{"id":"https://openalex.org/W4411471835","doi":"https://doi.org/10.1145/3695053.3731079","title":"DReX: Accurate and Scalable Dense Retrieval Acceleration via Algorithmic-Hardware Codesign","display_name":"DReX: Accurate and Scalable Dense Retrieval Acceleration via Algorithmic-Hardware Codesign","publication_year":2025,"publication_date":"2025-06-20","ids":{"openalex":"https://openalex.org/W4411471835","doi":"https://doi.org/10.1145/3695053.3731079"},"language":"en","primary_location":{"id":"doi:10.1145/3695053.3731079","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3695053.3731079","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3695053.3731079","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd Annual International Symposium on Computer Architecture","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3695053.3731079","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023012463","display_name":"Derrick Quinn","orcid":"https://orcid.org/0009-0000-5862-6565"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Derrick Quinn","raw_affiliation_strings":["Cornell University, Ithaca, NY, USA"],"affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118397438","display_name":"E. Ezgi Y\u00fccel","orcid":"https://orcid.org/0009-0000-0460-8230"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"E. Ezgi Y\u00fccel","raw_affiliation_strings":["Cornell University, Ithaca, NY, USA"],"affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021820528","display_name":"Martin Prammer","orcid":"https://orcid.org/0009-0000-4348-236X"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martin Prammer","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046797905","display_name":"Zhenxing Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhenxing Fan","raw_affiliation_strings":["University of Virginia, Charlottesville, VA, USA"],"affiliations":[{"raw_affiliation_string":"University of Virginia, Charlottesville, VA, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074818897","display_name":"Kevin Skadron","orcid":"https://orcid.org/0000-0002-8091-9302"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Skadron","raw_affiliation_strings":["University of Virginia, Charlottesville, VA, USA"],"affiliations":[{"raw_affiliation_string":"University of Virginia, Charlottesville, VA, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069237428","display_name":"Jignesh M. Patel","orcid":"https://orcid.org/0000-0003-3653-2538"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jignesh M. Patel","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083127721","display_name":"Jos\u00e9 F. Mart\u00ednez","orcid":"https://orcid.org/0000-0001-5451-5681"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 F. Mart\u00ednez","raw_affiliation_strings":["Cornell University, Ithaca, NY, USA"],"affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069911395","display_name":"Mohammad Alian","orcid":"https://orcid.org/0000-0002-4622-2181"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Alian","raw_affiliation_strings":["Cornell University, Ithaca, NY, USA"],"affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5023012463"],"corresponding_institution_ids":["https://openalex.org/I205783295"],"apc_list":null,"apc_paid":null,"fwci":2.5568,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.89890805,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1108","last_page":"1124"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9944000244140625,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9940000176429749,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.8015247583389282},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7710065841674805},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.6933156251907349},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.5941564440727234},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.43924930691719055},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.37564876675605774},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.37090450525283813},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3672594428062439},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3482898473739624},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.24190732836723328},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.12636405229568481},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07354095578193665}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8015247583389282},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7710065841674805},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.6933156251907349},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.5941564440727234},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.43924930691719055},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.37564876675605774},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.37090450525283813},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3672594428062439},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3482898473739624},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.24190732836723328},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.12636405229568481},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07354095578193665},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3695053.3731079","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3695053.3731079","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3695053.3731079","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd Annual International Symposium on Computer Architecture","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3695053.3731079","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3695053.3731079","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3695053.3731079","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd Annual International Symposium on Computer Architecture","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1452086972","display_name":null,"funder_award_id":"JUMP 2.0","funder_id":"https://openalex.org/F4320306087","funder_display_name":"Semiconductor Research Corporation"},{"id":"https://openalex.org/G171229425","display_name":"Collaborative Research: SHF: Medium: A hardware-software co-design approach for high-performance in-memory analytic data processing","funder_award_id":"2312739","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3109017302","display_name":"Collaborative Research: SHF: Medium: A hardware-software co-design approach for high-performance in-memory analytic data