{"id":"https://openalex.org/W4414198840","doi":"https://doi.org/10.1109/dac63849.2025.11132497","title":"Move Less, Retrieve Fast: A Retrieval-in-Memory Architecture for Language Models","display_name":"Move Less, Retrieve Fast: A Retrieval-in-Memory Architecture for Language Models","publication_year":2025,"publication_date":"2025-06-22","ids":{"openalex":"https://openalex.org/W4414198840","doi":"https://doi.org/10.1109/dac63849.2025.11132497"},"language":"en","primary_location":{"id":"doi:10.1109/dac63849.2025.11132497","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac63849.2025.11132497","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 62nd ACM/IEEE Design Automation Conference (DAC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057512648","display_name":"Jiaxian Chen","orcid":"https://orcid.org/0000-0002-1576-5992"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxian Chen","raw_affiliation_strings":["Shenzhen University,College of Computer Science and Software Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen University,College of Computer Science and Software Engineering","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101491985","display_name":"Yue Qi","orcid":"https://orcid.org/0000-0001-9304-1933"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxuan Qi","raw_affiliation_strings":["Shenzhen University,College of Computer Science and Software Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen University,College of Computer Science and Software Engineering","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115604861","display_name":"Jianan Yuan","orcid":"https://orcid.org/0009-0006-2656-1289"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianan Yuan","raw_affiliation_strings":["Shenzhen University,College of Computer Science and Software Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen University,College of Computer Science and Software Engineering","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021562819","display_name":"Kaoyi Sun","orcid":"https://orcid.org/0000-0002-0625-981X"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaoyi Sun","raw_affiliation_strings":["Shenzhen University,College of Computer Science and Software Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen University,College of Computer Science and Software Engineering","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100417411","display_name":"Tianyu Wang","orcid":"https://orcid.org/0000-0001-7030-1990"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyu Wang","raw_affiliation_strings":["Shenzhen University,College of Computer Science and Software Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen University,College of Computer Science and Software Engineering","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044419677","display_name":"Chenlin Ma","orcid":"https://orcid.org/0000-0002-0497-123X"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenlin Ma","raw_affiliation_strings":["Shenzhen University,College of Computer Science and Software Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen University,College of Computer Science and Software Engineering","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100364961","display_name":"Yi Wang","orcid":"https://orcid.org/0000-0002-5773-3817"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Wang","raw_affiliation_strings":["Shenzhen University,College of Computer Science and Software Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen University,College of Computer Science and Software Engineering","institution_ids":["https://openalex.org/I180726961"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I180726961"],"apc_list":null,"apc_paid":null,"fwci":1.673,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85084188,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9459999799728394,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.6499000191688538},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5389999747276306},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5187000036239624},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5031999945640564},{"id":"https://openalex.org/keywords/data-access","display_name":"Data access","score":0.4918999969959259},{"id":"https://openalex.org/keywords/software-architecture-description","display_name":"Software architecture description","score":0.38690000772476196},{"id":"https://openalex.org/keywords/software-architecture","display_name":"Software architecture","score":0.3472999930381775},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.34630000591278076},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.3416999876499176}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8687999844551086},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.6499000191688538},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.6402999758720398},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5389999747276306},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5187000036239624},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5031999945640564},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.4918999969959259},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.41179999709129333},{"id":"https://openalex.org/C73219336","wikidata":"https://www.wikidata.org/wiki/Q7554254","display_name":"Software