{"id":"https://openalex.org/W7148412367","doi":"https://doi.org/10.1109/hipcw66559.2025.00105","title":"Performance Analysis of Memory-Bound Deep Learning Recommendation Models","display_name":"Performance Analysis of Memory-Bound Deep Learning Recommendation Models","publication_year":2025,"publication_date":"2025-12-17","ids":{"openalex":"https://openalex.org/W7148412367","doi":"https://doi.org/10.1109/hipcw66559.2025.00105"},"language":"en","primary_location":{"id":"doi:10.1109/hipcw66559.2025.00105","doi":"https://doi.org/10.1109/hipcw66559.2025.00105","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipcw66559.2025.00105","pdf_url":null,"source":{"id":"https://openalex.org/S7407086554","display_name":"IEEE International Conference on High Performance Computing, Data and Analytics Workshop (HiPCW)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 32nd International Conference on High Performance Computing, Data and Analytics Workshop (HiPCW)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5015310794","display_name":"Sakshi Srivastava","orcid":"https://orcid.org/0000-0002-0405-6218","observed_orcids":["https://orcid.org/0000-0002-0405-6218"]},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sakshi Srivastava","raw_affiliation_strings":["IIT Hyderabad,Dept. of CSE,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT Hyderabad,Dept. of CSE,India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119515928","display_name":"Abed Mohammad Kamaluddin","orcid":"https://orcid.org/0009-0009-0889-6618","observed_orcids":["https://orcid.org/0009-0009-0889-6618"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abed Mohammad Kamaluddin","raw_affiliation_strings":["Marvell Technology,Hyderabad,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Marvell Technology,Hyderabad,India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052098266","display_name":"Praveen Tammana","orcid":"https://orcid.org/0000-0002-8057-7699","observed_orcids":["https://orcid.org/0000-0002-8057-7699"]},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Praveen Tammana","raw_affiliation_strings":["IIT Hyderabad,Dept. of CSE,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT Hyderabad,Dept. of CSE,India","institution_ids":["https://openalex.org/I65181880"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"301","last_page":"302"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9394999742507935,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9394999742507935,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10203","display_name":"Recommender Systems and Techniques","score":0.04309999942779541,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0031999999191612005,"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/deep-learning-recommendation-models","display_name":"deep learning recommendation models","score":0.9860000014305115},{"id":"https://openalex.org/keywords/memory-bound-performance","display_name":"memory-bound performance","score":0.9079999923706055},{"id":"https://openalex.org/keywords/embedding-tables","display_name":"embedding tables","score":0.8339999914169312},{"id":"https://openalex.org/keywords/memory-latency","display_name":"memory latency","score":0.6370000243186951},{"id":"https://openalex.org/keywords/high-bandwidth-memory","display_name":"high-bandwidth memory","score":0.7379999756813049},{"id":"https://openalex.org/keywords/dram","display_name":"DRAM","score":0.7400000095367432},{"id":"https://openalex.org/keywords/cache-locality","display_name":"cache locality","score":0.7049999833106995},{"id":"https://openalex.org/keywords/personalized-recommendation","display_name":"personalized recommendation","score":0.6430000066757202}],"concepts":[{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.730400025844574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6489999890327454},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.640999972820282},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3336000144481659},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.24969999492168427}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hipcw66559.2025.00105","doi":"https://doi.org/10.1109/hipcw66559.2025.00105","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipcw66559.2025.00105","pdf_url":null,"source":{"id":"https://openalex.org/S7407086554","display_name":"IEEE International Conference on High Performance Computing, Data and Analytics Workshop (HiPCW)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 32nd International Conference on High Performance Computing, Data and Analytics Workshop (HiPCW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W3197720002","https://openalex.org/W4312996980","https://openalex.org/W4409248575"],"related_works":["https://openalex.org/W3217681641","https://openalex.org/W4399911364","https://openalex.org/W7128391820","https://openalex.org/W4367860663","https://openalex.org/W7115740636","https://openalex.org/W4414199318","https://openalex.org/W4376456262","https://openalex.org/W4288043595","https://openalex.org/W7132345010","https://openalex.org/W4401980011"],"abstract_inverted_index":{"Deep":[0],"Learning":[1],"Recommendation":[2],"Models":[3],"(DLRMs)":[4],"play":[5],"a":[6,69],"crucial":[7],"role":[8],"in":[9],"personalized":[10],"recommendations":[11],"across":[12],"major":[13],"technology":[14],"platforms.":[15],"In":[16],"large-scale":[17],"deployments,":[18],"embedding":[19],"tables":[20],"dominates":[21],"memory":[22,29,63,77,93],"usage,":[23],"often":[24],"requiring":[25],"terabytes":[26],"of":[27,55,61,83],"high-bandwidth":[28],"(HBM/DRAM).":[30],"Memory-bound":[31],"models":[32],"suffer":[33],"from":[34],"high":[35],"access":[36],"latency,":[37],"limited":[38],"bandwidth,":[39],"and":[40],"poor":[41],"cache":[42],"locality,":[43],"which":[44],"limit":[45],"overall":[46],"performance.":[47],"This":[48],"paper":[49],"analyzes":[50],"the":[51,59],"theoretical":[52,89],"upper":[53],"bound":[54],"DLRM":[56,74],"performance":[57],"under":[58,91],"assumption":[60],"zero":[62,92],"latency":[64],"by":[65],"modeling":[66],"execution":[67],"as":[68],"DAG.":[70],"Experiments":[71],"on":[72],"open-source":[73],"show":[75],"that":[76],"operations":[78],"account":[79],"for":[80],"over":[81],"90%":[82],"runtime,":[84],"with":[85],"up":[86],"to":[87],"25\u00d7":[88],"speedup":[90],"latency.":[94]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-04-03T00:00:00"}