Back to papers
SVFusion: A CPU-GPU Co-Processing Architecture for Large-Scale Real-Time Vector Search
Summary: SVFusion tackles real-time large-scale ANNS by fusing CPU-GPU-disk in a hierarchical vector index, enabling high-throughput online updates without sacrificing GPU-style query speed. Key novelty: workload-aware GPU caching plus CUDA multi-stream/adaptive coordination and concurrency control for consistent interleaved query-update processing.
(summarized by gpt-5.4-mini on Apr 12 2026)
- Paper ID
- 14261
- Venue
- VLDB
- Year
- 2026
- Pagerank
- 4.1905499e-05
- Overall Rank
- 10,224 | 28.95%
- DOI
-
10.14778/3796195.3796216
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank |
Citing Paper |
Year |
Venue |
Pagerank |
Outgoing Citations (Sorted by Pagerank)
Showing 16 of 16 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank |
Cited Paper |
Year |
Venue |
Pagerank |
| 210 |
Fast Approximate Nearest Neighbor Search With The Navigating Spreading-out Graph |
2019 |
VLDB |
0.00034086264 |
| 579 |
Locality-Sensitive Hashing Scheme Based on Dynamic Collision Counting |
2012 |
SIGMOD |
0.0001982328 |
| 596 |
Query-Aware Locality-Sensitive Hashing for Approximate Nearest Neighbor Search |
2016 |
VLDB |
0.00019455943 |
| 763 |
A Comprehensive Survey and Experimental Comparison of Graph-Based Approximate Nearest Neighbor Search |
2021 |
VLDB |
0.00016963981 |
| 2,160 |
PM-LSH: A Fast and Accurate LSH Framework for High-Dimensional Approximate NN Search |
2020 |
VLDB |
9.4037759e-05 |
| 2,264 |
Manu: A Cloud Native Vector Database Management System |
2022 |
VLDB |
9.1587362e-05 |
| 2,287 |
RaBitQ: Quantizing High-Dimensional Vectors with a Theoretical Error Bound for Approximate Nearest Neighbor Search |
2024 |
SIGMOD |
9.1004806e-05 |
| 2,772 |
High-Dimensional Approximate Nearest Neighbor Search: with Reliable and Efficient Distance Comparison Operations |
2023 |
SIGMOD |
8.1491893e-05 |
| 3,403 |
ELPIS: Graph-Based Similarity Search for Scalable Data Science |
2023 |
VLDB |
7.1338786e-05 |
| 3,552 |
SeRF: Segment Graph for Range-Filtering Approximate Nearest Neighbor Search |
2024 |
SIGMOD |
6.9765275e-05 |
| 4,600 |
Practical and Asymptotically Optimal Quantization of High-Dimensional Vectors in Euclidean Space for Approximate Nearest Neighbor Search |
2025 |
SIGMOD |
6.0528015e-05 |
| 5,577 |
Revisiting the Index Construction of Proximity Graph-Based Approximate Nearest Neighbor Search |
2025 |
VLDB |
5.423881e-05 |
| 7,654 |
LiteHST: A Tree Embedding based Method for Similarity Search |
2023 |
SIGMOD |
4.6831082e-05 |
| 7,843 |
GTI: Graph-based Tree Index with Logarithm Updates for Nearest Neighbor Search in High-Dimensional Spaces |
2025 |
VLDB |
4.6335219e-05 |
| 9,482 |
Cost-Effective, Low Latency Vector Search with Azure Cosmos DB |
2025 |
VLDB |
4.3300131e-05 |
| 10,662 |
HAKES: Scalable Vector Database for Embedding Search Service |
2025 |
VLDB |
4.1905499e-05 |
Semantically Similar Papers
| Overall Rank |
Paper |
Year |
Venue |
Pagerank |
| 10,111 |
Scalable Graph Indexing using GPUs for Approximate Nearest Neighbor Search |
2026 |
SIGMOD |
4.1905499e-05 |
| 8,167 |
GTS: GPU-based Tree Index for Fast Similarity Search |
2024 |
SIGMOD |
4.567569e-05 |
| 9,880 |
VStream: A Distributed Streaming Vector Search System |
2025 |
VLDB |
4.2602815e-05 |
| 10,766 |
Turbocharging Vector Databases using Modern SSDs |
2025 |
VLDB |
4.1905499e-05 |
| 10,167 |
FlashANNS: GPU-Driven Asynchronous I/O Pipelining for Eliminating Storage-Compute Bottlenecks in Billion-Scale Similarity Search |
2026 |
SIGMOD |
4.1905499e-05 |
| 8,430 |
Accelerating Graph Indexing for ANNS on Modern CPUs |
2025 |
SIGMOD |
4.508568e-05 |
| 13,100 |
VecFlow-Chamfer: A GPU-based Data Management System for High-Performance Multi-Vector Search on Superchips |
2026 |
SIGMOD |
- |
| 10,160 |
Efficient Vector Index Merging in Vector Databases |
2026 |
SIGMOD |
4.1905499e-05 |
| 10,039 |
VecFlow: A High-Performance Vector Data Management System for Filtered-Search on GPUs |
2026 |
SIGMOD |
4.1905499e-05 |
| 10,086 |
High-Throughput, Cost-Effective Billion-Scale Vector Search with a Single GPU |
2026 |
SIGMOD |
4.1905499e-05 |