{"id":"https://openalex.org/W2801436955","doi":"https://doi.org/10.1109/iscas.2018.8351552","title":"Kernel Aware Warp Scheduler","display_name":"Kernel Aware Warp Scheduler","publication_year":2018,"publication_date":"2018-05-01","ids":{"openalex":"https://openalex.org/W2801436955","doi":"https://doi.org/10.1109/iscas.2018.8351552","mag":"2801436955"},"language":"en","primary_location":{"id":"doi:10.1109/iscas.2018.8351552","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas.2018.8351552","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Symposium on Circuits and Systems (ISCAS)","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/A5045643007","display_name":"Sen-Chih Tsai","orcid":null},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Sen-Chih Tsai","raw_affiliation_strings":["Computer Architecture and System Laboratory, National Cheng-Kung University, Tainan, Taiwan"],"affiliations":[{"raw_affiliation_string":"Computer Architecture and System Laboratory, National Cheng-Kung University, Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046574849","display_name":"Yu-Xiang Su","orcid":null},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Xiang Su","raw_affiliation_strings":["Computer Architecture and System Laboratory, National Cheng-Kung University, Tainan, Taiwan"],"affiliations":[{"raw_affiliation_string":"Computer Architecture and System Laboratory, National Cheng-Kung University, Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007315548","display_name":"Y.C. Chin","orcid":null},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Han Chin","raw_affiliation_strings":["Computer Architecture and System Laboratory, National Cheng-Kung University, Tainan, Taiwan"],"affiliations":[{"raw_affiliation_string":"Computer Architecture and System Laboratory, National Cheng-Kung University, Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049644561","display_name":"Wei-Zhong Ceng","orcid":null},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wei-Zhong Ceng","raw_affiliation_strings":["Computer Architecture and System Laboratory, National Cheng-Kung University, Tainan, Taiwan"],"affiliations":[{"raw_affiliation_string":"Computer Architecture and System Laboratory, National Cheng-Kung University, Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111582905","display_name":"Chung\u2010Ho Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chung-Ho Chen","raw_affiliation_strings":["Computer Architecture and System Laboratory, National Cheng-Kung University, Tainan, Taiwan"],"affiliations":[{"raw_affiliation_string":"Computer Architecture and System Laboratory, National Cheng-Kung University, Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5045643007"],"corresponding_institution_ids":["https://openalex.org/I91807558"],"apc_list":null,"apc_paid":null,"fwci":0.2525,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.47262283,"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":"5"},"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":0.9993000030517578,"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":0.9991999864578247,"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":0.889672577381134},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7134346961975098},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.698066771030426},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.602942943572998},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5871104001998901},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5688667893409729},{"id":"https://openalex.org/keywords/multiprocessing","display_name":"Multiprocessing","score":0.47397011518478394},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4434177875518799},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.410478413105011},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3340528905391693}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.889672577381134},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7134346961975098},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.698066771030426},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.602942943572998},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5871104001998901},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5688667893409729},{"id":"https://openalex.org/C4822641","wikidata":"https://www.wikidata.org/wiki/Q846651","display_name":"Multiprocessing","level":2,"score":0.47397011518478394},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4434177875518799},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.410478413105011},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3340528905391693},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscas.2018.8351552","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas.2018.8351552","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Symposium on Circuits and Systems (ISCAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322214","display_name":"Industrial Technology Research Institute","ror":"https://ror.org/05szzwt63"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2048441570","https://openalex.org/W2053744175","https://openalex.org/W2079038734","https://openalex.org/W2081583983","https://openalex.org/W2516179478","https://openalex.org/W2534888058","https://openalex.org/W2539975594","https://openalex.org/W3137551601"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2027972911","https://openalex.org/W2544617286","https://openalex.org/W2148915962","https://openalex.org/W2084977540"],"abstract_inverted_index":{"Observing":[0],"that":[1,7,67],"thread":[2],"blocks":[3],"of":[4,25,46,71,88,95],"different":[5,9],"kernels":[6,49],"use":[8],"functional":[10,26,89],"units":[11,90],"should":[12],"be":[13],"sent":[14],"to":[15,21,50,100],"the":[16,23,43,47,54,68,72,85,96,101],"same":[17],"SM":[18],"(Streaming":[19],"Multiprocessor)":[20],"promote":[22],"utilization":[24,87],"units,":[27],"we":[28],"propose":[29],"a":[30],"kernel-aware":[31],"warp":[32,103],"scheduler":[33],"for":[34],"GPGPUs.":[35],"The":[36,57,81],"proposed":[37,102],"Kernel":[38],"Aware":[39],"Warp":[40],"Scheduler":[41],"uses":[42],"profiling":[44],"information":[45],"executed":[48],"issue":[51],"instructions":[52],"from":[53,84],"right":[55],"warp.":[56],"experimental":[58],"results":[59],"based":[60],"on":[61,79],"our":[62],"HSAIL":[63],"simulation":[64],"platform":[65],"show":[66],"overall":[69],"performance":[70],"kernel":[73],"execution":[74],"improves":[75],"by":[76],"about":[77],"20%":[78],"average.":[80],"speedup":[82],"comes":[83],"increased":[86],"and":[91],"effectiveness":[92],"in":[93],"hiding":[94],"memory":[97],"latency":[98],"due":[99],"scheduling":[104],"policy.":[105]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}