Dot Products | NumKong for Python

Dot products are their own family because storage type, conjugation rules, and output widening matter.

import numpy as np
import numkong as nk

a = (np.random.randn(256) + 1j * np.random.randn(256)).astype(np.complex64)
b = (np.random.randn(256) + 1j * np.random.randn(256)).astype(np.complex64)

dot = nk.dot(a, b)   # numpy.dot(a, b)
vdot = nk.vdot(a, b) # numpy.vdot(a, b)

print(dot, vdot)

Real low-precision inputs can also be routed through explicit dtype tags when the storage buffer itself is raw bytes.

API

Functions

pointer_to_*× 3Return the address of the inner kernel for dtype, as an integer.

__init__.pyi:878 ↗

def pointer_to_inner(
    dtype: _FloatTypeName | _ComplexTypeName | _MiniFloatType,
    /,
) -> int

Symbol
`pointer_to_inner`
`pointer_to_dot`
`pointer_to_vdot`

*× 2Compute the inner product of two real or complex vectors.

__init__.pyi:937 ↗

def inner(
    a: _BufferType,
    b: _BufferType,
    /,
    dtype: _FloatTypeName | _ComplexTypeName | _MiniFloatType | None = None,
    *,
    out: _BufferType | None = None,
    out_dtype: _FloatTypeName | _ComplexTypeName | _MiniFloatType | None = None,
    capabilities: Capability | int | None = ...,
    stream: int | None = ...,
) -> float | complex | Tensor | None

Symbol
`inner`
`dot`

Similar to numpy.inner. Two vectors give a scalar. Matrices pair row i of a with row i of b, a single row pairing with every row of the other, into a new Tensor of one result per pair, or into out, returning None.

Similar to numpy.dot. Two vectors give a scalar. Matrices pair row i of a with row i of b, a single row pairing with every row of the other, into a new Tensor of one result per pair, or into out, returning None.

Parameters

`a_BufferType`		First real or complex vector or matrix.
`b_BufferType`		Second real or complex vector or matrix, of the dtype of `a`.
`dtype_FloatTypeName \| _ComplexTypeName \| _MiniFloatType \| None`		Input dtype to read both buffers as, overriding the one they report.
`out_BufferType \| None`		Output vector for the results.
`out_dtype_FloatTypeName \| _ComplexTypeName \| _MiniFloatType \| None`		Result dtype, by default that of `out`, else float64, complex128 for complex input.
`capabilitiesCapability \| int \| None`		Capabilities to run within: every CPU one by default, or for packed operands the mask that packed them.
`streamint \| None`		A GPU stream pointer, left None on the CPU.

vdotCompute the dot product of two complex vectors, conjugating the first.

__init__.pyi:987 ↗

def vdot(
    a: _BufferType,
    b: _BufferType,
    /,
    dtype: _ComplexTypeName | _MiniFloatType | None = None,
    *,
    out: _BufferType | None = None,
    out_dtype: _ComplexTypeName | _MiniFloatType | None = None,
    capabilities: Capability | int | None = ...,
    stream: int | None = ...,
) -> complex | Tensor | None

Similar to numpy.vdot. Two vectors give a scalar. Matrices pair row i of a with row i of b, a single row pairing with every row of the other, into a new Tensor of one result per pair, or into out, returning None.

Parameters

`a_BufferType`		First complex vector or matrix.
`b_BufferType`		Second complex vector or matrix, of the dtype of `a`.
`dtype_ComplexTypeName \| _MiniFloatType \| None`		Input dtype to read both buffers as, overriding the one they report.
`out_BufferType \| None`		Output vector for the results.
`out_dtype_ComplexTypeName \| _MiniFloatType \| None`		Result dtype, by default that of `out`, else complex128.
`capabilitiesCapability \| int \| None`		Capabilities to run within: every CPU one by default, or for packed operands the mask that packed them.
`streamint \| None`		A GPU stream pointer, left None on the CPU.