Delegate StridedUnaryKernel

Namespace

NumSharp.Backends.Kernels

Assembly

NumSharp.dll

Fused strided-source unary kernel: builds each SIMD vector directly from a strided 1-D source via lane-count scalar gathers, applies the unary op, and stores contiguously — single pass, no scratch buffer, no per-tile dispatch.

public delegate void StridedUnaryKernel(void* src, long srcByteStride, void* dst, long count)

Parameters

src void*

Strided source base pointer (already offset-adjusted).

srcByteStride long

Source stride in BYTES (may be negative for reversed views).

dst void*

Contiguous destination base pointer.

count long

Number of elements.

Extension Methods

LinqExtensions.Yield<T>(T)