{"id":"https://openalex.org/W2508028078","doi":"https://doi.org/10.1145/2967938.2967946","title":"Scalable Task Parallelism for NUMA","display_name":"Scalable Task Parallelism for NUMA","publication_year":2016,"publication_date":"2016-08-31","ids":{"openalex":"https://openalex.org/W2508028078","doi":"https://doi.org/10.1145/2967938.2967946","mag":"2508028078"},"language":"en","primary_location":{"id":"doi:10.1145/2967938.2967946","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2967938.2967946","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 International Conference on Parallel Architectures and Compilation","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.manchester.ac.uk/en/publications/16d8484e-6bf1-4e60-85f2-da3bcae33da1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084849650","display_name":"Andi Drebes","orcid":null},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Andi Drebes","raw_affiliation_strings":["The University of Manchester, Manchester, United Kingdom","School of Computer Science [Manchester] (University of Manchester Oxford Road Manchester M13 9PL UK - Royaume-Uni)"],"affiliations":[{"raw_affiliation_string":"The University of Manchester, Manchester, United Kingdom","institution_ids":["https://openalex.org/I28407311"]},{"raw_affiliation_string":"School of Computer Science [Manchester] (University of Manchester Oxford Road Manchester M13 9PL UK - Royaume-Uni)","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027341627","display_name":"Antoniu Pop","orcid":"https://orcid.org/0000-0002-7715-4281"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Antoniu Pop","raw_affiliation_strings":["The University of Manchester, Manchester, United Kingdom","School of Computer Science [Manchester] (University of Manchester Oxford Road Manchester M13 9PL UK - Royaume-Uni)"],"affiliations":[{"raw_affiliation_string":"The University of Manchester, Manchester, United Kingdom","institution_ids":["https://openalex.org/I28407311"]},{"raw_affiliation_string":"School of Computer Science [Manchester] (University of Manchester Oxford Road Manchester M13 9PL UK - Royaume-Uni)","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034064440","display_name":"Karine Heydemann","orcid":"https://orcid.org/0000-0003-2092-924X"},"institutions":[{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Karine Heydemann","raw_affiliation_strings":["Sorbonne Universit\u00e9s, UPMC Univ Paris 06, Paris, France"],"affiliations":[{"raw_affiliation_string":"Sorbonne Universit\u00e9s, UPMC Univ Paris 06, Paris, France","institution_ids":["https://openalex.org/I39804081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063162788","display_name":"Albert Cohen","orcid":"https://orcid.org/0000-0002-8866-5343"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Albert Cohen","raw_affiliation_strings":["INRIA and \u00c9cole Normale Sup\u00e9rieure, Paris, France"],"affiliations":[{"raw_affiliation_string":"INRIA and \u00c9cole Normale Sup\u00e9rieure, Paris, France","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110757581","display_name":"Nathalie Drach","orcid":null},"institutions":[{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nathalie Drach","raw_affiliation_strings":["Sorbonne Universit\u00e9s, UPMC Univ Paris 06, Paris, France"],"affiliations":[{"raw_affiliation_string":"Sorbonne Universit\u00e9s, UPMC Univ Paris 06, Paris, France","institution_ids":["https://openalex.org/I39804081"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5084849650"],"corresponding_institution_ids":["https://openalex.org/I28407311"],"apc_list":null,"apc_paid":null,"fwci":4.7996,"has_fulltext":true,"cited_by_count":33,"citation_normalized_percentile":{"value":0.95312216,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"125","last_page":"137"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9993000030517578,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9991999864578247,"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":0.9091777801513672},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6602752208709717},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.6216512322425842},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.579168438911438},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5654393434524536},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5533697605133057},{"id":"https://openalex.org/keywords/task-parallelism","display_name":"Task parallelism","score":0.5239781737327576},{"id":"https://openalex.org/keywords/locality-of-reference","display_name":"Locality