{"id":"https://openalex.org/W4407213048","doi":"https://doi.org/10.1109/tpds.2025.3539534","title":"Flips: A Flexible Partitioning Strategy Near Memory Processing Architecture for Recommendation System","display_name":"Flips: A Flexible Partitioning Strategy Near Memory Processing Architecture for Recommendation System","publication_year":2025,"publication_date":"2025-02-06","ids":{"openalex":"https://openalex.org/W4407213048","doi":"https://doi.org/10.1109/tpds.2025.3539534"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2025.3539534","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2025.3539534","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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 Transactions on Parallel and Distributed Systems","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/A5016867130","display_name":"Yudi Qiu","orcid":"https://orcid.org/0000-0001-6770-3681"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yudi Qiu","raw_affiliation_strings":["Alibaba Cloud Computing, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-6770-3681","affiliations":[{"raw_affiliation_string":"Alibaba Cloud Computing, Shanghai, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingfei Lu","raw_affiliation_strings":["State Key Laboratory of Integrated Chips and Systems, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0006-6416-6474","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Integrated Chips and Systems, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyan Yi","raw_affiliation_strings":["State Key Laboratory of Integrated Chips and Systems, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-0744-358X","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Integrated Chips and Systems, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073266325","display_name":"Minge Jing","orcid":"https://orcid.org/0009-0005-0446-5600"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minge Jing","raw_affiliation_strings":["State Key Laboratory of Integrated Chips and Systems, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Integrated Chips and Systems, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100656792","display_name":"Xiaoyang Zeng","orcid":"https://orcid.org/0000-0003-3986-137X"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyang Zeng","raw_affiliation_strings":["State Key Laboratory of Integrated Chips and Systems, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-3986-137X","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Integrated Chips and Systems, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100634448","display_name":"Yang Kong","orcid":"https://orcid.org/0009-0008-7390-8315"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Kong","raw_affiliation_strings":["Alibaba Cloud Computing, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Cloud Computing, Shanghai, China","institution_ids":["https://openalex.org/I45928872"]}]},{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yibo Fan","raw_affiliation_strings":["State Key Laboratory of Integrated Chips and Systems, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-2523-8261","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Integrated Chips and Systems, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.02346936,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"4","first_page":"745","last_page":"758"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.5299999713897705,"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":0.5299999713897705,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8224067687988281},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5818899869918823},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.5382131934165955},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4620285630226135},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.42298710346221924},{"id":"https://openalex.org/keywords/random-access-memory","display_name":"Random access memory","score":0.4118494391441345},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.38988882303237915},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.34001338481903076},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2581202983856201},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.22107070684432983},{"id":"https://openalex.org/keywords/semiconductor-memory","display_name":"Semiconductor memory","score":0.14327886700630188}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8224067687988281},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5818899869918823},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5382131934165955},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4620285630226135},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.42298710346221924},{"id":"https://openalex.org/C2994168587","wikidata":"https://www.wikidata.org/wiki/Q5295","display_name":"Random access memory","level":2,"score":0.4118494391441345},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.38988882303237915},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.34001338481903076},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2581202983856201},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.22107070684432983},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.14327886700630188},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2025.3539534","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2025.3539534","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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 Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2588198209","https://openalex.org/W1909006023","https://openalex.org/W4205824991","https://openalex.org/W3200723557","https://openalex.org/W4312713546","https://openalex.org/W2362195430","https://openalex.org/W2347494122","https://openalex.org/W2567983276","https://openalex.org/W2802298219","https://openalex.org/W2038503502"],"abstract_inverted_index":{"Personalized":[0],"recommendation":[1,15],"systems":[2,16],"are":[3,17,102],"massively":[4],"deployed":[5],"in":[6,67,129],"production":[7],"data":[8,68],"centers.":[9],"The":[10],"memory-intensive":[11],"embedding":[12,43,83,121],"layers":[13],"of":[14],"the":[18,105,115,124,137],"crucial":[19],"performance":[20],"bottleneck,":[21],"with":[22],"operations":[23,44],"manifesting":[24],"as":[25],"sparse":[26],"memory":[27,49],"lookups":[28],"and":[29,72,98,107,140,145,159,166],"simple":[30],"reduction":[31],"computations.":[32],"Recent":[33],"studies":[34],"propose":[35,76],"near-memory":[36],"processing":[37],"(NMP)":[38],"architectures":[39,97],"to":[40,63,65,113,126,163],"speed":[41],"up":[42,162],"by":[45,161],"utilizing":[46],"high":[47],"internal":[48],"bandwidth.":[50],"However,":[51],"these":[52],"solutions":[53],"typically":[54],"employ":[55],"a":[56],"fixed":[57],"vector":[58],"partitioning":[59,90,117],"strategy":[60,118],"that":[61,81],"fail":[62],"adapt":[64],"changes":[66,128],"center":[69],"deployment":[70,130],"scenarios":[71],"lack":[73],"practicality.":[74],"We":[75,109],"Flips,":[77],"aflexiblepartitioningstrategy":[78],"NMP":[79,138,150,155],"architecture":[80,125],"accelerates":[82],"layers.":[84],"Flips":[85,133,152],"supports":[86],"more":[87],"than":[88],"ten":[89],"strategies":[91],"through":[92],"hardware-software":[93],"co-design.":[94],"Novel":[95],"hardware":[96],"address":[99],"mapping":[100],"schemes":[101],"designed":[103],"for":[104,119],"memory-side":[106],"host-side.":[108],"provide":[110],"two":[111],"approaches":[112],"determine":[114],"optimal":[116],"each":[120],"table,":[122],"enabling":[123],"accommodate":[127],"scenarios.":[131],"Importantly,":[132],"is":[134],"decoupled":[135],"from":[136],"level":[139],"can":[141],"utilize":[142],"rank-level,":[143],"bank-group-level":[144],"bank-level":[146],"parallelism.":[147],"In":[148],"peer-level":[149],"evaluations,":[151],"outperforms":[153],"state-of-the-art":[154],"solutions,":[156],"RecNMP,":[157],"TRiM,":[158],"ReCross":[160],"4.0\u00d7,":[164],"4.1\u00d7,":[165],"3.5\u00d7,":[167],"respectively.":[168]},"counts_by_year":[],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}