sochdb-vector 2.0.5

Streaming elimination vector search engine for SochDB - CPU-first ANN with RDF + BPS
Documentation

Streaming Elimination Vector Search Engine

A silicon-sympathetic, CPU-first ANN design that avoids pointer chasing, supports updates, and makes recall a controllable knob.

Architecture

The engine uses two complementary views for candidate generation:

  • RDF (Rare-Dominant Fingerprint): IR-style inverted lists for precision
  • BPS (Block Projection Sketch): Dense-friendly streaming scans for recall

Final ranking uses int8 dot products with outlier-aware correction.

SIMD Acceleration

The engine uses pure Rust SIMD implementations for critical operations:

  • BPS scans: AVX2 (32x) / AVX512 (64x) / NEON (16x) speedup
  • int8 dot products: 8x speedup on AVX2
  • Visibility checks: 4x speedup on AVX2 / 2x on NEON

All SIMD code is written in Rust using core::arch intrinsics, enabling cross-function inlining and eliminating FFI overhead.

See [simd] module for the pure Rust implementations and [dispatch] module for runtime CPU detection and kernel dispatch.