of reference","score":0.4812440872192383},{"id":"https://openalex.org/keywords/distributed-memory","display_name":"Distributed memory","score":0.47594761848449707},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.45347267389297485},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.44415411353111267},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.3648151159286499},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.33614057302474976},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.15973448753356934},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.14865750074386597}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9091777801513672},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6602752208709717},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.6216512322425842},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.579168438911438},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5654393434524536},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5533697605133057},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.5239781737327576},{"id":"https://openalex.org/C27602214","wikidata":"https://www.wikidata.org/wiki/Q1868547","display_name":"Locality of reference","level":3,"score":0.4812440872192383},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.47594761848449707},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.45347267389297485},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.44415411353111267},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.3648151159286499},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.33614057302474976},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.15973448753356934},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14865750074386597},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/2967938.2967946","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2967938.2967946","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 International Conference on Parallel Architectures and Compilation","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire/16d8484e-6bf1-4e60-85f2-da3bcae33da1","is_oa":true,"landing_page_url":"https://research.manchester.ac.uk/en/publications/16d8484e-6bf1-4e60-85f2-da3bcae33da1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Drebes, A, Pop, A, Heydemann, K, Cohen, A & Drach, N 2016, Scalable Task Parallelism for NUMA: A Uniform Abstraction for Coordinated Scheduling and Memory Management. in International Conference on Parallel Architecture and Compilation Techniques. pp. 125-137, International Conference on Parallel Architecture and Compilation Techniques, Haifa, Israel, 11/09/16. https://doi.org/10.1145/2967938.2967946","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:HAL:hal-01425743v1","is_oa":false,"landing_page_url":"https://inria.hal.science/hal-01425743","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PACT'16 - ACM/IEEE Conference on Parallel Architectures and Compilation Techniques, Sep 2016, Haifa, Israel. pp.125 - 137, ⟨10.1145/2967938.2967946⟩","raw_type":"Conference papers"},{"id":"pmh:oai:pure.atira.dk:publications/16d8484e-6bf1-4e60-85f2-da3bcae33da1","is_oa":false,"landing_page_url":"https://www.research.manchester.ac.uk/portal/en/publications/scalable-task-parallelism-for-numa-a-uniform-abstraction-for-coordinated-scheduling-and-memory-management(16d8484e-6bf1-4e60-85f2-da3bcae33da1).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:openaire/16d8484e-6bf1-4e60-85f2-da3bcae33da1","is_oa":true,"landing_page_url":"https://research.manchester.ac.uk/en/publications/16d8484e-6bf1-4e60-85f2-da3bcae33da1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Drebes, A, Pop, A, Heydemann, K, Cohen, A & Drach, N 2016, Scalable Task Parallelism for NUMA: A Uniform Abstraction for Coordinated Scheduling and Memory Management. in International Conference on Parallel Architecture and Compilation Techniques. pp. 125-137, International Conference on Parallel Architecture and Compilation Techniques, Haifa, Israel, 11/09/16. https://doi.org/10.1145/2967938.2967946","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1361938442","display_name":null,"funder_award_id":"Fellowship","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G14823364","display_name":"Hybrid Static / Dynamic Optimisations for Many-Cores: Breaking the Memory