{"id":"https://openalex.org/W1981109753","doi":"https://doi.org/10.1145/1854273.1854298","title":"Reducing task creation and termination overhead in explicitly parallel programs","display_name":"Reducing task creation and termination overhead in explicitly parallel programs","publication_year":2010,"publication_date":"2010-09-11","ids":{"openalex":"https://openalex.org/W1981109753","doi":"https://doi.org/10.1145/1854273.1854298","mag":"1981109753"},"language":"en","primary_location":{"id":"doi:10.1145/1854273.1854298","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1854273.1854298","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th international conference on Parallel architectures and compilation techniques","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/A5048301900","display_name":"Jisheng Zhao","orcid":"https://orcid.org/0000-0001-5769-4507"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jisheng Zhao","raw_affiliation_strings":["Rice University, Houston, TX, USA","Rice Univ., Houston, TX, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Rice University, Houston, TX, USA","institution_ids":["https://openalex.org/I74775410"]},{"raw_affiliation_string":"Rice Univ., Houston, TX, USA#TAB#","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067511475","display_name":"Jun Shirako","orcid":"https://orcid.org/0000-0002-7900-7680"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jun Shirako","raw_affiliation_strings":["Rice University, Houston, TX, USA","Rice Univ., Houston, TX, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Rice University, Houston, TX, USA","institution_ids":["https://openalex.org/I74775410"]},{"raw_affiliation_string":"Rice Univ., Houston, TX, USA#TAB#","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022804082","display_name":"V. Krishna Nandivada","orcid":"https://orcid.org/0000-0002-5949-0046"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210129961","display_name":"IBM (India)","ror":"https://ror.org/034ahpr11","country_code":"IN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210129961"]}],"countries":["IN","US"],"is_corresponding":false,"raw_author_name":"V. Krishna Nandivada","raw_affiliation_strings":["IBM, Bangalore, India","[IBM, Bangalore, India]"],"affiliations":[{"raw_affiliation_string":"IBM, Bangalore, India","institution_ids":["https://openalex.org/I4210129961"]},{"raw_affiliation_string":"[IBM, Bangalore, India]","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043513001","display_name":"Vivek Sarkar","orcid":"https://orcid.org/0000-0002-3433-8830"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vivek Sarkar","raw_affiliation_strings":["Rice University, Houston, TX, USA","Rice Univ., Houston, TX, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Rice University, Houston, TX, USA","institution_ids":["https://openalex.org/I74775410"]},{"raw_affiliation_string":"Rice Univ., Houston, TX, USA#TAB#","institution_ids":["https://openalex.org/I74775410"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5048301900"],"corresponding_institution_ids":["https://openalex.org/I74775410"],"apc_list":null,"apc_paid":null,"fwci":3.2823,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.92264782,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"169","last_page":"180"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9986000061035156,"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"}},{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9970999956130981,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8714605569839478},{"id":"https://openalex.org/keywords/task-parallelism","display_name":"Task parallelism","score":0.7156132459640503},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6957665681838989},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.6239194273948669},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.5773848295211792},{"id":"https://openalex.org/keywords/implicit-parallelism","display_name":"Implicit parallelism","score":0.5280091166496277},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5220993757247925},{"id":"https://openalex.org/keywords/runtime-system","display_name":"Runtime system","score":0.4898921847343445},{"id":"https://openalex.org/keywords/concurrency","display_name":"Concurrency","score":0.489482045173645},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4727536141872406},{"id":"https://openalex.org/keywords/multithreading","display_name":"Multithreading","score":0.471781462430954},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4685187041759491},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.4679500162601471},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.43683528900146484},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.4235593378543854},{"id":"https://openalex.org/keywords/posix-threads","display_name":"POSIX Threads","score":0.4150370657444},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2631688416004181},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.2484378218650818}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8714605569839478},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.7156132459640503},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6957665681838989},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.6239194273948669},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.5773848295211792},{"id":"https://openalex.org/C3543717","wikidata":"https://www.wikidata.org/wiki/Q6007302","display_name":"Implicit parallelism","level":4,"score":0.5280091166496277},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5220993757247925},{"id":"https://openalex.org/C2780870223","wikidata":"https://www.wikidata.org/wiki/Q1004415","display_name":"Runtime