Metraipolis › archive › dc_9efbeebab00d

VS-Flash: Harnessing Vector Search with Computational Memory-Semantic Flash — arXiv:2610.26960

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.26960
License (as archived): CC0-1.0
Archived: 2026-10-21T07:11:26.749Z
SHA-256 of the archived text: e8647f452badaabd849723e7a018f7ca39af949da69b12e403dda13aa04f473f
Stable URL of this page: https://metraipolis.com/documento/dc_9efbeebab00d

How to cite

VS-Flash: Harnessing Vector Search with Computational Memory-Semantic Flash — arXiv:2610.26960 — arXiv (en), https://arxiv.org/abs/2610.26960 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9efbeebab00d (Metraipolis archive dc_9efbeebab00d, sha256 e8647f452badaabd849723e7a018f7ca39af949da69b12e403dda13aa04f473f)

BibTeX

@misc{dc9efbeebab00d,
  title = {VS-Flash: Harnessing Vector Search with Computational Memory-Semantic Flash — arXiv:2610.26960},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.26960},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9efbeebab00d; sha256 e8647f452badaabd849723e7a018f7ca39af949da69b12e403dda13aa04f473f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.26960. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

As generative AI continues to evolve, retrieval-augmented generation (RAG) systems are driving rapid growth in vector database capacity requirements. As datasets outgrow host DRAM, vector databases rely on MMap-based serving over SSDs to extend capacity. However, high-fan-out ANN searches generate concurrent irregular accesses that contend for host memory and storage resources, degrading bulk throughput and inflating tail latency under mixed workloads. In this paper, we address these challenges through memory-semantic capacity and workload-aware compute placement. VS-Flash exposes flash as a large-capacity memory-semantic space and dynamically selects the execution engine according to runtime query and workload characteristics. It offloads throughput-oriented large-batch queries to a Computational Memory-Semantic Flash (CMS-Flash) device, while executing latency-sensitive small-batch queries on the host CPU. Both paths access the same resident segments, avoiding a separate host-DRAM replica. Across three billion-scale datasets, VS-Flash improves bulk-search throughput over vanilla Milvus by 36.8X on average, with up to a 57.4X improvement. Under mixed workloads, VS-Flash reduces the p99 latency of latency-sensitive requests by up to 24.8X while sustaining device-side bulk search. These results show that VS-Flash delivers scalable vector search beyond host DRAM capacity while jointly improving bulk throughput and small-request tail latency.

Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.DC, nuovi lavori del giorno).
Categorie arXiv: Databases (cs.DB) ; Distributed, Parallel, and Cluster Computing (cs.DC).
Pagina del lavoro: https://arxiv.org/abs/2610.26960 — 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 2026-10-21T07:06:13.132Z dalla pagina https://arxiv.org/list/cs.DC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).