{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T16:44:22Z","timestamp":1781973862142,"version":"3.54.5"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tc.2025.3643434","type":"journal-article","created":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T18:35:14Z","timestamp":1765564514000},"page":"1323-1334","source":"Crossref","is-referenced-by-count":1,"title":["Performance Analysis and CXL Memory Optimization in Cluster-Based RAG Systems"],"prefix":"10.1109","volume":"75","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-7432-0150","authenticated-orcid":false,"given":"Jesin","family":"Kim","sequence":"first","affiliation":[{"name":"Memory Business, Device Solutions, Samsung Electronics, Seoul, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1592-8803","authenticated-orcid":false,"given":"Hochul","family":"Shin","sequence":"additional","affiliation":[{"name":"Memory Business, Device Solutions, Samsung Electronics, Seoul, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3432-4747","authenticated-orcid":false,"given":"Byeonghun","family":"Hwang","sequence":"additional","affiliation":[{"name":"Memory Business, Device Solutions, Samsung Electronics, Seoul, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8649-7020","authenticated-orcid":false,"given":"Seungpyo","family":"Cho","sequence":"additional","affiliation":[{"name":"Memory Business, Device Solutions, Samsung Electronics, Seoul, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9541-5756","authenticated-orcid":false,"given":"Kyumin","family":"Park","sequence":"additional","affiliation":[{"name":"Memory Business, Device Solutions, Samsung Electronics, Seoul, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0502-8544","authenticated-orcid":false,"given":"Young Geon","family":"Yoo","sequence":"additional","affiliation":[{"name":"Memory Business, Device Solutions, Samsung Electronics, Seoul, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4790-436X","authenticated-orcid":false,"given":"Byungyo","family":"Lee","sequence":"additional","affiliation":[{"name":"Memory Business, Device Solutions, Samsung Electronics, Seoul, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6797-7994","authenticated-orcid":false,"given":"Hojun","family":"Shim","sequence":"additional","affiliation":[{"name":"Memory Business, Device Solutions, Samsung Electronics, Seoul, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lewis","year":"2020"},{"key":"ref2","first-page":"825","article-title":"An investigation of practical approximate nearest neighbor algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu","year":"2005"},{"key":"ref3","first-page":"1","article-title":"DiskANN: Fast accurate billion-point nearest neighbor search on a single node","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Subramanya","year":"2019"},{"key":"ref4","first-page":"5199","article-title":"SPANN: Highly-efficient billion-scale approximate nearest neighbor search","volume-title":"Proc. Adv. Neural Inf. Process","author":"Chen","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3669900"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582063"},{"key":"ref7","first-page":"37","article-title":"Managing memory tiers with CXL in virtualized environments","volume-title":"Proc. 18th USENIX Symp. Oper. Syst. Des. Implementation (OSDI)","author":"Zhong","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3721145.3725754"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.14778\/3685800.3685809"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3676641.3715988"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00100"},{"key":"ref12","article-title":"Exploring CXL-based KV cache storage for LLM serving","volume-title":"Proc. Mach. Learn. Syst. Workshop (NeurIPS)","author":"Tang","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/mm.2025.3582433"},{"key":"ref14","first-page":"585","article-title":"CXL-ANNS: Software\u2013hardware collaborative memory disaggregation and computation for billion-scale approximate nearest neighbor search","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Jang","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3669940.3707264"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2025.3570235"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3457550"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.14778\/3554821.3554843"},{"key":"ref19","article-title":"Towards efficient and scalable distributed vector search with RDMA","author":"Zhi","year":"2025"},{"key":"ref20","article-title":"SHINE: A scalable HNSW index in disaggregated memory","author":"Widmoser","year":"2025"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3736548.3737822"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/BigData47090.2019.9006219"},{"key":"ref23","article-title":"Optimizing system memory bandwidth with Micron CXL memory expansion modules on Intel Xeon 6 processors","author":"Sehgal","year":"2024"},{"issue":"5","key":"ref24","first-page":"1205","article-title":"Survey of vector database management systems","volume":"33","author":"Liu","year":"2024","journal-title":"VLDB J."},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889473"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.57"},{"key":"ref27","article-title":"S. Semiconductor, CXL Memory, and Cmm-D\/c-Tap"},{"key":"ref28","article-title":"Intel\u00ae Memory Latency Checker (Intel\u00ae MLC), v3.11b\u2014Download & release notes","year":"2024"},{"key":"ref29","article-title":"Dissecting CXL memory performance at scale: analysis, modeling, and optimization","author":"Liu","year":"2024"},{"key":"ref30","first-page":"105","article-title":"Demystifying CXL memory with genuine CXL-ready systems and devices","volume-title":"Proc. 45th IEEE\/ACM Int. Symp. Microarchit. (MICRO)","author":"Sun","year":"2023"},{"key":"ref31","article-title":"CXL Type 3 memory device software guide","year":"2024"},{"key":"ref32","article-title":"Weighted interleaving for memory tiering,\u201d LWN.net","author":"Corbet","year":"2023"},{"key":"ref33","article-title":"MS MARCO: A human generated machine reading comprehension dataset","author":"Bajaj","year":"2016"},{"key":"ref34","article-title":"Billion-scale approximate nearest neighbor search using a single GPU","author":"Karthik"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3712285.3759801"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2789"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS64566.2025.00097"},{"key":"ref38","article-title":"MAO: Machine learning approach for NUMA optimization in warehouse-scale computers","author":"Liu","year":"2024"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.14778\/3746405.3746427"},{"key":"ref40","article-title":"Towards understanding systems trade-offs in retrieval-augmented generation model inference","author":"Shen","year":"2024"},{"key":"ref41","article-title":"LEANN: A low-storage vector index","author":"Wang","year":"2025"},{"key":"ref42","article-title":"CXL TCO Calculator","year":"2026"},{"key":"ref43","article-title":"Deep reinforcement learning for real-time green energy integration in data centers","author":"Bahi","year":"2025"},{"key":"ref44","article-title":"Streaming CXL adoption for hyperscale efficiency","author":"Arelakis","year":"2024"},{"key":"ref45","article-title":"The Hitchhiker\u2019s guide to programming and optimizing cache coherent heterogeneous systems: CXL, NVLink-C2C, and AMD infinity fabric","author":"Wang","year":"2025"}],"container-title":["IEEE Transactions on Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/12\/11435995\/11298523.pdf?arnumber=11298523","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T05:07:55Z","timestamp":1773810475000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11298523\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":45,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tc.2025.3643434","relation":{},"ISSN":["0018-9340","1557-9956","2326-3814"],"issn-type":[{"value":"0018-9340","type":"print"},{"value":"1557-9956","type":"electronic"},{"value":"2326-3814","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}