{"id":"https://openalex.org/W4411486328","doi":"https://doi.org/10.1145/3695053.3731026","title":"Dynamic Load Balancer in Intel Xeon Scalable Processor: Performance Analyses, Enhancements, and Guidelines","display_name":"Dynamic Load Balancer in Intel Xeon Scalable Processor: Performance Analyses, Enhancements, and Guidelines","publication_year":2025,"publication_date":"2025-06-20","ids":{"openalex":"https://openalex.org/W4411486328","doi":"https://doi.org/10.1145/3695053.3731026"},"language":"en","primary_location":{"id":"doi:10.1145/3695053.3731026","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3695053.3731026","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3695053.3731026","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd Annual International Symposium on Computer Architecture","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3695053.3731026","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jiaqi Lou","orcid":"https://orcid.org/0009-0000-0619-8634"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiaqi Lou","raw_affiliation_strings":["University of Illinois Urbana-Champaign, Urbana, IL, USA"],"raw_orcid":"https://orcid.org/0009-0000-0619-8634","affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000862490","display_name":"Srikar Vanavasam","orcid":"https://orcid.org/0000-0002-4224-2812"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Srikar Vanavasam","raw_affiliation_strings":["University of Illinois Urbana-Champaign, Urbana, IL, USA"],"raw_orcid":"https://orcid.org/0000-0002-4224-2812","affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033930997","display_name":"Yifan Yuan","orcid":"https://orcid.org/0000-0002-8389-2133"},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Yuan","raw_affiliation_strings":["Meta, Menlo Park, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-8389-2133","affiliations":[{"raw_affiliation_string":"Meta, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088502854","display_name":"Ren Wang","orcid":"https://orcid.org/0009-0005-2937-5804"},"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":"Ren Wang","raw_affiliation_strings":["Intel Labs, Portland, OR, USA"],"raw_orcid":"https://orcid.org/0009-0005-2937-5804","affiliations":[{"raw_affiliation_string":"Intel Labs, Portland, OR, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037648751","display_name":"Nam Sung Kim","orcid":"https://orcid.org/0000-0002-0442-5634"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nam Sung Kim","raw_affiliation_strings":["University of Illinois Urbana-Champaign, Urbana, IL, USA"],"raw_orcid":"https://orcid.org/0000-0002-0442-5634","affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"664","last_page":"678"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9987000226974487,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9973999857902527,"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/xeon-phi","display_name":"Xeon Phi","score":0.8901715278625488},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8035251498222351},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6950057744979858},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.6320000886917114},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6176348924636841},{"id":"https://openalex.org/keywords/x86","display_name":"x86","score":0.4518083333969116},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4408811032772064},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.43447232246398926},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.37360239028930664},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.14145725965499878}],"concepts":[{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.8901715278625488},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8035251498222351},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6950057744979858},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.6320000886917114},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6176348924636841},{"id":"https://openalex.org/C170723468","wikidata":"https://www.wikidata.org/wiki/Q182933","display_name":"x86","level":3,"score":0.4518083333969116},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4408811032772064},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.43447232246398926},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.37360239028930664},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.14145725965499878}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3695053.3731026","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3695053.3731026","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3695053.3731026","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd Annual International Symposium on Computer Architecture","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3695053.3731026","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3695053.3731026","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3695053.3731026","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd Annual International Symposium on Computer Architecture","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6499999761581421,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G3436121829","display_name":null,"funder_award_id":"RS-2024-00405857","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G7298062262","display_name":null,"funder_award_id":"RS-2024-00456287","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411486328.pdf","grobid_xml":"https://content.openalex.org/works/W4411486328.