{"id":"https://openalex.org/W4412610555","doi":"https://doi.org/10.1109/hpcc64274.2024.00046","title":"Optimizing the DFCPP Dataflow Runtime Library for Resource Utilization in NUMA Systems","display_name":"Optimizing the DFCPP Dataflow Runtime Library for Resource Utilization in NUMA Systems","publication_year":2024,"publication_date":"2024-12-13","ids":{"openalex":"https://openalex.org/W4412610555","doi":"https://doi.org/10.1109/hpcc64274.2024.00046"},"language":"en","primary_location":{"id":"doi:10.1109/hpcc64274.2024.00046","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcc64274.2024.00046","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on High Performance Computing and Communications (HPCC)","raw_type":"proceedings-article"},"type":"conference-paper","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":null,"display_name":"Qiuming Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiuming Luo","raw_affiliation_strings":["Shenzhen University,College of Computer Science and Software Engineering,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen University,College of Computer Science and Software Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":null,"display_name":"LiXin Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"LiXin Tang","raw_affiliation_strings":["Shenzhen University,College of Computer Science and Software Engineering,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen University,College of Computer Science and Software Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100511630","display_name":"Du Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Du","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]}],"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":0.37783434,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"276","last_page":"283"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.6521000266075134,"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":0.6521000266075134,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.914192795753479},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8140299916267395},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5381044149398804},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.40624141693115234},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.399743914604187},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3918801546096802},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3771064281463623},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1129004955291748}],"concepts":[{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.914192795753479},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8140299916267395},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5381044149398804},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.40624141693115234},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.399743914604187},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3918801546096802},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3771064281463623},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1129004955291748}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpcc64274.2024.00046","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcc64274.2024.00046","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on High Performance Computing and Communications (HPCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1988888548","https://openalex.org/W1990092986","https://openalex.org/W2009614111","https://openalex.org/W2045299099","https://openalex.org/W2108801243","https://openalex.org/W2160559747","https://openalex.org/W2775620913","https://openalex.org/W2949888609","https://openalex.org/W3040269689","https://openalex.org/W3122131028","https://openalex.org/W3188917597","https://openalex.org/W4231875539","https://openalex.org/W4239997146","https://openalex.org/W4242946001","https://openalex.org/W4362666558","https://openalex.org/W4362711416","https://openalex.org/W4386504997","https://openalex.org/W4401436014","https://openalex.org/W6606521517","https://openalex.org/W6691343681"],"related_works":["https://openalex.org/W2293118914","https://openalex.org/W2998381397","https://openalex.org/W4236419692","https://openalex.org/W2171015181","https://openalex.org/W3167919718","https://openalex.org/W4251718783","https://openalex.org/W4239447582","https://openalex.org/W1484403103","https://openalex.org/W2521947294","https://openalex.org/W1998888015"],"abstract_inverted_index":{"In":[0,26],"parallel":[1,202],"computing,":[2],"Data":[3],"Flow":[4],"Graphs":[5],"play":[6],"a":[7,71,100,114,118,162,176],"critical":[8],"role":[9],"by":[10],"explicitly":[11],"representing":[12],"the":[13,27,37,55,95,126,167,201],"dependencies":[14],"between":[15,92],"tasks,":[16,124],"which":[17,135],"is":[18,33],"essential":[19],"for":[20,51,79,122],"task":[21,60,105,217],"scheduling":[22,30],"and":[23,44,63,108,139,157,174,188,208,212,221],"resource":[24,219],"utilization.":[25],"process":[28],"of":[29,40,57,128,205],"optimization,":[31,220],"it":[32],"crucial":[34],"to":[35,89,131,149],"address":[36],"dual":[38],"challenges":[39],"balancing":[41],"computational":[42,172],"load":[43],"distributing":[45],"data":[46,61],"access":[47],"pressure.":[48],"The":[49],"Dataflow":[50],"C++":[52],"(DFCPP)":[53],"possesses":[54],"advantage":[56],"accurately":[58],"sensing":[59],"sizes,":[62],"based":[64],"on":[65,94],"this":[66,68],"capability,":[67],"paper":[69],"proposes":[70],"Primary-Secondary":[72],"Core":[73],"Selecting":[74],"(PSCS)":[75],"strategy":[76,87,121],"specifically":[77],"designed":[78],"Hyper-Threading-enabled":[80],"Non-Uniform":[81],"Memory":[82],"Access":[83],"systems":[84],"(HT-NUMA).":[85],"This":[86],"aims":[88],"mitigate":[90],"interference":[91],"threads":[93],"same":[96],"physical":[97],"core":[98,169],"in":[99,190,215],"hyper-threading":[101],"environment,":[102],"thereby":[103],"enhancing":[104],"execution":[106],"stability":[107],"overall":[109],"performance.":[110],"Additionally,":[111],"DFCPP":[112,159,184],"integrates":[113],"task-stealing":[115],"mechanism":[116],"with":[117,193],"proactive":[119],"allocation":[120],"large-cache":[123],"enabling":[125],"distribution":[127],"large":[129],"tasks":[130,192],"low-load":[132],"NUMA":[133,206],"nodes,":[134],"reduces":[136],"cache":[137,141],"contention":[138],"improves":[140],"hit":[142],"rates.":[143],"Experimental":[144],"results":[145],"demonstrate":[146],"that,":[147],"compared":[148],"common":[150],"dataflow":[151,216],"programming":[152],"libraries":[153],"such":[154],"as":[155],"Taskflow":[156],"TBB,":[158],"achieves":[160],"over":[161],"20%":[163],"performance":[164,211],"improvement":[165,178],"when":[166,179],"system":[168],"count":[170],"meets":[171],"demands,":[173],"nearly":[175],"25%":[177],"handling":[180],"large-dataset":[181],"tasks.":[182],"Furthermore,":[183],"exhibits":[185],"high":[186],"efficiency":[187],"adaptability":[189],"processing":[191],"various":[194],"directed":[195],"acyclic":[196],"graph":[197],"topologies,":[198],"fully":[199],"leveraging":[200],"computing":[203],"advantages":[204],"systems,":[207],"demonstrates":[209],"exceptional":[210],"broad":[213],"applicability":[214],"scheduling,":[218],"complex":[222],"dependency":[223],"management.":[224]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}