{"id":"https://openalex.org/W3163294349","doi":"https://doi.org/10.1145/3466752.3480127","title":"RecPipe: Co-designing Models and Hardware to Jointly Optimize Recommendation Quality and Performance","display_name":"RecPipe: Co-designing Models and Hardware to Jointly Optimize Recommendation Quality and Performance","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3163294349","doi":"https://doi.org/10.1145/3466752.3480127","mag":"3163294349"},"language":"en","primary_location":{"id":"doi:10.1145/3466752.3480127","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3466752.3480127","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"MICRO-54: 54th Annual IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2105.08820","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035704218","display_name":"Udit Gupta","orcid":"https://orcid.org/0000-0002-9118-0961"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]},{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Udit Gupta","raw_affiliation_strings":["Harvard University/FAIR, United States of America","Harvard University ,"],"affiliations":[{"raw_affiliation_string":"Harvard University/FAIR, United States of America","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"Harvard University ,","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047381366","display_name":"Samuel Hsia","orcid":null},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samuel Hsia","raw_affiliation_strings":["Harvard University, United States of America"],"affiliations":[{"raw_affiliation_string":"Harvard University, United States of America","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077249620","display_name":"Jeff Zhang","orcid":"https://orcid.org/0000-0001-7411-8923"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeff Zhang","raw_affiliation_strings":["Harvard University, United States of America"],"affiliations":[{"raw_affiliation_string":"Harvard University, United States of America","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003878521","display_name":"Mark Wilkening","orcid":"https://orcid.org/0009-0008-7730-448X"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Wilkening","raw_affiliation_strings":["Harvard University, United States of America"],"affiliations":[{"raw_affiliation_string":"Harvard University, United States of America","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086944328","display_name":"Javin Pombra","orcid":null},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Javin Pombra","raw_affiliation_strings":["Harvard University","Harvard University ,"],"affiliations":[{"raw_affiliation_string":"Harvard University","institution_ids":["https://openalex.org/I2801851002"]},{"raw_affiliation_string":"Harvard University ,","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072539515","display_name":"Hsien-Hsin S. Lee","orcid":"https://orcid.org/0000-0002-8926-8243"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hsien-Hsin Sean Lee","raw_affiliation_strings":["Facebook AI Research, United States of America"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research, United States of America","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043327132","display_name":"Gu-Yeon Wei","orcid":"https://orcid.org/0000-0001-5730-9904"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gu-Yeon Wei","raw_affiliation_strings":["Harvard University","Harvard University ,"],"affiliations":[{"raw_affiliation_string":"Harvard University","institution_ids":["https://openalex.org/I2801851002"]},{"raw_affiliation_string":"Harvard University ,","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028220093","display_name":"Carole-Jean Wu","orcid":"https://orcid.org/0000-0002-9032-7239"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carole-Jean Wu","raw_affiliation_strings":["Facebook/ASU, United States of America"],"affiliations":[{"raw_affiliation_string":"Facebook/ASU, United States of America","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026496503","display_name":"David Brooks","orcid":"https://orcid.org/0000-0002-0662-7889"},"institutions":[{"id":"https://openalex.org/I4210141641","display_name":"IIT@Harvard","ror":"https://ror.org/044hpwe09","country_code":"US","type":"facility","lineage":["https://openalex.org/I30771326","https://openalex.org/I4210141641"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Brooks","raw_affiliation_strings":["Harvard, United States of America"],"affiliations":[{"raw_affiliation_string":"Harvard, United States of America","institution_ids":["https://openalex.org/I4210141641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5035704218"],"corresponding_institution_ids":["https://openalex.org/I136199984","https://openalex.org/I2801851002"],"apc_list":null,"apc_paid":null,"fwci":0.2844,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.60017328,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"870","last_page":"884"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9977999925613403,"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/T11478","display_name":"Caching and Content Delivery","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8299072980880737},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.7521608471870422},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6188807487487793},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6172846555709839},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5744597911834717},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4598484933376312},{"id":"https://openalex.org/keywords/design-space-exploration","display_name":"Design space exploration","score":0.4562394320964813},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4544461667537689},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4466087818145752},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.4130329489707947},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4032297134399414},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.34527987241744995},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.17795145511627197},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14893412590026855},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.1440315842628479},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.10187900066375732}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8299072980880737},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7521608471870422},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6188807487487793},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6172846555709839},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5744597911834717},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4598484933376312},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.4562394320964813},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4544461667537689},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4466087818145752},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.4130329489707947},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4032297134399414},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.34527987241744995},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17795145511627197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14893412590026855},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.1440315842628479},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.10187900066375732},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1145/3466752.3480127","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3466752.3480127","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"MICRO-54: 