system","level":2,"score":0.4898921847343445},{"id":"https://openalex.org/C193702766","wikidata":"https://www.wikidata.org/wiki/Q1414548","display_name":"Concurrency","level":2,"score":0.489482045173645},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4727536141872406},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.471781462430954},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4685187041759491},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.4679500162601471},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.43683528900146484},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4235593378543854},{"id":"https://openalex.org/C41138395","wikidata":"https://www.wikidata.org/wiki/Q928112","display_name":"POSIX Threads","level":3,"score":0.4150370657444},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2631688416004181},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.2484378218650818}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1854273.1854298","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1854273.1854298","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th international conference on Parallel architectures and compilation techniques","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.639.2370","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.639.2370","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.rice.edu/~vs3/PDF/ZSNS10.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W307918303","https://openalex.org/W1494930385","https://openalex.org/W1534870518","https://openalex.org/W1588278888","https://openalex.org/W1970787534","https://openalex.org/W1990886115","https://openalex.org/W1998604148","https://openalex.org/W2008677874","https://openalex.org/W2012394090","https://openalex.org/W2059654835","https://openalex.org/W2091547234","https://openalex.org/W2104861744","https://openalex.org/W2109065830","https://openalex.org/W2112121929","https://openalex.org/W2119148081","https://openalex.org/W2136763012","https://openalex.org/W2147671175","https://openalex.org/W2149207009","https://openalex.org/W2395077608","https://openalex.org/W2783040245","https://openalex.org/W3006649941","https://openalex.org/W4285719527","https://openalex.org/W6632010911","https://openalex.org/W6650021354"],"related_works":["https://openalex.org/W2003935582","https://openalex.org/W4240606930","https://openalex.org/W2526302199","https://openalex.org/W74409296","https://openalex.org/W2494130044","https://openalex.org/W1972271823","https://openalex.org/W2950520577","https://openalex.org/W1483753031","https://openalex.org/W2124828090","https://openalex.org/W2059654835"],"abstract_inverted_index":{"There":[0],"has":[1],"been":[2],"a":[3,100,111,155,162,169,214],"proliferation":[4],"of":[5,13,91,96,128,140,249],"task-parallel":[6,18,37,116],"programming":[7],"systems":[8,19],"to":[9,53,59,103,114,144,199],"address":[10,88],"the":[11,51,56,71,89,93,230,238,243,247,250],"requirements":[12],"multicore":[14],"programmers.":[15],"Current":[16],"production":[17],"include":[20,39],"Cilk++,":[21],"Intel":[22,165],"Threading":[23],"Building":[24],"Blocks,":[25],"Java":[26],"Concurrency,":[27],".Net":[28],"Task":[29],"Parallel":[30],"Library,":[31],"OpenMP":[32],"3.0,":[33],"and":[34,44,68,107,121,132,168,181,187,190],"current":[35],"research":[36],"languages":[38],"Cilk,":[40],"Chapel,":[41],"Fortress,":[42],"X10,":[43],"Habanero-Java":[45],"(HJ).":[46],"It":[47],"is":[48],"desirable":[49],"for":[50,65,221,229],"programmer":[52],"express":[54],"all":[55],"parallelism":[57],"intrinsic":[58],"their":[60,63],"algorithm":[61],"in":[62,81,195,206,235,254],"code":[64],"forward":[66],"scalability":[67],"portability,":[69],"but":[70],"overhead":[72,97],"incurred":[73,98],"by":[74,99,242],"doing":[75],"so":[76],"can":[77,218],"be":[78,219],"prohibitively":[79],"large":[80],"today's":[82],"systems.":[83],"In":[84],"this":[85,207,236,255],"paper,":[86,237],"we":[87],"problem":[90],"reducing":[92],"total":[94],"amount":[95],"program":[101],"due":[102],"excessive":[104],"task":[105,130],"creation":[106,131],"termination.":[108],"We":[109],"introduce":[110],"transformation":[112,244],"framework":[113,245],"optimize":[115],"programs":[117,222],"with":[118,211,224],"finish,":[119],"forall":[120],"next":[122],"statements.":[123],"Our":[124],"approach":[125],"includes":[126],"elimination":[127],"redundant":[129],"termination":[133,141],"operations":[134,142],"as":[135,137],"well":[136],"strength":[138],"reduction":[139],"(finish)":[143],"lighter-weight":[145],"synchronizations":[146],"(next).":[147],"Experimental":[148],"results":[149,175],"were":[150,209],"obtained":[151,241],"on":[152,184],"three":[153],"platforms:":[154],"dual-socket":[156],"128-thread":[157],"(16-core)":[158],"Niagara":[159],"T2":[160],"system,":[161],"quad-socket":[163,170],"16-way":[164],"Xeon":[166],"SMP":[167],"32-way":[171],"Power7":[172],"SMP.":[173],"The":[174,203],"showed":[176],"maximum":[177],"speedup":[178],"66.7x,":[179],"11.25x":[180],"23.1x":[182],"respectively":[183,194],"each":[185],"platform":[186],"4.6x,":[188],"2.1x":[189],"6.4x":[191],"performance":[192],"improvements":[193],"geometric":[196],"mean":[197],"related":[198],"non-optimized":[200],"parallel":[201,232],"codes.":[202],"original":[204],"benchmarks":[205,233],"study":[208],"written":[210,223],"medium-grained":[212,231],"parallelism;":[213],"larger":[215],"relative":[216],"improvement":[217,240],"expected":[220],"finer-grained":[225],"parallelism.":[226],"However,":[227],"even":[228],"studied":[234],"significant":[239],"underscores":[246],"importance":[248],"compiler":[251],"optimizations":[252],"introduced":[253],"paper.":[256]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}