Metraipolis › archive › dc_d2d6ab54e2e2

GrAND: GPU-based Dynamic Graph Indexes for Approximate Nearest Neighbour Search — arXiv:2608.21163

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.21163
License (as archived)
CC0-1.0
Archived
2026-10-18T10:22:13.787Z
SHA-256 of the archived text
9d084234e9a431d5dbd7827283119b05ac77dc1c3865596db00e45fc9a312818
Stable URL of this page
https://metraipolis.com/documento/dc_d2d6ab54e2e2

How to cite

GrAND: GPU-based Dynamic Graph Indexes for Approximate Nearest Neighbour Search — arXiv:2608.21163 — arXiv (en), https://arxiv.org/abs/2608.21163 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d2d6ab54e2e2 (Metraipolis archive dc_d2d6ab54e2e2, sha256 9d084234e9a431d5dbd7827283119b05ac77dc1c3865596db00e45fc9a312818)
BibTeX
@misc{dcd2d6ab54e2e2,
  title = {GrAND: GPU-based Dynamic Graph Indexes for Approximate Nearest Neighbour Search — arXiv:2608.21163},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.21163},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d2d6ab54e2e2; sha256 9d084234e9a431d5dbd7827283119b05ac77dc1c3865596db00e45fc9a312818},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.21163. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Modern Approximate Nearest Neighbour Search (ANNS) applications operate over continuously evolving vector collections and require graph indexes that sustain high-throughput searches while incorporating insertions and deletions with high recall. However, most GPU graph indexes are static or provide limited update support. Updates require neighbour discovery, reverse-edge creation, pruning, and deletion-induced graph repair; executing these operations concurrently introduces redundant distance computations and conflicting accesses to shared adjacency lists. Background-rebuild-based deletion further incurs substantial computation, additional memory consumption, and interference with foreground queries. We present GrAND (GPU-based Dynamic Graph Indexes for Approximate Nearest Neighbour Search), a GPU-native collection of dynamic-update algorithms for two popular graph indexes, Vamana and CAGRA. GrAND consolidates graph repair across a batch, eliminating redundant pruning computations, and employs a lock-free find-and-replace strategy for parallel adjacency-list updates. For reliable in-place deletion, GrAND constructs an on-demand reverse graph on the GPU, accurately identifying incoming edges without permanently duplicating the index. We evaluate GrAND on seven real-world datasets across five streaming workloads, comparing it against SVFusion and FreshDiskANN-GPU (our GPU adaptation of FreshDiskANN). GrAND improves overall workload throughput by 2.2x-8.7x and 6.5x-25.4x, respectively, while maintaining high search throughput and recall over sustained updates.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-24 in cs.DC).
Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC) ; Databases (cs.DB).
Pagina del lavoro: https://arxiv.org/abs/2608.21163 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T10:18:05.596Z dalla pagina https://arxiv.org/catchup/cs.DC/2026-08-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).