architecture description","level":5,"score":0.38690000772476196},{"id":"https://openalex.org/C35869016","wikidata":"https://www.wikidata.org/wiki/Q846636","display_name":"Software architecture","level":3,"score":0.3472999930381775},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.34630000591278076},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.3416999876499176},{"id":"https://openalex.org/C154240960","wikidata":"https://www.wikidata.org/wiki/Q2860294","display_name":"Database-centric architecture","level":5,"score":0.3312000036239624},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C551230270","wikidata":"https://www.wikidata.org/wiki/Q4368942","display_name":"Data retrieval","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3091000020503998},{"id":"https://openalex.org/C98025372","wikidata":"https://www.wikidata.org/wiki/Q477538","display_name":"Systems architecture","level":3,"score":0.3034000098705292},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27900001406669617},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27799999713897705},{"id":"https://openalex.org/C55356503","wikidata":"https://www.wikidata.org/wiki/Q2136675","display_name":"Reference architecture","level":4,"score":0.27730000019073486},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.27709999680519104},{"id":"https://openalex.org/C94070970","wikidata":"https://www.wikidata.org/wiki/Q638422","display_name":"Data architecture","level":5,"score":0.27090001106262207},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C56288433","wikidata":"https://www.wikidata.org/wiki/Q58673","display_name":"Data manipulation language","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.26030001044273376},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.25519999861717224},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.25279998779296875},{"id":"https://openalex.org/C2779965156","wikidata":"https://www.wikidata.org/wiki/Q5227350","display_name":"Data sharing","level":3,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dac63849.2025.11132497","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac63849.2025.11132497","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 62nd ACM/IEEE Design Automation Conference (DAC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2124509324","https://openalex.org/W2728809642","https://openalex.org/W2963469388","https://openalex.org/W2998702515","https://openalex.org/W3006586535","https://openalex.org/W3100806282","https://openalex.org/W3156789018","https://openalex.org/W3178213104","https://openalex.org/W3189166979","https://openalex.org/W4280568654","https://openalex.org/W4285122897","https://openalex.org/W4361857408","https://openalex.org/W4385573102","https://openalex.org/W4386764001","https://openalex.org/W4386764554","https://openalex.org/W4404133855","https://openalex.org/W4404134065"],"related_works":[],"abstract_inverted_index":{"Retrieval-augmented":[0],"language":[1,15],"models":[2],"(RALMs)":[3],"have":[4],"attracted":[5],"widespread":[6],"attention":[7],"for":[8,58,87],"addressing":[9],"the":[10,32,67,107,126,140,151,154],"limitations":[11],"of":[12,36,153,173],"traditional":[13],"large":[14],"models.":[16],"However,":[17],"challenges":[18],"involved":[19],"in":[20,65,90,147],"retrieval,":[21],"including":[22],"substantial":[23],"data":[24,97,123,130,168],"movement":[25,98],"and":[26,34,50,77,99,132,178,184],"irregular":[27,141],"access":[28,142],"patterns,":[29],"seriously":[30],"impact":[31],"efficiency":[33],"deployment":[35],"RALMs.":[37,91,148],"The":[38,92,160],"emerging":[39],"3D-stacked":[40],"processing-in-memory":[41],"(PIM)":[42],"architecture,":[43],"characterized":[44],"by":[45],"its":[46],"high":[47],"memory":[48],"bandwidth":[49],"near-data":[51],"computing":[52],"capabilities,":[53],"presents":[54,82],"a":[55,84,110,115],"promising":[56],"solution":[57],"efficient":[59],"retrieval.":[60],"To":[61],"support":[62],"large-scale":[63],"retrieval":[64,89,146],"RALMs,":[66],"PIM":[68,112],"architecture":[69,86,113],"should":[70],"be":[71],"carefully":[72],"designed":[73,119],"with":[74,114,145],"joint":[75],"software":[76,127],"hardware":[78,108],"optimization.":[79],"This":[80],"paper":[81],"Rimast,":[83],"retrieval-in-memory":[85,116],"fast":[88],"objective":[93],"is":[94,118],"to":[95,120,138],"minimize":[96],"improve":[100],"overall":[101],"performance":[102],"through":[103],"hardwaresoftware":[104],"co-design.":[105],"At":[106,125],"level,":[109,128],"hierarchical":[111],"dataflow":[117],"reduce":[121],"unnecessary":[122],"transfer.":[124],"skew-free":[129],"mapping":[131],"adaptive":[133],"offloading":[134],"strategies":[135],"are":[136],"proposed":[137,155],"address":[139],"patterns":[143],"associated":[144],"We":[149],"demonstrate":[150,163],"effectiveness":[152],"Rimast":[156,165],"using":[157],"extensive":[158],"experiments.":[159],"experimental":[161],"results":[162],"that":[164],"effectively":[166],"reduces":[167],"movement,":[169],"achieving":[170],"average":[171],"speedups":[172],"$273":[174],"\\times":[175],"55":[176],"\\times$,":[177],"$2.41":[179],"\\times$":[180],"over":[181],"CPUs,":[182],"GPUs,":[183],"prior":[185],"art":[186],"accelerators,":[187],"respectively.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
