Interface ITensorData

Interface for device-dependent storage of tensor data.

Inherited Members
Namespace: Unity.InferenceEngine
Assembly: Unity.InferenceEngine.dll
Syntax
[MovedFrom("Unity.Sentis")]
public interface ITensorData : IDisposable
Remarks

ITensorData abstracts where tensor elements are physically stored (CPU, GPU compute, or GPU pixel). A Tensor holds an ITensorData instance via dataOnBackend.

Implementations
Use CPUTensorData for CPU storage (Burst-compatible, Job system). Use ComputeTensorData for GPU compute buffers. Use TextureTensorData for GPU texture-backed storage.

Data transfer
Call Upload<T>(NativeArray<T>, int) to copy data into the backing storage. Call Download<T>(int) to copy data out (blocking), or ReadbackRequest() and IsReadbackRequestDone() for async readback. Call CompleteAllPendingOperations() before accessing data when operations may be pending.

Lifetime
Implementations manage native resources. Call Dispose() when finished. Ownership typically belongs to the tensor; do not dispose separately when the tensor owns the data.

Examples

Pin a tensor to CPU and access its data.

var cpuData = CPUTensorData.Pin(inputTensor);
var job = new MyJob { data = cpuData.array.GetNativeArrayHandle<float>() };
cpuData.fence = job.Schedule(inputTensor.shape.length, 64);
worker.Schedule(inputTensor);
cpuData.CompleteAllPendingOperations();
cpuData.Dispose();

Properties

backendType

The device backend (CPU, GPU compute, or GPU pixel) where the tensor data is stored.

Declaration
BackendType backendType { get; }
Property Value
Type Description
BackendType
Remarks

Returns CPU, GPUCompute, or GPUPixel. Use this to determine whether data is on CPU or GPU before calling Download<T>(int) or scheduling Jobs that access the buffer.

See Also

maxCapacity

The maximum count of the stored data elements.

Declaration
int maxCapacity { get; }
Property Value
Type Description
int
See Also

Methods

CompleteAllPendingOperations()

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

Declaration
void CompleteAllPendingOperations()
Remarks

Call before reading data via Download<T>(int) or IsReadbackRequestDone() when Jobs or GPU operations may still be in progress. For CPU backends, this completes any scheduled Jobs. For GPU backends, this waits for any in-flight transfers.

Examples

Complete pending jobs, then download.

cpuData.fence = job.Schedule(count, 64);
worker.Schedule(inputTensor);
cpuData.CompleteAllPendingOperations();
var data = cpuData.Download<float>(count);
See Also

DownloadAsync<T>(int)

Awaitable contiguous block of data from internal storage.

Declaration
Awaitable<NativeArray<T>> DownloadAsync<T>(int dstCount) where T : unmanaged
Parameters
Type Name Description
int dstCount

The number of elements to copy.
Returns
Type Description
Awaitable<NativeArray<T>>

An Awaitable_1 that resolves to a NativeArray_1 containing the copied data.
Type Parameters
Name Description
T

The element type of the data (for example, float or int).
Remarks

Use this to download data without blocking the main thread. For GPU backends, the readback runs asynchronously. The returned array uses Temp. Dispose of it when finished.

Examples

Download without blocking the main thread.

var data = await tensorData.DownloadAsync<float>(count);
float value = data[0];
data.Dispose();
See Also

Download<T>(int)

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

Declaration
NativeArray<T> Download<T>(int dstCount) where T : unmanaged
Parameters
Type Name Description
int dstCount

The number of elements to copy.
Returns
Type Description
NativeArray<T>

A new NativeArray_1 containing the copied data.
Type Parameters
Name Description
T

The element type of the data (for example, float or int).
Remarks

Blocks until the data is available. For GPU backends, this may trigger a synchronous readback. The returned array uses Temp. Dispose of it or use it within the same frame. Call CompleteAllPendingOperations() first if Jobs or GPU work may be pending.

Examples

Wait for operations, download data, and dispose the array.

tensorData.CompleteAllPendingOperations();
var data = tensorData.Download<float>(count);
float value = data[0];
data.Dispose();
See Also

IsReadbackRequestDone()

Checks if asynchronous readback request is done.

Declaration
bool IsReadbackRequestDone()
Returns
Type Description
bool

true if the readback has completed. Otherwise false.
Remarks

Use after calling ReadbackRequest() to poll for completion. When this returns true, the data is available for CPU access. For CPU backends, this completes any pending Job operations and returns true when ready.

Examples

Poll for readback completion, then download.

tensorData.ReadbackRequest();
while (!tensorData.IsReadbackRequestDone())
    await Task.Yield();
var data = tensorData.Download<float>(count);
See Also

ReadbackRequest()

Schedules asynchronous readback of the internal data.

Declaration
void ReadbackRequest()
Remarks

For GPU backends, initiates a non-blocking transfer from device to CPU. Poll IsReadbackRequestDone() to check completion, then call Download<T>(int) to obtain the data. For CPU backends, this is a no-op; data is already on CPU.

Examples

Schedule async readback.

tensorData.ReadbackRequest();
// Continue other work, then check IsReadbackRequestDone()
See Also

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

Uploads a contiguous block of tensor data to internal storage.

Declaration
void Upload<T>(NativeArray<T> data, int srcCount) where T : unmanaged
Parameters
Type Name Description
NativeArray<T> data

The source data to copy.
int srcCount

The number of elements to copy from data.
Type Parameters
Name Description
T

The element type of the data (for example, float or int).
Remarks

Copies srcCount elements from data into the internal buffer. For GPU backends, this transfers data from CPU to the device. Call CompleteAllPendingOperations() before reading the uploaded data if other operations may be pending.

Examples

Upload data to backing storage and wait for completion.

var data = new NativeArray<float>(256, Allocator.Temp);
// Fill data
tensorData.Upload(data, 256);
tensorData.CompleteAllPendingOperations();
See Also

See Also