Salvato in:
Dettagli Bibliografici
Autori principali: Li, Zheng, Zeng, Guangyi, Delestrac, Paul, Yao, Enyi, Yang, Simei
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2602.19242
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911461502091264
author Li, Zheng
Zeng, Guangyi
Delestrac, Paul
Yao, Enyi
Yang, Simei
author_facet Li, Zheng
Zeng, Guangyi
Delestrac, Paul
Yao, Enyi
Yang, Simei
contents Hierarchical Navigable Small World (HNSW) has demonstrated impressive accuracy and low latency for high-dimensional nearest neighbor searches. However, its high computational demands and irregular, large-volume data access patterns present significant challenges to search efficiency. To address these challenges, we introduce pHNSW, an algorithm-hardware co-optimized solution that accelerates HNSW through Principal Component Analysis (PCA) filtering. On the algorithm side, we apply PCA filtering to reduce the dimensionality of the dataset, thereby lowering the volume of neighbor access and decreasing the computational load for distance calculations. On the hardware side, we design the pHNSW processor with custom instructions to optimize search throughput and energy efficiency. In the experiments, we synthesized the pHNSW processor RTL design with a 65nm technology node and evaluated it using DDR4 and HBM1.0 DRAM standards. The results show that pHNSW boosts Queries per Second (QPS) by 14.47x-21.37x on a CPU and 5.37x-8.46x on a GPU, while reducing energy consumption by up to 57.4% compared to standard HNSW implementation.
format Preprint
id arxiv_https___arxiv_org_abs_2602_19242
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle pHNSW: PCA-Based Filtering to Accelerate HNSW Approximate Nearest Neighbor Search
Li, Zheng
Zeng, Guangyi
Delestrac, Paul
Yao, Enyi
Yang, Simei
Hardware Architecture
Hierarchical Navigable Small World (HNSW) has demonstrated impressive accuracy and low latency for high-dimensional nearest neighbor searches. However, its high computational demands and irregular, large-volume data access patterns present significant challenges to search efficiency. To address these challenges, we introduce pHNSW, an algorithm-hardware co-optimized solution that accelerates HNSW through Principal Component Analysis (PCA) filtering. On the algorithm side, we apply PCA filtering to reduce the dimensionality of the dataset, thereby lowering the volume of neighbor access and decreasing the computational load for distance calculations. On the hardware side, we design the pHNSW processor with custom instructions to optimize search throughput and energy efficiency. In the experiments, we synthesized the pHNSW processor RTL design with a 65nm technology node and evaluated it using DDR4 and HBM1.0 DRAM standards. The results show that pHNSW boosts Queries per Second (QPS) by 14.47x-21.37x on a CPU and 5.37x-8.46x on a GPU, while reducing energy consumption by up to 57.4% compared to standard HNSW implementation.
title pHNSW: PCA-Based Filtering to Accelerate HNSW Approximate Nearest Neighbor Search
topic Hardware Architecture
url https://arxiv.org/abs/2602.19242