{"id":324272,"date":"2026-03-17T15:09:48","date_gmt":"2026-03-17T07:09:48","guid":{"rendered":"http:\/\/www.namnewsnetwork.org\/?p=324272"},"modified":"2026-03-17T15:09:48","modified_gmt":"2026-03-17T07:09:48","slug":"%e2%80%8bkioxia-achieves-4-8-billion-high-dimensional-vector-search-database-on-a-single-server-with-7-8x-index-build-time-acceleration-via-gpus","status":"publish","type":"post","link":"http:\/\/namnewsnetwork.org\/?p=324272","title":{"rendered":"\u200bKIOXIA Achieves 4.8 Billion High-Dimensional Vector Search Database on a Single Server, with 7.8x Index Build Time Acceleration via GPUs"},"content":{"rendered":"\n

TOKYO, March 17 (Bernama-BUSINESS WIRE) — <\/strong>Kioxia Corporation<\/a> today announced the successful demonstration of achieving high-dimensional vector search scaling to 4.8 billion vectors on a single server with its open-source KIOXIA AiSAQ\u2122 approximate nearest neighbor search (ANNS) technology. Additionally, Kioxia demonstrated a significant reduction in index build time by leveraging GPU acceleration through NVIDIA cuVS<\/a>. These two achievements mark a significant advancement for retrieval augmented generation (RAG) search solutions. Continued development is underway to support larger-scale deployments beyond 4.8 billion vectors.<\/p>\n\n\n\n

Index build time on a massive-scale vector database is a crucial pain point for the industry. In collaboration with NVIDIA, Kioxia demonstrated up to 20x improvement in KIOXIA AiSAQ index build time for high-dimensional vectors of 1024 dimensions, and up to 7.8x improvement in end-to-end build times. This 20x improvement represents a reduction from 28.4 days using CPU to 1.4 days using four\u00a0NVIDIA\u00a0<\/a>Hopper<\/a>\u00a0GPUs<\/a>\u00a0to build the index, and a reduction from 31 days to 4 days in end-to-end testing.1<\/sup><\/p>\n\n\n\n

https:\/\/mrem.bernama.com\/viewsm.php?idm=53769<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"

TOKYO, March 17 (Bernama-BUSINESS WIRE) — Kioxia Corporation today announced the successful demonstration of achieving high-dimensional vector search scaling to 4.8 billion vectors on a single server with its open-source KIOXIA AiSAQ\u2122 approximate nearest neighbor search (ANNS) technology. Additionally, Kioxia demonstrated a significant reduction in index build time by leveraging GPU acceleration through NVIDIA cuVS. These two achievements […]<\/p>\n","protected":false},"author":14,"featured_media":0,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":[],"categories":[315],"tags":[],"_links":{"self":[{"href":"http:\/\/namnewsnetwork.org\/index.php?rest_route=\/wp\/v2\/posts\/324272"}],"collection":[{"href":"http:\/\/namnewsnetwork.org\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/namnewsnetwork.org\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/namnewsnetwork.org\/index.php?rest_route=\/wp\/v2\/users\/14"}],"replies":[{"embeddable":true,"href":"http:\/\/namnewsnetwork.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=324272"}],"version-history":[{"count":1,"href":"http:\/\/namnewsnetwork.org\/index.php?rest_route=\/wp\/v2\/posts\/324272\/revisions"}],"predecessor-version":[{"id":324273,"href":"http:\/\/namnewsnetwork.org\/index.php?rest_route=\/wp\/v2\/posts\/324272\/revisions\/324273"}],"wp:attachment":[{"href":"http:\/\/namnewsnetwork.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=324272"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/namnewsnetwork.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=324272"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/namnewsnetwork.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=324272"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}