54th Annual IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2105.08820","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.08820","pdf_url":"https://arxiv.org/pdf/2105.08820","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.2105.08820","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2105.08820","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.5281/zenodo.5146294","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.5146294","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.5281/zenodo.5146295","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.5146295","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"mag:3163294349","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2105.08820","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.08820","pdf_url":"https://arxiv.org/pdf/2105.08820","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"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/F4320307102","display_name":"Intel Corporation","ror":"https://ror.org/01ek73717"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3163294349.pdf"},"referenced_works_count":63,"referenced_works":["https://openalex.org/W2048266589","https://openalex.org/W2069870183","https://openalex.org/W2142697503","https://openalex.org/W2219888463","https://openalex.org/W2285660444","https://openalex.org/W2289252105","https://openalex.org/W2513554817","https://openalex.org/W2542189141","https://openalex.org/W2565851976","https://openalex.org/W2589156932","https://openalex.org/W2605350416","https://openalex.org/W2606722458","https://openalex.org/W2612445135","https://openalex.org/W2723293840","https://openalex.org/W2794670651","https://openalex.org/W2900810680","https://openalex.org/W2911491685","https://openalex.org/W2947737663","https://openalex.org/W2948229371","https://openalex.org/W2953212265","https://openalex.org/W2962745591","https://openalex.org/W2963163009","https://openalex.org/W2963358710","https://openalex.org/W2972269283","https://openalex.org/W2973172293","https://openalex.org/W2974215621","https://openalex.org/W2975367729","https://openalex.org/W2979313476","https://openalex.org/W2979719709","https://openalex.org/W2982930951","https://openalex.org/W2984020950","https://openalex.org/W2984140583","https://openalex.org/W3010969086","https://openalex.org/W3012897490","https://openalex.org/W3016842236","https://openalex.org/W3016939927","https://openalex.org/W3035318851","https://openalex.org/W3042495273","https://openalex.org/W3043023836","https://openalex.org/W3043433718","https://openalex.org/W3045045900","https://openalex.org/W3088420542","https://openalex.org/W3095776306","https://openalex.org/W3097822150","https://openalex.org/W3101026687","https://openalex.org/W3109610142","https://openalex.org/W3113181213","https://openalex.org/W3125484574","https://openalex.org/W3130104841","https://openalex.org/W3133241465","https://openalex.org/W3134691233","https://openalex.org/W3138787737","https://openalex.org/W3155243801","https://openalex.org/W3157531038","https://openalex.org/W3158146252","https://openalex.org/W3160344148","https://openalex.org/W3166863226","https://openalex.org/W3166914430","https://openalex.org/W3167625290","https://openalex.org/W3191222816","https://openalex.org/W3193626058","https://openalex.org/W4239385313","https://openalex.org/W4240168186"],"related_works":["https://openalex.org/W3144271226","https://openalex.org/W3161161408","https://openalex.org/W2896180420","https://openalex.org/W3104995883","https://openalex.org/W2108404227","https://openalex.org/W3196336542","https://openalex.org/W2122493521","https://openalex.org/W2158873318","https://openalex.org/W3000777515","https://openalex.org/W2793528961","https://openalex.org/W1487031710","https://openalex.org/W2984200518","https://openalex.org/W128462016","https://openalex.org/W2991186234","https://openalex.org/W1980478243","https://openalex.org/W2931850608","https://openalex.org/W2094124398","https://openalex.org/W2793112343","https://openalex.org/W1992662900","https://openalex.org/W2604883028"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"recommendation":[2,27,37,62,126,151],"systems":[3],"must":[4],"provide":[5],"high":[6,15],"quality,":[7,99],"personalized":[8],"content":[9],"under":[10],"strict":[11],"tail-latency":[12],"targets":[13],"and":[14,29,49,101,131,141,153,162,167],"system":[16,23,102],"loads.":[17],"This":[18],"paper":[19],"presents":[20],"RecPipe,":[21],"a":[22,93,135,142],"to":[24,33,42,59,108,124,147],"jointly":[25,97],"optimize":[26],"quality":[28,44],"inference":[30,57],"performance.":[31],"Central":[32],"RecPipe":[34,54],"is":[35,105],"decomposing":[36],"models":[38],"into":[39],"multi-stage":[40,61],"pipelines":[41],"maintain":[43],"while":[45],"reducing":[46],"compute":[47],"complexity":[48],"exposing":[50],"distinct":[51,111],"parallelism":[52],"opportunities.":[53],"implements":[55,128],"an":[56],"scheduler":[58],"map":[60],"engines":[63],"onto":[64],"commodity,":[65],"heterogeneous":[66],"platforms":[67,80],"(e.g.,":[68],"CPUs,":[69],"GPUs).":[70],"While":[71],"the":[72,78,110],"hardware-aware":[73],"scheduling":[74],"improves":[75,160],"ranking":[76],"efficiency,":[77],"commodity":[79],"suffer":[81],"from":[82],"many":[83],"limitations":[84],"requiring":[85],"specialized":[86,150],"hardware.":[87],"Thus,":[88],"we":[89,156],"design":[90,112],"RecPipeAccel":[91],"(RPAccel),":[92],"custom":[94],"accelerator":[95],"that":[96,158],"optimizes":[98],"tail-latency,":[100],"throughput.":[103],"RPAccel":[104,119,159],"designed":[106],"specifically":[107],"exploit":[109],"space":[113],"opened":[114],"via":[115],"RecPipe.":[116],"In":[117],"particular,":[118],"processes":[120],"queries":[121],"in":[122],"sub-batches":[123],"pipeline":[125],"stages,":[127],"dual":[129],"static":[130],"dynamic":[132],"embedding":[133],"caches,":[134],"set":[136],"of":[137],"top-k":[138],"filtering":[139],"units,":[140],"reconfigurable":[143],"systolic":[144],"array.":[145],"Compared":[146],"previously":[148],"proposed":[149],"accelerators":[152],"at":[154],"iso-quality,":[155],"demonstrate":[157],"latency":[161],"throughput":[163],"by":[164],"3":[165],"\u00d7":[166],"6":[168],"\u00d7.":[169]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}