ARM 4-BIT PQ: SIMD-based Acceleration for Approximate Nearest Neighbor Search on ARM

TL;DR

This paper introduces an ARM-optimized 4-bit product quantization method that significantly accelerates approximate nearest neighbor search by leveraging NEON SIMD instructions, achieving a tenfold speedup over naive implementations.

Contribution

The paper presents a novel ARM-specific SIMD acceleration technique for 4-bit PQ, overcoming x64 limitations and enabling efficient approximate nearest neighbor search on ARM devices.

Findings

Achieves 10x speedup over naive 4-bit PQ

Uses ARM NEON instructions with register bundling and shuffling

Demonstrates consistent performance improvements

Abstract

We accelerate the 4-bit product quantization (PQ) on the ARM architecture. Notably, the drastic performance of the conventional 4-bit PQ strongly relies on x64-specific SIMD register, such as AVX2; hence, we cannot yet achieve such good performance on ARM. To fill this gap, we first bundle two 128-bit registers as one 256-bit component. We then apply shuffle operations for each using the ARM-specific NEON instruction. By making this simple but critical modification, we achieve a dramatic speedup for the 4-bit PQ on an ARM architecture. Experiments show that the proposed method consistently achieves a 10x improvement over the naive PQ with the same accuracy.