Class CpuVectorAddKernel

Namespace

Orleans.GpuBridge.Runtime

Assembly

Orleans.GpuBridge.Runtime.dll

CPU-based vector addition kernel that processes float arrays and returns their element-wise sum. Used for testing and CPU fallback scenarios.

public sealed class CpuVectorAddKernel : GpuKernelBase<float[], float>, IGpuKernel<float[], float>, IDisposable

Inheritance

object

GpuKernelBase<float[], float>

CpuVectorAddKernel

Implements

IGpuKernel<float[], float>

IDisposable

Inherited Members

GpuKernelBase<float[], float>.KernelId

GpuKernelBase<float[], float>.DisplayName

GpuKernelBase<float[], float>.BackendProvider

GpuKernelBase<float[], float>.IsInitialized

GpuKernelBase<float[], float>.IsGpuAccelerated

GpuKernelBase<float[], float>.InitializeAsync(CancellationToken)

GpuKernelBase<float[], float>.ExecuteAsync(float[], CancellationToken)

GpuKernelBase<float[], float>.ExecuteBatchAsync(float[][], CancellationToken)

GpuKernelBase<float[], float>.GetEstimatedExecutionTimeMicroseconds(int)

GpuKernelBase<float[], float>.GetMemoryRequirements()

GpuKernelBase<float[], float>.ValidateInput(float[])

GpuKernelBase<float[], float>.WarmupAsync(CancellationToken)

GpuKernelBase<float[], float>.Dispose()

object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.ReferenceEquals(object, object)

object.ToString()

Properties

BackendProvider

Backend provider name

public override string BackendProvider { get; }

Property Value

string

DisplayName

Kernel display name

public override string DisplayName { get; }

Property Value

string

IsGpuAccelerated

Whether kernel uses GPU acceleration (always false for CPU)

public override bool IsGpuAccelerated { get; }

Property Value

bool

KernelId

Kernel unique identifier

public override string KernelId { get; }

Property Value

string

Methods

ExecuteAsync(float[], CancellationToken)

Executes vector addition on a float array, returning the sum of all elements.

public override Task<float> ExecuteAsync(float[] input, CancellationToken cancellationToken = default)

Parameters

input float[]

Input vector (float array).

cancellationToken CancellationToken

Cancellation token.

Returns

Task<float>

The sum of all elements.

ExecuteBatchAsync(float[][], CancellationToken)

Execute vector addition for batch of inputs (optimized for CPU).

public override Task<float[]> ExecuteBatchAsync(float[][] inputs, CancellationToken cancellationToken = default)

Parameters

inputs float[][]

Array of input vectors.

cancellationToken CancellationToken

Cancellation token.

Returns

Task<float[]>

Array of sums (one per input vector).

GetEstimatedExecutionTimeMicroseconds(int)

Get estimated execution time for input size. CPU vector addition is ~1μs per 1000 elements.

public override long GetEstimatedExecutionTimeMicroseconds(int inputSize)

Parameters

inputSize int

Returns

long

GetMemoryRequirements()

Get memory requirements for vector addition.

public override KernelMemoryRequirements GetMemoryRequirements()

Returns

KernelMemoryRequirements

ValidateInput(float[])

Validate input vector.

public override KernelValidationResult ValidateInput(float[] input)

Parameters

input float[]

Returns

KernelValidationResult