|国家预印本平台
首页|KBest: Efficient Vector Search on Kunpeng CPU

KBest: Efficient Vector Search on Kunpeng CPU

KBest: Efficient Vector Search on Kunpeng CPU

来源:Arxiv_logoArxiv
英文摘要

Vector search, which returns the vectors most similar to a given query vector from a large vector dataset, underlies many important applications such as search, recommendation, and LLMs. To be economic, vector search needs to be efficient to reduce the resources required by a given query workload. However, existing vector search libraries (e.g., Faiss and DiskANN) are optimized for x86 CPU architectures (i.e., Intel and AMD CPUs) while Huawei Kunpeng CPUs are based on the ARM architecture and competitive in compute power. In this paper, we present KBest as a vector search library tailored for the latest Kunpeng 920 CPUs. To be efficient, KBest incorporates extensive hardware-aware and algorithmic optimizations, which include single-instruction-multiple-data (SIMD) accelerated distance computation, data prefetch, index refinement, early termination, and vector quantization. Experiment results show that KBest outperforms SOTA vector search libraries running on x86 CPUs, and our optimizations can improve the query throughput by over 2x. Currently, KBest serves applications from both our internal business and external enterprise clients with tens of millions of queries on a daily basis.

Kaihao Ma、Meiling Wang、Senkevich Oleg、Zijian Li、Daihao Xue、Dmitriy Malyshev、Yangming Lv、Shihai Xiao、Xiao Yan、Radionov Alexander、Weidi Zeng、Yuanzhan Gao、Zhiyu Zou、Xin Yao、Lin Liu、Junhao Wu、Yiding Liu、Yaoyao Fu、Gongyi Wang、Gong Zhang、Fei Yi、Yingfan Liu

计算技术、计算机技术

Kaihao Ma,Meiling Wang,Senkevich Oleg,Zijian Li,Daihao Xue,Dmitriy Malyshev,Yangming Lv,Shihai Xiao,Xiao Yan,Radionov Alexander,Weidi Zeng,Yuanzhan Gao,Zhiyu Zou,Xin Yao,Lin Liu,Junhao Wu,Yiding Liu,Yaoyao Fu,Gongyi Wang,Gong Zhang,Fei Yi,Yingfan Liu.KBest: Efficient Vector Search on Kunpeng CPU[EB/OL].(2025-08-07)[2025-08-16].https://arxiv.org/abs/2508.03016.点此复制

评论