{"id":"https://openalex.org/W2517977240","doi":"https://doi.org/10.1145/2967938.2967952","title":"Automatically Exploiting Implicit Pipeline Parallelism from Multiple Dependent Kernels for GPUs","display_name":"Automatically Exploiting Implicit Pipeline Parallelism from Multiple Dependent Kernels for GPUs","publication_year":2016,"publication_date":"2016-08-31","ids":{"openalex":"https://openalex.org/W2517977240","doi":"https://doi.org/10.1145/2967938.2967952","mag":"2517977240"},"language":"en","primary_location":{"id":"doi:10.1145/2967938.2967952","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2967938.2967952","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":"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/A5100334897","display_name":"Gwangsun Kim","orcid":"https://orcid.org/0000-0001-5749-5794"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Gwangsun Kim","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072609114","display_name":"Jiyun Jeong","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jiyun Jeong","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100698124","display_name":"John Kim","orcid":"https://orcid.org/0000-0003-3958-3891"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"John Kim","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015391591","display_name":"Mark W. Stephenson","orcid":"https://orcid.org/0000-0002-1350-0165"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Stephenson","raw_affiliation_strings":["NVIDIA, Austin, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA, Austin, USA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100334897"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":2.5598,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.8919534,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"341","last_page":"352"},"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/T11181","display_name":"Advanced Data Storage Technologies","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"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9990000128746033,"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":0.9153276681900024},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.816084086894989},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5625057816505432},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.5247057676315308},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.5093058347702026},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5081818103790283},{"id":"https://openalex.org/keywords/programmer","display_name":"Programmer","score":0.4613594710826874},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.4459289014339447},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.4199531674385071},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.39233386516571045},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.21388313174247742},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.18806114792823792},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1506519317626953}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9153276681900024},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.816084086894989},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5625057816505432},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.5247057676315308},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.5093058347702026},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5081818103790283},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.4613594710826874},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.4459289014339447},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.4199531674385071},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.39233386516571045},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.21388313174247742},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.18806114792823792},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1506519317626953},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2967938.2967952","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2967938.2967952","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:oasis.postech.ac.kr:2014.oak/94451","is_oa":false,"landing_page_url":"https://oasis.postech.ac.kr/handle/2014.oak/94451","pdf_url":null,"source":{"id":"https://openalex.org/S4306401965","display_name":"Open Access System for Information Sharing (Pohang University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I123900574","host_organization_name":"Pohang University of Science and Technology","host_organization_lineage":["https://openalex.org/I123900574"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1446278828","https://openalex.org/W1965601529","https://openalex.org/W1966124831","https://openalex.org/W1979527452","https://openalex.org/W1979717209","https://openalex.org/W1991709203","https://openalex.org/W2001559332","https://openalex.org/W2016352575","https://openalex.org/W2041679393","https://openalex.org/W2042681472","https://openalex.org/W2067280503","https://openalex.org/W2079038734","https://openalex.org/W2080592089","https://openalex.org/W2080756995","https://openalex.org/W2095894588","https://openalex.org/W2100415730","https://openalex.org/W2109051991","https://openalex.org/W2127510911","https://openalex.org/W2128120785","https://openalex.org/W2150851481","https://openalex.org/W2153185479","https://openalex.org/W2167101788","https://openalex.org/W2252556718","https://openalex.org/W2273440736","https://openalex.org/W2330672121","https://openalex.org/W4241790656"],"related_works":["https://openalex.org/W85300993","https://openalex.org/W2950520577","https://openalex.org/W1501159154","https://openalex.org/W1554644772","https://openalex.org/W2003935582","https://openalex.org/W2494130044","https://openalex.org/W3170887803","https://openalex.org/W74409296","https://openalex.org/W3209384898","https://openalex.org/W4400951174"],"abstract_inverted_index":{"Execution":[0],"of":[1,5,61,69,82,96,117,190,196,204],"GPGPU":[2],"workloads":[3,83],"consists":[4],"different":[6],"stages":[7],"including":[8],"data":[9,40,71],"I/O":[10,30],"on":[11,185],"the":[12,17,59,62,67,80,94,130,174,188,197,217],"CPU,":[13],"memory":[14,32,44],"copy":[15],"between":[16],"CPU":[18],"and":[19,21,31,43,66,165],"GPU,":[20],"kernel":[22,47,210],"execution.":[23],"While":[24],"GPU":[25],"can":[26,49,73,177],"remain":[27],"idle":[28],"during":[29,114],"copy,":[33],"prior":[34],"work":[35,199],"has":[36],"shown":[37],"that":[38,84,151,173,200],"overlapping":[39,70],"movement":[41,72],"(I/O":[42],"copies)":[45],"with":[46],"execution":[48,60,95,116,203],"improve":[50,79,126,166,178],"performance.":[51,168],"However,":[52,120],"when":[53],"there":[54],"are":[55,135],"multiple":[56,86,118,205],"dependent":[57,87,206],"kernels,":[58,88],"kernels":[63,97,207],"is":[64,194],"serialized":[65],"benefit":[68],"be":[74],"limited.":[75],"In":[76],"order":[77],"to":[78,91,111,161,182],"performance":[81,128,179],"have":[85],"we":[89,139],"propose":[90,105,140],"automatically":[92],"overlap":[93],"by":[98,180,216],"exploiting":[99],"implicit":[100],"pipeline":[101,154,163],"parallelism.":[102],"We":[103],"first":[104,198],"Coarse-grained":[106],"Reference":[107],"Counting-based":[108],"Scoreboarding":[109],"(CRCS)":[110],"guarantee":[112],"correctness":[113],"overlapped":[115,202],"kernels.":[119],"CRCS":[121],"alone":[122],"does":[123],"not":[124],"necessarily":[125],"overall":[127,167],"if":[129],"thread":[131],"blocks":[132],"(or":[133],"CTAs)":[134],"scheduled":[136],"sequentially.":[137],"Thus,":[138],"an":[141],"alternative":[142],"CTA":[143,148,159],"scheduler":[144],"-":[145],"Pipeline":[146],"Parallelism-aware":[147],"Scheduler":[149],"(PPCS)":[150],"takes":[152],"available":[153],"parallelism":[155,164],"into":[156],"account":[157],"in":[158],"scheduling":[160],"maximize":[162],"Our":[169],"evaluation":[170],"results":[171],"show":[172],"proposed":[175],"mechanisms":[176],"up":[181],"67%":[183],"(33%":[184],"average).":[186],"To":[187],"best":[189],"our":[191],"knowledge,":[192],"this":[193],"one":[195],"enables":[201],"without":[208],"any":[209],"modification":[211],"or":[212],"explicitly":[213],"expressing":[214],"dependency":[215],"programmer.":[218]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}