{"id":"https://openalex.org/W4380881110","doi":"https://doi.org/10.1145/3579371.3589112","title":"Optimizing CPU Performance for Recommendation Systems At-Scale","display_name":"Optimizing CPU Performance for Recommendation Systems At-Scale","publication_year":2023,"publication_date":"2023-06-16","ids":{"openalex":"https://openalex.org/W4380881110","doi":"https://doi.org/10.1145/3579371.3589112"},"language":"en","primary_location":{"id":"doi:10.1145/3579371.3589112","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3579371.3589112","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 50th Annual International Symposium on Computer Architecture","raw_type":"proceedings-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/A5101807692","display_name":"Rishabh Jain","orcid":"https://orcid.org/0009-0003-4017-2093"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rishabh Jain","raw_affiliation_strings":["Pennsylvania State University, University Park, PA, USA"],"raw_orcid":"https://orcid.org/0009-0003-4017-2093","affiliations":[{"raw_affiliation_string":"Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035702201","display_name":"S. H. Cheng","orcid":"https://orcid.org/0000-0001-9954-7986"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott Cheng","raw_affiliation_strings":["Pennsylvania State University, University Park, PA, USA"],"raw_orcid":"https://orcid.org/0000-0001-9954-7986","affiliations":[{"raw_affiliation_string":"Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092183281","display_name":"Vishwas Kalagi","orcid":"https://orcid.org/0009-0001-3757-9904"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vishwas Kalagi","raw_affiliation_strings":["Pennsylvania State University, University Park, PA, USA"],"raw_orcid":"https://orcid.org/0009-0001-3757-9904","affiliations":[{"raw_affiliation_string":"Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006946407","display_name":"Vrushabh Sanghavi","orcid":"https://orcid.org/0000-0001-9886-7419"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vrushabh Sanghavi","raw_affiliation_strings":["Intel, Portland, USA"],"raw_orcid":"https://orcid.org/0000-0001-9886-7419","affiliations":[{"raw_affiliation_string":"Intel, Portland, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011449671","display_name":"Samvit Kaul","orcid":"https://orcid.org/0009-0003-1932-8997"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samvit Kaul","raw_affiliation_strings":["Intel, Folsom, USA"],"raw_orcid":"https://orcid.org/0009-0003-1932-8997","affiliations":[{"raw_affiliation_string":"Intel, Folsom, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017509912","display_name":"Meena Arunachalam","orcid":"https://orcid.org/0000-0002-3155-6269"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Meena Arunachalam","raw_affiliation_strings":["Intel, Portland, USA"],"raw_orcid":"https://orcid.org/0000-0002-3155-6269","affiliations":[{"raw_affiliation_string":"Intel, Portland, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035750684","display_name":"Kiwan Maeng","orcid":"https://orcid.org/0000-0002-0321-8406"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kiwan Maeng","raw_affiliation_strings":["Pennsylvania State University, University Park, PA, USA"],"raw_orcid":"https://orcid.org/0000-0002-0321-8406","affiliations":[{"raw_affiliation_string":"Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050350124","display_name":"Adwait Jog","orcid":"https://orcid.org/0000-0002-5525-7204"},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]},{"id":"https://openalex.org/I267592682","display_name":"Williams (United States)","ror":"https://ror.org/007zhvp17","country_code":"US","type":"company","lineage":["https://openalex.org/I267592682"]},{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adwait Jog","raw_affiliation_strings":["University of Virginia, Charlottesville, VA, USA","William & Mary, Williamsburg, VA, USA","William & Mary, Williamsburg, VA, USA University of Virginia, Charlottesville, VA, USA"],"raw_orcid":"https://orcid.org/0000-0002-5525-7204","affiliations":[{"raw_affiliation_string":"University of Virginia, Charlottesville, VA, USA","institution_ids":["https://openalex.org/I51556381"]},{"raw_affiliation_string":"William & Mary, Williamsburg, VA, USA","institution_ids":["https://openalex.org/I16285277","https://openalex.org/I267592682"]},{"raw_affiliation_string":"William & Mary, Williamsburg, VA, USA University of Virginia, Charlottesville, VA, USA","institution_ids":["https://openalex.org/I16285277","https://openalex.org/I51556381","https://openalex.org/I267592682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033253809","display_name":"Anand Sivasubramaniam","orcid":"https://orcid.org/0000-0001-6173-687X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anand Sivasubramaniam","raw_affiliation_strings":["Pennsylvania State University, University Park, PA, USA"],"raw_orcid":"https://orcid.org/0000-0001-6173-687X","affiliations":[{"raw_affiliation_string":"Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007116603","display_name":"Mahmut Kandemir","orcid":"https://orcid.org/0000-0002-9940-9951"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mahmut Taylan Kandemir","raw_affiliation_strings":["Pennsylvania State University, University Park, PA, USA"],"raw_orcid":"https://orcid.org/0000-0002-9940-9951","affiliations":[{"raw_affiliation_string":"Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054027488","display_name":"Chita R. Das","orcid":"https://orcid.org/0000-0002-4746-7578"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chita R. Das","raw_affiliation_strings":["Pennsylvania State University, University Park, PA, USA"],"raw_orcid":"https://orcid.org/0000-0002-4746-7578","affiliations":[{"raw_affiliation_string":"Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5101807692"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":10.7621,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.98288398,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9980999827384949,"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":0.9980000257492065,"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":0.8795820474624634},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6494718194007874},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5919976234436035},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5455079674720764},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5312466621398926},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.48581695556640625},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.4789067506790161},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.46407321095466614},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4485791325569153},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