{"id":"https://openalex.org/W4416963201","doi":"https://doi.org/10.1109/islped65674.2025.11261807","title":"DIRC-RAG: Accelerating Edge RAG with Robust High-Density and High-Loading-Bandwidth Digital In-ReRAM Computation","display_name":"DIRC-RAG: Accelerating Edge RAG with Robust High-Density and High-Loading-Bandwidth Digital In-ReRAM Computation","publication_year":2025,"publication_date":"2025-08-06","ids":{"openalex":"https://openalex.org/W4416963201","doi":"https://doi.org/10.1109/islped65674.2025.11261807"},"language":"en","primary_location":{"id":"doi:10.1109/islped65674.2025.11261807","is_oa":false,"landing_page_url":"https://doi.org/10.1109/islped65674.2025.11261807","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED)","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/A5080073605","display_name":"Kunming Shao","orcid":"https://orcid.org/0009-0002-9459-0779"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kunming Shao","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024795353","display_name":"Zhipeng Liao","orcid":"https://orcid.org/0000-0003-0804-2371"},"institutions":[{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhipeng Liao","raw_affiliation_strings":["University of Southampton"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southampton","institution_ids":["https://openalex.org/I43439940"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079545857","display_name":"Jiangnan Yu","orcid":"https://orcid.org/0000-0002-6417-2501"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiangnan Yu","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061568038","display_name":"Liang Zhao","orcid":"https://orcid.org/0000-0001-5829-6850"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Zhao","raw_affiliation_strings":["South China University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061142418","display_name":"Q. Li","orcid":"https://orcid.org/0009-0007-2531-6537"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiwei Li","raw_affiliation_strings":["Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002384034","display_name":"Xijie Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xijie Huang","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064455588","display_name":"Jingyu He","orcid":"https://orcid.org/0000-0001-5908-8738"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jingyu He","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009667181","display_name":"Fengshi Tian","orcid":"https://orcid.org/0000-0003-1304-5593"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Fengshi Tian","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100458990","display_name":"Yi Zou","orcid":"https://orcid.org/0000-0002-4382-4670"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Zou","raw_affiliation_strings":["South China University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100423401","display_name":"Xiaomeng Wang","orcid":"https://orcid.org/0000-0003-2169-3013"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiaomeng Wang","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tim Kwang-Ting Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tim Kwang-Ting Cheng","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072596277","display_name":"Chi-Ying Tsui","orcid":"https://orcid.org/0000-0002-8024-2637"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chi-Ying Tsui","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.29010000824928284,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.29010000824928284,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.2508000135421753,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.14090000092983246,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/static-random-access-memory","display_name":"Static random-access memory","score":0.6715999841690063},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5848000049591064},{"id":"https://openalex.org/keywords/resistive-random-access-memory","display_name":"Resistive random-access memory","score":0.5509999990463257},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.4318999946117401},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.4278999865055084},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.4124999940395355},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.40130001306533813},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.39910000562667847},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.3700000047683716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7490000128746033},{"id":"https://openalex.org/C68043766","wikidata":"https://www.wikidata.org/wiki/Q267416","display_name":"Static random-access memory","level":2,"score":0.6715999841690063},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5848000049591064},{"id":"https://openalex.org/C182019814","wikidata":"https://www.wikidata.org/wiki/Q1143830","display_name":"Resistive random-access memory","level":3,"score":0.5509999990463257},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.4318999946117401},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.4278999865055084},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.4165000021457672},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.4124999940395355},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.40130001306533813},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.39910000562667847},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.3700000047683716},{"id":"https://openalex.org/C46362747","wikidata":"https://www.wikidata.org/wiki/Q173431","display_name":"CMOS","level":2,"score":0.33799999952316284},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C77390884","wikidata":"https://www.wikidata.org/wiki/Q217302","display_name":"Application-specific