NDSEARCH: Accelerating Graph-Traversal-Based Approximate Nearest Neighbor Search through Near Data Processing

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Wang, Yitu, Li, Shiyu, Zheng, Qilin, Song, Linghao, Li, Zongwang, Chang, Andrew, Li, Hai "Helen", Chen, Yiran
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909212491120640
author Wang, Yitu
Li, Shiyu
Zheng, Qilin
Song, Linghao
Li, Zongwang
Chang, Andrew
Li, Hai "Helen"
Chen, Yiran
author_facet Wang, Yitu
Li, Shiyu
Zheng, Qilin
Song, Linghao
Li, Zongwang
Chang, Andrew
Li, Hai "Helen"
Chen, Yiran
contents Approximate nearest neighbor search (ANNS) is a key retrieval technique for vector database and many data center applications, such as person re-identification and recommendation systems. It is also fundamental to retrieval augmented generation (RAG) for large language models (LLM) now. Among all the ANNS algorithms, graph-traversal-based ANNS achieves the highest recall rate. However, as the size of dataset increases, the graph may require hundreds of gigabytes of memory, exceeding the main memory capacity of a single workstation node. Although we can do partitioning and use solid-state drive (SSD) as the backing storage, the limited SSD I/O bandwidth severely degrades the performance of the system. To address this challenge, we present NDSEARCH, a hardware-software co-designed near-data processing (NDP) solution for ANNS processing. NDSEARCH consists of a novel in-storage computing architecture, namely, SEARSSD, that supports the ANNS kernels and leverages logic unit (LUN)-level parallelism inside the NAND flash chips. NDSEARCH also includes a processing model that is customized for NDP and cooperates with SEARSSD. The processing model enables us to apply a two-level scheduling to improve the data locality and exploit the internal bandwidth in NDSEARCH, and a speculative searching mechanism to further accelerate the ANNS workload. Our results show that NDSEARCH improves the throughput by up to 31.7x, 14.6x, 7.4x 2.9x over CPU, GPU, a state-of-the-art SmartSSD-only design, and DeepStore, respectively. NDSEARCH also achieves two orders-of-magnitude higher energy efficiency than CPU and GPU.
format Preprint
id arxiv_https___arxiv_org_abs_2312_03141
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle NDSEARCH: Accelerating Graph-Traversal-Based Approximate Nearest Neighbor Search through Near Data Processing
Wang, Yitu
Li, Shiyu
Zheng, Qilin
Song, Linghao
Li, Zongwang
Chang, Andrew
Li, Hai "Helen"
Chen, Yiran
Hardware Architecture
Approximate nearest neighbor search (ANNS) is a key retrieval technique for vector database and many data center applications, such as person re-identification and recommendation systems. It is also fundamental to retrieval augmented generation (RAG) for large language models (LLM) now. Among all the ANNS algorithms, graph-traversal-based ANNS achieves the highest recall rate. However, as the size of dataset increases, the graph may require hundreds of gigabytes of memory, exceeding the main memory capacity of a single workstation node. Although we can do partitioning and use solid-state drive (SSD) as the backing storage, the limited SSD I/O bandwidth severely degrades the performance of the system. To address this challenge, we present NDSEARCH, a hardware-software co-designed near-data processing (NDP) solution for ANNS processing. NDSEARCH consists of a novel in-storage computing architecture, namely, SEARSSD, that supports the ANNS kernels and leverages logic unit (LUN)-level parallelism inside the NAND flash chips. NDSEARCH also includes a processing model that is customized for NDP and cooperates with SEARSSD. The processing model enables us to apply a two-level scheduling to improve the data locality and exploit the internal bandwidth in NDSEARCH, and a speculative searching mechanism to further accelerate the ANNS workload. Our results show that NDSEARCH improves the throughput by up to 31.7x, 14.6x, 7.4x 2.9x over CPU, GPU, a state-of-the-art SmartSSD-only design, and DeepStore, respectively. NDSEARCH also achieves two orders-of-magnitude higher energy efficiency than CPU and GPU.
title NDSEARCH: Accelerating Graph-Traversal-Based Approximate Nearest Neighbor Search through Near Data Processing
topic Hardware Architecture
url https://arxiv.org/abs/2312.03141