Salvato in:
| Autori principali: | , , , , |
|---|---|
| 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 |