KScaNN: Scalable Approximate Nearest Neighbor Search on Kunpeng

TL;DR

KScaNN is a new ARM-optimized ANNS algorithm that combines hardware-specific optimizations and adaptive techniques, achieving significant speedups over x86 solutions.

Contribution

It introduces novel algorithmic and hardware-specific optimizations for ANNS on ARM, including an ML-driven adaptive search module and SIMD kernels.

Findings

Achieves up to 1.63x speedup over x86-based solutions.

Demonstrates effective hardware-aware algorithmic refinements.

Provides a blueprint for high-performance vector search on ARM.

Abstract

Approximate Nearest Neighbor Search (ANNS) is a cornerstone algorithm for information retrieval, recommendation systems, and machine learning applications. While x86-based architectures have historically dominated this domain, the increasing adoption of ARM-based servers in industry presents a critical need for ANNS solutions optimized on ARM architectures. A naive port of existing x86 ANNS algorithms to ARM platforms results in a substantial performance deficit, failing to leverage the unique capabilities of the underlying hardware. To address this challenge, we introduce KScaNN, a novel ANNS algorithm co-designed for the Kunpeng 920 ARM architecture. KScaNN embodies a holistic approach that synergizes sophisticated, data aware algorithmic refinements with carefully-designed hardware specific optimizations. Its core contributions include: 1) novel algorithmic techniques, including a hybrid intra-cluster search strategy and an improved PQ residual calculation method, which optimize the search process at a higher level; 2) an ML-driven adaptive search module that provides adaptive, per-query tuning of search parameters, eliminating the inefficiencies of static configurations; and 3) highly-optimized SIMD kernels for ARM that maximize hardware utilization for the critical distance computation workloads. The experimental results demonstrate that KScaNN not only closes the performance gap but establishes a new standard, achieving up to a 1.63x speedup over the fastest x86-based solution. This work provides a definitive blueprint for achieving leadership-class performance for vector search on modern ARM architectures and underscores