Struct SimdBruteForceSearch 

pub struct SimdBruteForceSearch { /* private fields */ }

Brute-force nearest-neighbor search with SIMD-accelerated distance computation.

All N squared distances are computed in a single SIMD-vectorised pass before selection, which is more cache-friendly than repeated point-by-point comparison and exploits the full width of the CPU’s SIMD units.

Method	Complexity	Notes
find_k_nearest	O(N + k log k)	compute-all-then-partial-select
find_radius_neighbors	O(N)	compute-all-then-filter

Example

let pts = vec![Point3f::new(0.0, 0.0, 0.0), Point3f::new(1.0, 0.0, 0.0)];
let searcher = SimdBruteForceSearch::new(&pts);
let result = searcher.find_k_nearest(&Point3f::new(0.1, 0.0, 0.0), 1);
assert_eq!(result[0].0, 0); // index of nearest point

Implementations

impl SimdBruteForceSearch

pub fn new(points: &[Point3f]) -> Self

Construct a new searcher from a point slice (O(N) time and space).

pub fn len(&self) -> usize

Number of indexed points.

pub fn is_empty(&self) -> bool

Returns true if the index is empty.

pub fn soa(&self) -> &SoaPoints

Return the SoA representation (useful for benchmarks / inspection).

Trait Implementations

impl NearestNeighborSearch for SimdBruteForceSearch

fn find_k_nearest(&self, query: &Point3f, k: usize) -> Vec<(usize, f32)>

Find the k nearest neighbors to a query point

fn find_radius_neighbors( &self, query: &Point3f, radius: f32, ) -> Vec<(usize, f32)>

Find all neighbors within a given radius