KScaNN: Scalable Approximate Nearest Neighbor Search on Kunpeng

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Senkevich, Oleg, Xu, Siyang, Jiang, Tianyi, Radionov, Alexander, Tabaszewski, Jan, Malyshev, Dmitriy, Li, Zijian, Xue, Daihao, Yu, Licheng, Zeng, Weidi, Wang, Meiling, Yao, Xin, Huang, Siyu, Neshchetkin, Gleb, Pan, Qiuling, Fu, Yaoyao
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915934284808192
author Senkevich, Oleg
Xu, Siyang
Jiang, Tianyi
Radionov, Alexander
Tabaszewski, Jan
Malyshev, Dmitriy
Li, Zijian
Xue, Daihao
Yu, Licheng
Zeng, Weidi
Wang, Meiling
Yao, Xin
Huang, Siyu
Neshchetkin, Gleb
Pan, Qiuling
Fu, Yaoyao
author_facet Senkevich, Oleg
Xu, Siyang
Jiang, Tianyi
Radionov, Alexander
Tabaszewski, Jan
Malyshev, Dmitriy
Li, Zijian
Xue, Daihao
Yu, Licheng
Zeng, Weidi
Wang, Meiling
Yao, Xin
Huang, Siyu
Neshchetkin, Gleb
Pan, Qiuling
Fu, Yaoyao
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2511_03298
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle KScaNN: Scalable Approximate Nearest Neighbor Search on Kunpeng
Senkevich, Oleg
Xu, Siyang
Jiang, Tianyi
Radionov, Alexander
Tabaszewski, Jan
Malyshev, Dmitriy
Li, Zijian
Xue, Daihao
Yu, Licheng
Zeng, Weidi
Wang, Meiling
Yao, Xin
Huang, Siyu
Neshchetkin, Gleb
Pan, Qiuling
Fu, Yaoyao
Information Retrieval
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
title KScaNN: Scalable Approximate Nearest Neighbor Search on Kunpeng
topic Information Retrieval
url https://arxiv.org/abs/2511.03298