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W2036895660","https://openalex.org/W2061201147","https://openalex.org/W2164846625","https://openalex.org/W2165663045","https://openalex.org/W2516627871","https://openalex.org/W2593720592","https://openalex.org/W2613694343","https://openalex.org/W2734941459","https://openalex.org/W2736285633","https://openalex.org/W2900470020","https://openalex.org/W3012088208","https://openalex.org/W3012143782","https://openalex.org/W4214603110","https://openalex.org/W4245772811","https://openalex.org/W4360831805","https://openalex.org/W4360831852","https://openalex.org/W4361194512","https://openalex.org/W4380875476","https://openalex.org/W4381612123","https://openalex.org/W4387951121","https://openalex.org/W4401211635","https://openalex.org/W4404954500"],"related_works":["https://openalex.org/W2753965283","https://openalex.org/W2740999212","https://openalex.org/W2188971969","https://openalex.org/W1994052277","https://openalex.org/W2024554511","https://openalex.org/W2588843388","https://openalex.org/W3042238487","https://openalex.org/W2885985254","https://openalex.org/W2599563411","https://openalex.org/W1964236241"],"abstract_inverted_index":{"The":[0],"rapid":[1],"increase":[2],"in":[3,126],"inter-host":[4],"networking":[5],"speed":[6],"has":[7,43],"challenged":[8],"host":[9,20,71,106,123,185],"processing":[10],"capabilities,":[11],"as":[12,175],"bursty":[13],"traffic":[14],"and":[15,29,58,111,155,231],"uneven":[16],"load":[17,87,127,196],"distribution":[18],"among":[19],"CPU":[21,72,107,124,186],"cores":[22],"give":[23],"rise":[24],"to":[25,65,109,118,147,189,216],"excessive":[26],"queuing":[27],"delays":[28],"service":[30],"latency":[31],"variances.To":[32],"cost-efficiently":[33],"tackle":[34],"this":[35,75],"challenge,":[36],"the":[37,80,120,139,162,172,180,190,218],"latest":[38],"Intel":[39],"Xeon":[40],"Scalable":[41],"Processor":[42],"integrated":[44],"an":[45,199],"on-chip":[46],"accelerator,":[47],"named":[48],"Dynamic":[49],"Load":[50],"Balancer":[51],"(DLB).It":[52],"consists":[53],"of":[54,61,82,105,122,144,184,192,203,221],"hardware":[55],"queues,":[56],"arbiters,":[57],"priority-based":[59],"Quality":[60],"Service":[62],"(QoS)":[63],"features":[64],"maximize":[66],"load-balancing":[67],"performance":[68,81,174],"while":[69,178],"minimizing":[70],"cycle":[73],"consumption.In":[74],"work,":[76],"we":[77,129,213],"first":[78],"compare":[79],"DLB":[83,95,99,154,169,177,205],"against":[84],"popular":[85],"softwarebased":[86],"balancers":[88],"with":[89,209,226],"a":[90,102,131,149,193,227,236],"microbenchmark":[91],"suite,":[92],"demonstrating":[93],"that":[94,167,202],"significantly":[96],"outperforms":[97],"them.Yet,":[98],"still":[100],"consumes":[101],"significant":[103],"number":[104],"cycles":[108,125],"prepare":[110],"enqueue":[112],"work":[113,163],"descriptors":[114],"for":[115,198],"received":[116],"packets.Second,":[117],"eliminate":[119],"consumption":[121,183],"balancing,":[128],"propose":[130],"system":[132],"architecture/software":[133],"co-design":[134],"solution,":[135],"AccDirect.Specifically,":[136],"AccDirect":[137],"leverages":[138],"Peer-to-Peer":[140],"(P2P)":[141],"communication":[142,151],"capability":[143],"PCIe":[145],"devices":[146],"enable":[148],"direct":[150],"path":[152],"between":[153],"NIC,":[156],"through":[157],"which":[158,223],"NIC":[159],"directly":[160],"enqueues":[161],"descriptors.Our":[164],"evaluation":[165],"shows":[166],"AccDirect-based":[168,204],"offers":[170],"practically":[171],"same":[173],"conventional":[176],"reducing":[179],"system-wide":[181],"power":[182],"by":[187],"10%.Compared":[188],"throughput":[191],"commodity":[194],"hardware-based":[195],"balancer":[197],"end-to-end":[200],"application,":[201],"is":[206,224],"14-50%":[207],"higher":[208],"comparable":[210],"p99":[211],"latency.Lastly,":[212],"provide":[214],"guidelines":[215],"make":[217],"best":[219],"use":[220],"DLB,":[222],"riddled":[225],"vast":[228],"configuration":[229],"space":[230],"advanced":[232],"features,":[233],"after":[234],"conducting":[235],"comprehensive":[237],"evaluation.":[238]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
