResource, ITensorData, IDisposable, ITensorDataStatistics, IUniqueResource

Constructors

ComputeTensorData(ComputeBuffer, TensorShape, Int32, String, ComputeInfo.ChannelsOrder)

Create ComputeTensorData with specified buffer

Declaration
public ComputeTensorData(ComputeBuffer buffer, TensorShape shape, int offset, string buffername, ComputeInfo.ChannelsOrder onDeviceChannelsOrder)
Parameters
Type Name Description
ComputeBuffer buffer

buffer
TensorShape shape

shape
Int32 offset

offset
String buffername

buffer name
ComputeInfo.ChannelsOrder onDeviceChannelsOrder

channels order

ComputeTensorData(TensorShape, String, ComputeInfo.ChannelsOrder, Boolean)

Create ComputeTensorData

Declaration
public ComputeTensorData(TensorShape shape, string buffername, ComputeInfo.ChannelsOrder onDeviceChannelsOrder, bool clearOnInit = true)
Parameters
Type Name Description
TensorShape shape

shape
String buffername

buffer name
ComputeInfo.ChannelsOrder onDeviceChannelsOrder

channel order
Boolean clearOnInit

clear on init

Fields

name

Parent Tensor name

Declaration
public string name
Field Value
Type Description
String

Properties

buffer

Data storage as ComputeBuffer

Declaration
public ComputeBuffer buffer { get; }
Property Value
Type Description
ComputeBuffer

channelsOrder

Channel order channels-first vs channels-last

Declaration
public ComputeInfo.ChannelsOrder channelsOrder { get; }
Property Value
Type Description
ComputeInfo.ChannelsOrder

inUse

Returns true if this tensor data is attached to any tensor.

Declaration
public virtual bool inUse { get; }
Property Value
Type Description
Boolean
Implements

isGPUMem

Returns true if this tensor data is reserved as GPU memory.

Declaration
public virtual bool isGPUMem { get; }
Property Value
Type Description
Boolean
Implements

maxCapacity

Returns the maximum number of element this tensorData can contain.

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

offset

Offset in the data storage buffer

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

Methods

Dispose()

Dispose internal storage

Declaration
public virtual void Dispose()

Download(TensorShape)

Returns an array filled with the values of a tensor. Depending on the implementation and underlying device this array might be a copy or direct reference to the tensor values. This is a blocking call, unless data from device was requested via ScheduleAsyncDownload beforehand and has already arrived.

Declaration
public virtual float[] Download(TensorShape shape)
Parameters
Type Name Description
TensorShape shape

the TensorShape (and thus length) of the data to copy
Returns
Type Description
Single[]

Tensor data as float arrary
Implements

Finalize()

Finalizer

Declaration
protected void Finalize()

Reserve(Int32)

Reserve uninitialized memory.

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

element count to reserve
Implements

ScheduleAsyncDownload(Int32)

Schedule an asynchronous download from device memory. count is the number of element to readback.

Declaration
public virtual bool ScheduleAsyncDownload(int count)
Parameters
Type Name Description
Int32 count

count of elements to download
Returns
Type Description
Boolean

false until data from device arrives to CPU and is ready for access
Implements

SharedAccess(out Int32)

Returns an array filled with the values of multiple tensors that share the same tensorData on device. Depending on the implementation and underlying device this array might be a copy or direct reference to tensor values, no conversion from on device memory layout will occur. This is a blocking call, unless data from device was requested via ScheduleAsyncDownload beforehand and has already arrived.

Declaration
public virtual float[] SharedAccess(out int offset)
Parameters
Type Name Description
Int32 offset

This function outputs offset from the beginning of the array to location of values for specific tensor. offset parameters is specified in float elements
Returns
Type Description
Single[]

array filled with the values of multiple tensors that share the same tensorData on device
Implements

ToString()

Summary

Declaration
public override string ToString()
Returns
Type Description
String

summary

Upload(Single[], TensorShape, Int32)

Initialize with data. shape is the TensorShape (and thus length) of the data to copy. managedBufferStartIndex is the offset where to start the copy in the data

Declaration
public virtual void Upload(float[] data, TensorShape shape, int managedBufferStartIndex = 0)
Parameters
Type Name Description
Single[] data

data as float array
TensorShape shape

Tensor shape
Int32 managedBufferStartIndex

managed buffer start index
Implements