integrated circuit","level":2,"score":0.32170000672340393},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.28439998626708984},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.2800000011920929},{"id":"https://openalex.org/C78371743","wikidata":"https://www.wikidata.org/wiki/Q1672829","display_name":"Optical proximity correction","level":3,"score":0.2791000008583069},{"id":"https://openalex.org/C2776638159","wikidata":"https://www.wikidata.org/wiki/Q18343761","display_name":"Memory cell","level":4,"score":0.2703999876976013},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.2696000039577484},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2676999866962433},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.2653000056743622},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.2556000053882599}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/islped65674.2025.11261807","is_oa":false,"landing_page_url":"https://doi.org/10.1109/islped65674.2025.11261807","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-169438","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-169438","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2470818894","https://openalex.org/W2613205562","https://openalex.org/W2798329376","https://openalex.org/W2885441816","https://openalex.org/W2963122961","https://openalex.org/W2970641574","https://openalex.org/W3035324702","https://openalex.org/W3099977667","https://openalex.org/W3134526034","https://openalex.org/W3179961400","https://openalex.org/W4220837341","https://openalex.org/W4293261839","https://openalex.org/W4360831836","https://openalex.org/W4387490588","https://openalex.org/W4388469767","https://openalex.org/W4389162410","https://openalex.org/W4391407189","https://openalex.org/W4392746125","https://openalex.org/W4404520182","https://openalex.org/W4406025423","https://openalex.org/W4407197060","https://openalex.org/W4408182783","https://openalex.org/W4408245641","https://openalex.org/W4409282487","https://openalex.org/W4410552861","https://openalex.org/W4411726814"],"related_works":[],"abstract_inverted_index":{"Retrieval-Augmented":[0],"Generation":[1],"(RAG)":[2],"enhances":[3],"large":[4],"language":[5],"models":[6],"(LLMs)":[7],"by":[8,33,48,153],"integrating":[9],"external":[10],"knowledge":[11],"retrieval":[12,213,226],"but":[13,45],"faces":[14],"challenges":[15],"on":[16],"edge":[17,66],"devices":[18],"due":[19],"to":[20,123,177],"high":[21],"storage,":[22],"energy,":[23],"and":[24,40,88,95,120,139,164,203,217],"latency":[25,121,214],"demands.":[26],"Computing-in-Memory":[27],"(CIM)":[28],"offers":[29],"a":[30,64,77,204,211],"promising":[31],"solution":[32],"storing":[34,101],"document":[35,103],"embeddings":[36,104],"in":[37],"CIM":[38,107],"macros":[39],"enabling":[41],"in-situ":[42],"parallel":[43],"retrievals":[44],"is":[46,130,174],"constrained":[47],"either":[49],"low":[50],"memory":[51,197],"density":[52,198],"or":[53],"limited":[54],"computational":[55],"accuracy.":[56],"To":[57],"address":[58],"these":[59],"challenges,":[60],"we":[61],"present":[62],"DIRC-RAG,":[63],"novel":[65],"RAG":[67,133],"acceleration":[68],"architecture":[69],"leveraging":[70],"Digital":[71],"In-ReRAM":[72],"Computation":[73],"(DIRC).":[74],"DIRC":[75,109,150],"integrates":[76],"high-density":[78],"multi-level":[79],"ReRAM":[80,93,162],"subarray":[81,163],"with":[82],"an":[83,194,218],"SRAM":[84,87,141],"cell,":[85],"utilizing":[86],"differential":[89],"sensing":[90],"for":[91,132,148],"robust":[92],"readout":[94,179],"digital":[96],"multiply-accumulate":[97],"(MAC)":[98],"operations.":[99],"By":[100],"all":[102],"within":[105],"the":[106,149,155,161,225],"macro,":[108],"achieves":[110,193],"ultra-low-power,":[111],"single-cycle":[112],"data":[113,137,168],"loading,":[114],"substantially":[115],"reducing":[116,140],"both":[117],"energy":[118,219],"consumption":[119,220],"compared":[122],"off-chip":[124],"DRAM.":[125],"A":[126],"query-stationary":[127],"(QS)":[128],"dataflow":[129],"supported":[131],"tasks,":[134],"minimizing":[135],"on-chip":[136,195],"movement":[138],"buffer":[142],"requirements.":[143],"We":[144],"introduce":[145],"error":[146,158,171],"optimization":[147],"ReRAM-SRAM":[151],"cell":[152],"extracting":[154],"bit-wise":[156,167],"spatial":[157],"distribution":[159],"of":[160,199,206,215,221],"applying":[165],"targeted":[166],"remapping.":[169],"An":[170],"detection":[172],"circuit":[173],"also":[175],"implemented":[176],"enhance":[178],"resilience":[180],"against":[181],"device-and":[182],"circuit-level":[183],"variations.Simulation":[184],"results":[185],"demonstrate":[186],"that":[187],"DIRC-RAG":[188],"under":[189],"TSMC":[190],"40nm":[191],"process":[192],"non-volatile":[196],"5.18Mb/mm<sup":[200],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[201],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[202],"throughput":[205],"131":[207],"TOPS.":[208],"It":[209],"delivers":[210],"4MB":[212],"5.6\u03bcs/query":[216],"0.956\u03bcJ/query,":[222],"while":[223],"maintaining":[224],"precision.":[227]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-12-03T00:00:00"}
