{"id":"https://openalex.org/W4385885086","doi":"https://doi.org/10.1109/lca.2023.3305668","title":"A Flexible Embedding-Aware Near Memory Processing Architecture for Recommendation System","display_name":"A Flexible Embedding-Aware Near Memory Processing Architecture for Recommendation System","publication_year":2023,"publication_date":"2023-07-01","ids":{"openalex":"https://openalex.org/W4385885086","doi":"https://doi.org/10.1109/lca.2023.3305668"},"language":"en","primary_location":{"id":"doi:10.1109/lca.2023.3305668","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lca.2023.3305668","pdf_url":null,"source":{"id":"https://openalex.org/S17643076","display_name":"IEEE Computer Architecture Letters","issn_l":"1556-6056","issn":["1556-6056","1556-6064","2473-2575"],"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 Computer Architecture Letters","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/A5054730030","display_name":"Lingfei Lu","orcid":"https://orcid.org/0009-0006-6416-6474"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4210132426","display_name":"Shanghai Fudan Microelectronics (China)","ror":"https://ror.org/02vfj3j86","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210132426"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingfei Lu","raw_affiliation_strings":["School of Microelectronics, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0006-6416-6474","affiliations":[{"raw_affiliation_string":"School of Microelectronics, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067","https://openalex.org/I4210132426"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016867130","display_name":"Yudi Qiu","orcid":"https://orcid.org/0000-0001-6770-3681"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4210132426","display_name":"Shanghai Fudan Microelectronics (China)","ror":"https://ror.org/02vfj3j86","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210132426"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yudi Qiu","raw_affiliation_strings":["School of Microelectronics, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-6770-3681","affiliations":[{"raw_affiliation_string":"School of Microelectronics, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067","https://openalex.org/I4210132426"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020055336","display_name":"Shiyan Yi","orcid":"https://orcid.org/0000-0002-0744-358X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4210132426","display_name":"Shanghai Fudan Microelectronics (China)","ror":"https://ror.org/02vfj3j86","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210132426"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyan Yi","raw_affiliation_strings":["School of Microelectronics, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-0744-358X","affiliations":[{"raw_affiliation_string":"School of Microelectronics, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067","https://openalex.org/I4210132426"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085004179","display_name":"Yibo Fan","orcid":"https://orcid.org/0000-0003-2523-8261"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4210132426","display_name":"Shanghai Fudan Microelectronics (China)","ror":"https://ror.org/02vfj3j86","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210132426"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yibo Fan","raw_affiliation_strings":["School of Microelectronics, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-2523-8261","affiliations":[{"raw_affiliation_string":"School of Microelectronics, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067","https://openalex.org/I4210132426"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6631,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.68884346,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":"22","issue":"2","first_page":"165","last_page":"168"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9997000098228455,"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"}},{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9979000091552734,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.996399998664856,"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/embedding","display_name":"Embedding","score":0.8587381839752197},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6949259042739868},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6165255308151245},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5354213118553162},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.49659115076065063},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.42960768938064575},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.362970769405365},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35942453145980835},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.34040915966033936},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33799752593040466},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1582619547843933}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.8587381839752197},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6949259042739868},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6165255308151245},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5354213118553162},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.49659115076065063},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.42960768938064575},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.362970769405365},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35942453145980835},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.34040915966033936},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33799752593040466},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1582619547843933},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lca.2023.3305668","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lca.2023.3305668","pdf_url":null,"source":{"id":"https://openalex.org/S17643076","display_name":"IEEE Computer Architecture Letters","issn_l":"1556-6056","issn":["1556-6056","1556-6064","2473-2575"],"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 Computer Architecture Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5}],"awards":[{"id":"https://openalex.org/G6391884445","display_name":null,"funder_award_id":"62031009","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2095076490","https://openalex.org/W2464177207","https://openalex.org/W2979719709","https://openalex.org/W3006586535","https://openalex.org/W3016842236","https://openalex.org/W3043023836","https://openalex.org/W3157531038","https://openalex.org/W3197870239","https://openalex.org/W3207399097","https://openalex.org/W4226150639","https://openalex.org/W4285113882","https://openalex.org/W4318328413","https://openalex.org/W6719768283"],"related_works":["https://openalex.org/W2317245370","https://openalex.org/W4249323025","https://openalex.org/W2097707447","https://openalex.org/W198851386","https://openalex.org/W2030310580","https://openalex.org/W947442053","https://openalex.org/W1980160788","https://openalex.org/W2148915962","https://openalex.org/W2283866686","https://openalex.org/W4287182096"],"abstract_inverted_index":{"Personalized":[0],"recommendation":[1],"system":[2],"(RS)":[3],"is":[4,24,35,73],"widely":[5],"used":[6],"in":[7,15,105],"the":[8,25,66,95,129],"industrial":[9],"community":[10],"and":[11,34,107,121],"occupies":[12],"much":[13],"time":[14],"AI":[16],"computing":[17],"centers.":[18],"A":[19],"critical":[20],"component":[21],"of":[22,30,68,98],"RS":[23],"embedding":[26,32,53,59,82,119,143],"layer,":[27],"which":[28],"consists":[29],"sparse":[31],"lookups":[33],"memory-bounded.":[36],"Recent":[37],"works":[38,57],"have":[39],"proposed":[40],"near-memory":[41],"processing":[42],"(NMP)":[43],"architectures":[44],"to":[45,50,75,112,128,139],"utilize":[46],"high":[47],"inner-memory":[48],"bandwidth":[49],"speed":[51],"up":[52,138],"lookups.":[54],"These":[55],"NMP":[56,132],"divide":[58],"vectors":[60],"either":[61],"horizontally":[62],"or":[63,70,81],"vertically.":[64],"However,":[65],"effectiveness":[67],"horizontal":[69],"vertical":[71],"partitioning":[72,103],"hard":[74],"guarantee":[76],"under":[77,145],"different":[78,102,118],"memory":[79],"configurations":[80],"vector":[83],"sizes.":[84],"To":[85],"improve":[86],"this":[87],"issue,":[88],"we":[89],"propose":[90],"FeaNMP,":[91],"aflexibleembedding-awareNMParchitecture":[92],"that":[93],"accelerates":[94],"inference":[96],"phase":[97],"RS.":[99],"We":[100],"explore":[101],"strategies":[104],"detail":[106],"design":[108],"a":[109,125],"flexible":[110],"way":[111],"select":[113],"optimal":[114],"ones":[115],"depending":[116],"on":[117],"dimensions":[120],"DDR":[122],"configurations.":[123],"As":[124],"result,":[126],"compared":[127],"state-of-the-art":[130],"rank-level":[131],"work":[133,136],"RecNMP,":[134],"our":[135],"achieves":[137],"11.1\u00d7":[140],"speedup":[141],"for":[142],"layers":[144],"mix-dimensioned":[146],"workloads.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}
