{"id":"https://openalex.org/W2887805304","doi":"https://doi.org/10.1145/3229710.3229723","title":"Scheduling Methods to Optimize Dependent Programs for GPU Architecture","display_name":"Scheduling Methods to Optimize Dependent Programs for GPU Architecture","publication_year":2018,"publication_date":"2018-07-31","ids":{"openalex":"https://openalex.org/W2887805304","doi":"https://doi.org/10.1145/3229710.3229723","mag":"2887805304"},"language":"en","primary_location":{"id":"doi:10.1145/3229710.3229723","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3229710.3229723","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International Conference on Parallel Processing Companion","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/A5101465606","display_name":"Wei-Cheng Liao","orcid":"https://orcid.org/0000-0002-5797-1049"},"institutions":[{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wei-Cheng Liao","raw_affiliation_strings":["National Taiwan University of Science and Technology, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University of Science and Technology, Taipei, Taiwan","institution_ids":["https://openalex.org/I154864474"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101687590","display_name":"Yuan\u2010Ming Chang","orcid":"https://orcid.org/0000-0001-7831-987X"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yuan-Ming Chang","raw_affiliation_strings":["National Tsing Hua University, Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037552091","display_name":"Shao-Chung Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shao-Chung Wang","raw_affiliation_strings":["National Tsing Hua University, Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101660516","display_name":"Chun\u2010Chieh Yang","orcid":"https://orcid.org/0000-0002-1897-5338"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chun-Chieh Yang","raw_affiliation_strings":["National Tsing Hua University, Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038803698","display_name":"Jenq\u2010Kuen Lee","orcid":"https://orcid.org/0000-0001-9919-6258"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jenq-Kuen Lee","raw_affiliation_strings":["National Tsing-Hua University, Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing-Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041551416","display_name":"Yuan\u2010Shin Hwang","orcid":null},"institutions":[{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yuan-Shin Hwang","raw_affiliation_strings":["National Taiwan University of Science and Technology, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University of Science and Technology, Taipei, Taiwan","institution_ids":["https://openalex.org/I154864474"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2375,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.52445778,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9973000288009644,"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":0.8924458622932434},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7139382362365723},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.66233229637146},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5911595821380615},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.498640775680542},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.49114224314689636},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4372902512550354},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.33159536123275757},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19836047291755676},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.0853862464427948},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.08339300751686096}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8924458622932434},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7139382362365723},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.66233229637146},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5911595821380615},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.498640775680542},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.49114224314689636},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4372902512550354},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.33159536123275757},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19836047291755676},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0853862464427948},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.08339300751686096},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3229710.3229723","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3229710.3229723","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International Conference on Parallel Processing Companion","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1871378126","https://openalex.org/W1979527452","https://openalex.org/W2097643185","https://openalex.org/W2099084006","https://openalex.org/W2155893237","https://openalex.org/W2517977240","https://openalex.org/W2761591491","https://openalex.org/W2767882261","https://openalex.org/W2799595460"],"related_works":["https://openalex.org/W3062287","https://openalex.org/W3213381848","https://openalex.org/W2005148983","https://openalex.org/W2017587301","https://openalex.org/W2012954338","https://openalex.org/W2602637431","https://openalex.org/W2096672917","https://openalex.org/W2392023973","https://openalex.org/W2939411666","https://openalex.org/W1973046741"],"abstract_inverted_index":{"GPUs":[0],"have":[1],"now":[2],"been":[3],"widely":[4],"used":[5],"in":[6,59,63],"various":[7],"computation-intensive":[8],"applications,":[9],"such":[10],"as":[11],"image":[12],"processing,":[13],"deep":[14],"learning,":[15],"artificial":[16],"intelligence,":[17],"etc.":[18],"As":[19],"these":[20],"applications":[21],"could":[22],"be":[23,34,86],"modeled":[24],"by":[25,56,109],"multiple":[26],"GPU":[27,49],"kernels,":[28,79],"some":[29],"of":[30,54],"which":[31],"might":[32],"even":[33],"dependent,":[35],"it":[36],"is":[37],"essential":[38],"to":[39,44,71],"find":[40],"an":[41,91],"efficient":[42,92],"method":[43,93],"schedule":[45],"dependent":[46,67,78,96],"kernels":[47,55,68,97],"on":[48,98,111],"cores.":[50],"Simply":[51],"observing":[52],"dependences":[53],"executing":[57],"them":[58],"sequence":[60],"will":[61,85],"result":[62],"performance":[64,108],"degradation.":[65],"Furthermore,":[66],"generally":[69],"need":[70],"share":[72],"data.":[73],"Consequently,":[74],"without":[75],"properly":[76],"scheduling":[77,95],"unnecessary":[80],"memory":[81,117],"accesses":[82],"and":[83],"copies":[84],"generated.":[87],"This":[88],"paper":[89],"proposes":[90],"for":[94],"GPUs.":[99],"Preliminary":[100],"experimental":[101],"results":[102],"show":[103],"that":[104],"this":[105],"technique":[106],"improves":[107],"43%":[110],"average":[112],"when":[113],"combining":[114],"with":[115],"appropriate":[116],"write-back":[118],"policies.":[119]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}