processing","funder_award_id":"2407690","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3541748552","display_name":null,"funder_award_id":"CCF-2239020","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3734241260","display_name":null,"funder_award_id":"JUMP 2.0 research centers ACE and PRISM","funder_id":"https://openalex.org/F4320306087","funder_display_name":"Semiconductor Research Corporation"},{"id":"https://openalex.org/G6625619449","display_name":null,"funder_award_id":"CCF-22170","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7704717666","display_name":"Collaborative Research: SHF: Medium: A hardware-software co-design approach for high-performance in-memory analytic data processing","funder_award_id":"2312740","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7869976093","display_name":"Collaborative Research: SHF: Medium: A hardware-software co-design approach for high-performance in-memory analytic data processing","funder_award_id":"2312741","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8735212043","display_name":null,"funder_award_id":"CCF-2239020, CCF-2217071, CCF-2312739, CCF-2312740, CCF-2312741, and CCF-2407690","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G879073502","display_name":"CAREER: Near-Memory Datacenter Network","funder_award_id":"2239020","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8794816260","display_name":null,"funder_award_id":"PRISM","funder_id":"https://openalex.org/F4320306087","funder_display_name":"Semiconductor Research Corporation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411471835.pdf","grobid_xml":"https://content.openalex.org/works/W4411471835.grobid-xml"},"referenced_works_count":58,"referenced_works":["https://openalex.org/W1978394996","https://openalex.org/W1986693891","https://openalex.org/W1999085092","https://openalex.org/W2039742379","https://openalex.org/W2065653320","https://openalex.org/W2071866949","https://openalex.org/W2084363474","https://openalex.org/W2086179657","https://openalex.org/W2121456571","https://openalex.org/W2124509324","https://openalex.org/W2133995768","https://openalex.org/W2144211451","https://openalex.org/W2147717514","https://openalex.org/W2250539671","https://openalex.org/W2588191434","https://openalex.org/W2757662681","https://openalex.org/W2787275496","https://openalex.org/W2963284996","https://openalex.org/W2963469388","https://openalex.org/W2963521540","https://openalex.org/W3006586535","https://openalex.org/W3012047118","https://openalex.org/W3036079062","https://openalex.org/W3038572442","https://openalex.org/W3099700870","https://openalex.org/W3156789018","https://openalex.org/W3160149608","https://openalex.org/W3174809957","https://openalex.org/W3189166979","https://openalex.org/W3191222816","https://openalex.org/W3196481040","https://openalex.org/W4200515834","https://openalex.org/W4214821564","https://openalex.org/W4226321975","https://openalex.org/W4280568654","https://openalex.org/W4288103229","https://openalex.org/W4308083511","https://openalex.org/W4312854033","https://openalex.org/W4380881154","https://openalex.org/W4381610063","https://openalex.org/W4384774018","https://openalex.org/W4385573236","https://openalex.org/W4385688545","https://openalex.org/W4386576685","https://openalex.org/W4388757726","https://openalex.org/W4389470986","https://openalex.org/W4390041933","https://openalex.org/W4391418506","https://openalex.org/W4393399908","https://openalex.org/W4393407316","https://openalex.org/W4394998968","https://openalex.org/W4395020674","https://openalex.org/W4399115375","https://openalex.org/W4400641571","https://openalex.org/W4400681611","https://openalex.org/W4404133855","https://openalex.org/W4407197060","https://openalex.org/W4407448732"],"related_works":["https://openalex.org/W2389214306","https://openalex.org/W2965083567","https://openalex.org/W2565094479","https://openalex.org/W4235240664","https://openalex.org/W1838576100","https://openalex.org/W2390829436","https://openalex.org/W2095886385","https://openalex.org/W1989791859","https://openalex.org/W2146872326","https://openalex.org/W3158825072"],"abstract_inverted_index":{"Retrieval-augmented":[0],"generation":[1,64],"(RAG)":[2],"supplements":[3],"large":[4],"language":[5],"models":[6],"(LLM)":[7],"with":[8],"information":[9],"retrieval":[10,25],"to":[11,39,44,53,60,70,98],"ensure":[12],"up-to-date,":[13],"accurate,":[14,82],"factually":[15],"grounded,":[16],"and":[17,27,37,83,130,133,141,172],"contextually":[18],"relevant":[19],"outputs.RAG":[20],"implementations":[21],"often":[22],"employ":[23],"dense":[24],"methods":[26],"approximate":[28],"k-nearest":[29],"neighbor":[30,117],"search":[31],"(ANNS).Unfortunately,":[32],"ANNS":[33],"is":[34,51],"inherently":[35],"dataset-specific":[36],"prone":[38],"low":[40],"recall,":[41],"potentially":[42],"leading":[43],"inaccuracies":[45],"when":[46],"irrelevant":[47],"or":[48],"incomplete":[49],"context":[50],"passed":[52],"the":[54,61,107,120,137,176],"LLM.Furthermore,":[55],"sending":[56],"numerous":[57],"imprecise":[58],"documents":[59],"LLM":[62],"for":[63,139,159],"can":[65],"significantly":[66],"degrade":[67],"performance":[68],"compared":[69],"processing":[71],"a":[72,80,91,154,160,165],"smaller":[73],"set":[74],"of":[75,102],"accurate":[76],"documents.We":[77],"propose":[78],"DReX,":[79],"dataset-agnostic,":[81],"scalable":[84],"Dense":[85],"Retrieval":[86],"Acceleration":[87],"scheme":[88],"enabled":[89],"through":[90],"novel":[92],"algorithmic-hardware":[93],"co-design.We":[94],"leverage":[95],"in-DRAM":[96],"logic":[97],"enable":[99],"early":[100],"filtering":[101],"embedding":[103],"vectors":[104],"far":[105],"from":[106],"query":[108],"vector.An":[109],"outside-DRAM":[110],"near-memory":[111],"accelerator":[112],"then":[113],"performs":[114],"exact":[115],"nearest":[116],"searches":[118],"on":[119],"remaining":[121],"filtered":[122],"embeddings.This":[123],"resulting":[124],"design":[125],"minimizes":[126],"off-chip":[127],"data":[128],"movement":[129],"ensures":[131],"precise":[132],"efficient":[134],"retrieval,":[135],"laying":[136],"foundation":[138],"robust":[140],"performant":[142],"RAG":[143,162],"systems":[144],"that":[145,151],"are":[146],"broadly":[147],"applicable.Our":[148],"evaluation":[149],"shows":[150],"DReX":[152],"delivers":[153],"6.2-7":[155],"reduction":[156],"in":[157,175],"time-to-first-token":[158],"representative":[161],"application":[163],"over":[164],"state-of-the-art":[166],"mechanism":[167],"while":[168],"incurring":[169],"reasonable":[170],"area":[171],"power":[173],"overheads":[174],"memory":[177],"subsystem.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}