Wall","funder_award_id":"EP/M004880/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G2119974683","display_name":null,"funder_award_id":"EP/M004880/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G2864483227","display_name":null,"funder_award_id":"Fellowship","funder_id":"https://openalex.org/F4320320005","funder_display_name":"Royal Academy of Engineering"},{"id":"https://openalex.org/G37784125","display_name":null,"funder_award_id":"671578","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320320005","display_name":"Royal Academy of Engineering","ror":"https://ror.org/0526snb40"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W157734009","https://openalex.org/W1086484114","https://openalex.org/W1710455405","https://openalex.org/W1977899806","https://openalex.org/W1983876516","https://openalex.org/W1986864222","https://openalex.org/W2009964586","https://openalex.org/W2016559894","https://openalex.org/W2037244283","https://openalex.org/W2050626467","https://openalex.org/W2084903759","https://openalex.org/W2087085699","https://openalex.org/W2091511280","https://openalex.org/W2091905905","https://openalex.org/W2102490737","https://openalex.org/W2104861744","https://openalex.org/W2109065830","https://openalex.org/W2109639089","https://openalex.org/W2113941519","https://openalex.org/W2124142472","https://openalex.org/W2141389982","https://openalex.org/W2145442181","https://openalex.org/W2157802978","https://openalex.org/W2159184943","https://openalex.org/W2171119362","https://openalex.org/W2615176937","https://openalex.org/W2751343396","https://openalex.org/W2911472304","https://openalex.org/W2946724226","https://openalex.org/W4243404638"],"related_works":["https://openalex.org/W2950520577","https://openalex.org/W74409296","https://openalex.org/W2567390125","https://openalex.org/W2003935582","https://openalex.org/W1554644772","https://openalex.org/W305742777","https://openalex.org/W1638215063","https://openalex.org/W2468095077","https://openalex.org/W2940653809","https://openalex.org/W2026512611"],"abstract_inverted_index":{"Dynamic":[0],"task-parallel":[1,50,220],"programming":[2,51],"models":[3,52],"are":[4,19,126],"popular":[5],"on":[6,90,167],"shared-memory":[7],"systems,":[8],"promising":[9],"enhanced":[10],"scalability,":[11],"load":[12],"balancing":[13],"and":[14,32,46,116,134,153,184,213,215],"locality.":[15,57],"Yet":[16],"these":[17],"promises":[18],"undermined":[20],"by":[21,112,200],"non-uniform":[22],"memory":[23,47,73,165],"access":[24],"(NUMA).":[25],"We":[26,160],"show":[27,194],"that":[28,63,195],"using":[29],"NUMA-aware":[30,181],"task":[31,67,80,87,102,108],"data":[33,56,59,69,89,109,122,145,214],"placement,":[34],"it":[35],"is":[36],"possible":[37],"to":[38,66,136,176,188,218],"preserve":[39],"the":[40,71,75,84,105,150,157,201],"uniform":[41],"abstraction":[42],"of":[43,74,86,99,107,163],"both":[44],"computing":[45],"resources":[48],"for":[49],"while":[53],"achieving":[54],"high":[55],"Our":[58,95],"placement":[60,81,154],"scheme":[61],"guarantees":[62],"all":[64],"accesses":[65,166],"output":[68],"target":[70],"local":[72,164],"accessing":[76],"core.":[77],"The":[78,124],"complementary":[79],"heuristic":[82],"improves":[83],"locality":[85],"input":[88],"a":[91,168],"best":[92],"effort":[93],"basis.":[94],"algorithms":[96,125],"take":[97],"advantage":[98],"data-flow":[100],"style":[101],"parallelism,":[103],"where":[104],"privatization":[106],"enhances":[110],"scalability":[111],"eliminating":[113],"false":[114],"dependences":[115,146],"enabling":[117],"fine-grained":[118],"dynamic":[119,137,197],"control":[120],"over":[121],"placement.":[123],"fully":[127],"automatic,":[128],"application-independent,":[129],"performance-portable":[130],"across":[131],"NUMA":[132,173],"machines,":[133],"adapt":[135],"changes.":[138],"Placement":[139],"decisions":[140],"use":[141],"information":[142,155],"about":[143],"inter-task":[144],"readily":[147],"available":[148],"in":[149],"run-time":[151],"system":[152,170,203],"from":[156],"operating":[158,202],"system.":[159],"achieve":[161],"94%":[162],"192-core":[169],"with":[171,207],"24":[172],"nodes,":[174],"up":[175,206],"5x":[177],"higher":[178],"performance":[179],"than":[180],"hierarchical":[182],"work-stealing,":[183],"even":[185],"5.6x":[186],"compared":[187],"static":[189],"interleaved":[190],"allocation.":[191],"Finally,":[192],"we":[193],"state-of-the-art":[196],"page":[198],"migration":[199],"cannot":[204],"catch":[205],"frequent":[208],"affinity":[209],"changes":[210],"between":[211],"cores":[212],"thus":[216],"fails":[217],"accelerate":[219],"applications.":[221]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2016-09-16T00:00:00"}