.43149834871292114},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.35427945852279663},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2836153209209442},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11458271741867065}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8795820474624634},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6494718194007874},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5919976234436035},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5455079674720764},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5312466621398926},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.48581695556640625},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.4789067506790161},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.46407321095466614},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4485791325569153},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.43149834871292114},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.35427945852279663},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2836153209209442},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11458271741867065},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"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/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3579371.3589112","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3579371.3589112","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 50th Annual International Symposium on Computer Architecture","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2571087023","display_name":null,"funder_award_id":"#1912495","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2645164485","display_name":null,"funder_award_id":"#2028929","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2847520476","display_name":null,"funder_award_id":"#1714389","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3332571016","display_name":null,"funder_award_id":"#1909004","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3343325422","display_name":null,"funder_award_id":"#2116962","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G480602589","display_name":null,"funder_award_id":"#2211018","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5174757511","display_name":null,"funder_award_id":"#1931531","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W117083835","https://openalex.org/W1982063824","https://openalex.org/W2036162037","https://openalex.org/W2062840343","https://openalex.org/W2120230074","https://openalex.org/W2123608497","https://openalex.org/W2210543184","https://openalex.org/W2249344705","https://openalex.org/W2475334473","https://openalex.org/W2512971201","https://openalex.org/W2723293840","https://openalex.org/W2734941459","https://openalex.org/W2794670651","https://openalex.org/W2900810680","https://openalex.org/W2928897890","https://openalex.org/W2929131209","https://openalex.org/W2931743911","https://openalex.org/W2962745591","https://openalex.org/W2964182926","https://openalex.org/W2973172293","https://openalex.org/W2979719709","https://openalex.org/W2983581636","https://openalex.org/W2984020950","https://openalex.org/W3016842236","https://openalex.org/W3027097765","https://openalex.org/W3042495273","https://openalex.org/W3043023836","https://openalex.org/W3043433718","https://openalex.org/W3093945404","https://openalex.org/W3102840236","https://openalex.org/W3109610142","https://openalex.org/W3138433673","https://openalex.org/W3138811091","https://openalex.org/W3152508978","https://openalex.org/W3153687269","https://openalex.org/W3153887672","https://openalex.org/W3155243801","https://openalex.org/W3158783012","https://openalex.org/W3187188899","https://openalex.org/W3197720002","https://openalex.org/W3206393216","https://openalex.org/W3209259988","https://openalex.org/W3209593805","https://openalex.org/W4221079727","https://openalex.org/W4239554475","https://openalex.org/W4240390622","https://openalex.org/W4281787632","https://openalex.org/W4285361428","https://openalex.org/W4290877962","https://openalex.org/W4308426104"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2037549926","https://openalex.org/W2345479200","https://openalex.org/W2183306018","https://openalex.org/W2031026393","https://openalex.org/W2473478803","https://openalex.org/W2063611263","https://openalex.org/W2729363167","https://openalex.org/W2060611139","https://openalex.org/W2115229350"],"abstract_inverted_index":{"Deep":[0],"Learning":[1],"Recommendation":[2],"Models":[3],"(DLRMs)":[4],"are":[5,13,44],"very":[6],"popular":[7],"in":[8,37,60,71],"personalized":[9],"recommendation":[10,85,187],"systems":[11],"and":[12,27,42,78,117,122,155,159,181,189,205],"a":[14,179],"major":[15],"contributor":[16,131],"to":[17,23,68,132,144,162,168,203],"the":[18,24,34,55,61,72,76,87,91,100,112,129,146,152,170,185,199],"data-center":[19],"AI":[20],"cycles.":[21],"Due":[22],"high":[25,133],"computational":[26,88],"memory":[28,58,126,147,160],"bandwidth":[29],"needs":[30],"of":[31,54,64,90,102,114],"DLRMs,":[32],"specifically":[33],"embedding":[35,62,92],"stage":[36,63,93],"DLRM":[38],"inferences,":[39],"both":[40],"CPUs":[41,103],"GPUs":[43],"used":[45],"for":[46,104],"hosting":[47],"such":[48],"workloads.":[49],"This":[50],"is":[51,128],"primarily":[52],"because":[53],"heavy":[56],"irregular":[57,115],"accesses":[59,116],"computation":[65,158],"that":[66,124],"leads":[67],"significant":[69],"stalls":[70,165],"CPU":[73,164],"pipeline.":[74],"As":[75],"model":[77],"parameter":[79],"sizes":[80],"keep":[81],"increasing":[82],"with":[83,184],"newer":[84],"models,":[86],"dominance":[89],"also":[94],"grows,":[95],"thereby,":[96],"bringing":[97],"into":[98],"question":[99],"suitability":[101],"inference.":[105],"In":[106],"this":[107],"paper,":[108],"we":[109,136],"first":[110],"quantify":[111],"cause":[113],"their":[118],"impact":[119],"on":[120,178,206],"caches":[121],"observe":[123],"off-chip":[125],"access":[127,148],"main":[130],"latency.":[134],"Therefore,":[135],"exploit":[137],"two":[138],"well-known":[139],"techniques:":[140],"(1)":[141],"Software":[142],"prefetching,":[143],"hide":[145],"latency":[149],"suffered":[150],"by":[151,201,208],"demand":[153],"loads":[154],"(2)":[156],"Overlapping":[157],"accesses,":[161],"reduce":[163],"via":[166],"hyperthreading":[167],"minimize":[169],"overall":[171],"execution":[172],"time.":[173],"We":[174],"evaluate":[175],"our":[176],"work":[177],"single-core":[180],"24-core":[182],"configuration":[183],"latest":[186],"models":[188],"recently":[190],"released":[191],"production":[192],"traces.":[193],"Our":[194],"integrated":[195],"techniques":[196],"speed":[197],"up":[198,202],"inference":[200],"1.59x,":[204],"average":[207],"1.4x.":[209]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}