{"id":"https://openalex.org/W7131275352","doi":"https://doi.org/10.1109/mm.2026.3666797","title":"Beyond the Accelerator: A Full-Stack HW/SW Co-Design Analysis for Recommendation System Inference","display_name":"Beyond the Accelerator: A Full-Stack HW/SW Co-Design Analysis for Recommendation System Inference","publication_year":2026,"publication_date":"2026-02-24","ids":{"openalex":"https://openalex.org/W7131275352","doi":"https://doi.org/10.1109/mm.2026.3666797"},"language":null,"primary_location":{"id":"doi:10.1109/mm.2026.3666797","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mm.2026.3666797","pdf_url":null,"source":{"id":"https://openalex.org/S59697426","display_name":"IEEE Micro","issn_l":"0272-1732","issn":["0272-1732","1937-4143"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Micro","raw_type":"journal-article"},"type":"article","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/A5126728071","display_name":"Zhanqiu Hu","orcid":null},"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"]},{"id":"https://openalex.org/I4405261073","display_name":"Cornell Tech","ror":"https://ror.org/04qscbg47","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295","https://openalex.org/I4405261073"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhanqiu Hu","raw_affiliation_strings":["Cornell Tech, New York, NY, USA"],"raw_orcid":"https://orcid.org/0009-0005-4343-8277","affiliations":[{"raw_affiliation_string":"Cornell Tech, New York, NY, USA","institution_ids":["https://openalex.org/I205783295","https://openalex.org/I4405261073"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126691613","display_name":"Mark Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Zhao","raw_affiliation_strings":["University of Colorado Boulder, Boulder, CO, USA"],"raw_orcid":"https://orcid.org/0000-0002-0706-5208","affiliations":[{"raw_affiliation_string":"University of Colorado Boulder, Boulder, CO, USA","institution_ids":["https://openalex.org/I188538660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126584068","display_name":"Zhiru Zhang","orcid":null},"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":"Zhiru Zhang","raw_affiliation_strings":["Cornell University, Ithaca, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-0778-0308","affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126690657","display_name":"Udit Gupta","orcid":null},"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"]},{"id":"https://openalex.org/I4405261073","display_name":"Cornell Tech","ror":"https://ror.org/04qscbg47","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295","https://openalex.org/I4405261073"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Udit Gupta","raw_affiliation_strings":["Cornell Tech, New York, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-9118-0961","affiliations":[{"raw_affiliation_string":"Cornell Tech, New York, NY, USA","institution_ids":["https://openalex.org/I205783295","https://openalex.org/I4405261073"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14843444,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"46","issue":"3","first_page":"24","last_page":"32"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.5821999907493591,"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":0.5821999907493591,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.08649999648332596,"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/T12384","display_name":"Customer churn and segmentation","score":0.025800000876188278,"subfield":{"id":"https://openalex.org/subfields/1406","display_name":"Marketing"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.616100013256073},{"id":"https://openalex.org/keywords/movielens","display_name":"MovieLens","score":0.6155999898910522},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6021999716758728},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5828999876976013},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.49140000343322754},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45809999108314514},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.4514999985694885},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.4372999966144562},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41670000553131104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.891700029373169},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.616100013256073},{"id":"https://openalex.org/C2776156558","wikidata":"https://www.wikidata.org/wiki/Q4353746","display_name":"MovieLens","level":4,"score":0.6155999898910522},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6021999716758728},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5828999876976013},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.49239999055862427},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.49140000343322754},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4803999960422516},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45809999108314514},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.4514999985694885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44209998846054077},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.4372999966144562},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41670000553131104},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.385699987411499},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.36079999804496765},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3343000113964081},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.3334999978542328},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.31850001215934753},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.30709999799728394},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C46743427","wikidata":"https://www.wikidata.org/wiki/Q1341685","display_name":"Inference engine","level":3,"score":0.3003999888896942},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2840000092983246},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2648000121116638},{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C21569690","wikidata":"https://www.wikidata.org/wiki/Q94702","display_name":"Collaborative filtering","level":3,"score":0.259799987077713}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mm.2026.3666797","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mm.2026.3666797","pdf_url":null,"source":{"id":"https://openalex.org/S59697426","display_name":"IEEE Micro","issn_l":"0272-1732","issn":["0272-1732","1937-4143"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Micro","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Modern":[0],"recommendation":[1,70,135],"engines":[2],"power":[3],"most":[4],"online":[5],"interactions":[6],"through":[7],"multi-stage":[8],"pipelines":[9,14],"at":[10],"massive":[11],"scale.":[12],"These":[13],"combine":[15],"user":[16],"and":[17,26,45,64,75,80,92],"item":[18],"feature":[19,78],"processing,":[20],"approximate":[21],"nearest":[22],"neighbor":[23],"(ANN)":[24],"retrieval,":[25,77],"deep":[27],"neural":[28],"network":[29],"(DNN)":[30],"ranking.":[31],"However,":[32],"optimizing":[33],"only":[34],"the":[35,61],"DNN":[36],"ranking":[37,81],"stage":[38],"leaves":[39],"substantial":[40],"bottlenecks":[41],"in":[42],"data":[43],"movement":[44],"non-DNN":[46,88],"stages,":[47],"leading":[48],"to":[49,132],"suboptimal":[50],"performance.":[51],"This":[52],"work":[53],"introduces":[54],"ReCoOpt,":[55],"a":[56,109],"modular":[57],"framework":[58],"for":[59],"exploring":[60],"joint":[62],"hardware":[63],"software":[65],"design":[66],"space":[67],"of":[68],"end-to-end":[69],"inference":[71],"pipelines.":[72],"By":[73],"profiling":[74],"tuning":[76],"fetching,":[79],"across":[82],"heterogeneous":[83],"hardware,":[84],"we":[85],"show":[86],"that":[87,102,123],"stages":[89],"dominate":[90],"latency":[91,111,117],"require":[93],"co-design.":[94],"Using":[95],"public":[96],"MovieLens":[97],"datasets,":[98],"ReCoOpt":[99],"identifies":[100],"configurations":[101],"improve":[103],"hit":[104],"rate":[105],"by":[106,118],"0.05":[107],"under":[108],"fixed":[110],"budget,":[112],"double":[113],"throughput,":[114],"or":[115],"reduce":[116],"40%.":[119],"Our":[120],"findings":[121],"highlight":[122],"balanced":[124],"co-design":[125],"rather":[126],"than":[127],"accelerator-only":[128],"optimization":[129],"is":[130],"key":[131],"future":[133],"scalable":[134],"systems.":[136]},"counts_by_year":[],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2026-02-25T00:00:00"}