Introduction

KBest

Kunpeng Blazing-fast embedding similarity search thruster (KBest) is an efficient, Huawei-developed graph search algorithm. It optimizes the performance and precision of the nearest neighbor search by using methods such as quantization and NUMA scheduling, which are used for multi-dimensional vector approximate nearest neighbor search.

Applicable to various application fields of vector retrieval, including network search, multi-modal search, recommendation system, advertisement placement, and retrieval-augmented generation (RAG).

KScaNN

Kunpeng Scalable Nearest Neighbors (KScaNN) is a vector retrieval algorithm that is based on inverted indexes. It uses the Kunpeng architecture to deeply optimize the index layout, algorithm process, and computing process, fully unleashing the chip potential.

KVecTurbo

KVecTurbo is a vector retrieval acceleration component developed by Kunpeng and can be used together with the openGauss vector database. It quantifies and compresses high-dimensional vectors to quickly obtain the near neighbors of a query. In addition, KVecTurbo uses the SIMD instructions to accelerate distance calculation for multidimensional vector nearest neighbor search.

KNewPfordelta

KNewPfordelta is an integer compression algorithm optimized by Kunpeng based on the open source PForDelta algorithm. It is designed for efficient compression and fast decompression of inverted indexes. KNewPfordelta leverages block-based processing, exception handling, and SIMD acceleration to achieve an optimal balance between storage costs and query performance in inverted index compression. It is widely used in search engines, recommendation systems, and other scenarios that require fast processing of large-scale ordered integer sequences, such as document ID lists, and term frequencies and positions.

hnswlib

hnswlib is an efficient retrieval algorithm based on Hierarchical Navigable Small World (HNSW) graphs. Huawei has optimized the open source hnswlib algorithm library for the Arm architecture. It delivers FP16 support through vectorization, and leverages optimization strategies such as prefetching and instruction rescheduling.

Faiss

The open source Faiss algorithm library has been deeply optimized using key technologies such as vectorization, dimension-interleaved lookup and accumulation, and vector filtering and compression. These enhancements significantly improve the similarity search and clustering efficiency across IVFFlat, IVFPQ, HNSW, PQFS, and IVFPQFS indexing algorithms.