{"id":"https://openalex.org/W3091118039","doi":"https://doi.org/10.1109/iscas45731.2020.9180866","title":"Optimization of Stride Prefetching Mechanism and Dependent Warp Scheduling on GPGPU","display_name":"Optimization of Stride Prefetching Mechanism and Dependent Warp Scheduling on GPGPU","publication_year":2020,"publication_date":"2020-09-29","ids":{"openalex":"https://openalex.org/W3091118039","doi":"https://doi.org/10.1109/iscas45731.2020.9180866","mag":"3091118039"},"language":"en","primary_location":{"id":"doi:10.1109/iscas45731.2020.9180866","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas45731.2020.9180866","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 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/A5003365494","display_name":"Tsung-Han Tsou","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":"Tsung-Han Tsou","raw_affiliation_strings":["Inst. of Computer and Communication Engineering, Dept. of Electrical Engineering, National Cheng-Kung University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inst. of Computer and Communication Engineering, Dept. of Electrical Engineering, National Cheng-Kung University, Taiwan","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028815027","display_name":"Dun-Jie 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":"Dun-Jie Chen","raw_affiliation_strings":["Inst. of Computer and Communication Engineering, Dept. of Electrical Engineering, National Cheng-Kung University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inst. of Computer and Communication Engineering, Dept. of Electrical Engineering, National Cheng-Kung University, Taiwan","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002764843","display_name":"Sheng-Yang Hung","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":"Sheng-Yang Hung","raw_affiliation_strings":["Inst. of Computer and Communication Engineering, Dept. of Electrical Engineering, National Cheng-Kung University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inst. of Computer and Communication Engineering, Dept. of Electrical Engineering, National Cheng-Kung University, Taiwan","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032461992","display_name":"Yu\u2010Hsiang Wang","orcid":"https://orcid.org/0000-0002-6278-2664"},"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-Hsiang Wang","raw_affiliation_strings":["Inst. of Computer and Communication Engineering, Dept. of Electrical Engineering, National Cheng-Kung University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inst. of Computer and Communication Engineering, Dept. of Electrical Engineering, National Cheng-Kung University, 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":["Inst. of Computer and Communication Engineering, Dept. of Electrical Engineering, National Cheng-Kung University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inst. of Computer and Communication Engineering, Dept. of Electrical Engineering, National Cheng-Kung University, Taiwan","institution_ids":["https://openalex.org/I91807558"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.236,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.50316946,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"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":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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9995999932289124,"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":0.9952999949455261,"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/instruction-prefetch","display_name":"Instruction prefetch","score":0.9701943397521973},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8923382759094238},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.6716470122337341},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.62171471118927},{"id":"https://openalex.org/keywords/stride","display_name":"STRIDE","score":0.5957860946655273},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.511655867099762},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.48780325055122375},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.46176663041114807},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3710567355155945},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.16373109817504883}],"concepts":[{"id":"https://openalex.org/C133588205","wikidata":"https://www.wikidata.org/wiki/Q28455645","display_name":"Instruction prefetch","level":3,"score":0.9701943397521973},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8923382759094238},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.6716470122337341},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.62171471118927},{"id":"https://openalex.org/C18007350","wikidata":"https://www.wikidata.org/wiki/Q7394815","display_name":"STRIDE","level":2,"score":0.5957860946655273},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.511655867099762},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.48780325055122375},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.46176663041114807},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3710567355155945},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.16373109817504883},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscas45731.2020.9180866","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas45731.2020.9180866","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Symposium on Circuits and Systems (ISCAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1983235612","https://openalex.org/W2090584832","https://openalex.org/W2107349848","https://openalex.org/W2152659795","https://openalex.org/W2166620913","https://openalex.org/W2916411819","https://openalex.org/W4251259849"],"related_works":["https://openalex.org/W2140324148","https://openalex.org/W2121199344","https://openalex.org/W2285914869","https://openalex.org/W3117515082","https://openalex.org/W2113441357","https://openalex.org/W3022537591","https://openalex.org/W2167639078","https://openalex.org/W2379283503","https://openalex.org/W2141676084","https://openalex.org/W2462146500"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,28],"propose":[4],"a":[5,15,33],"data":[6,139],"prefetching":[7,93,105],"scheme,":[8],"History-Awoken":[9],"Stride":[10],"(HAS)":[11],"prefetching,":[12],"optimized":[13],"with":[14,48],"warp":[16,88],"scheduler,":[17],"Prefetched-Then-Executed":[18],"(PTE),":[19],"and":[20,45,72,83,87,115,135,149],"evaluate":[21],"the":[22,25,75,92,96,150,157],"performance":[23,131],"on":[24,120],"platform":[26,31],"that":[27,123],"developed.":[29],"Our":[30],"is":[32],"single":[34],"instruction,":[35],"multiple":[36],"thread":[37],"(SIMT)":[38],"GPGPU":[39],"environment,":[40],"supporting":[41],"OpenCL":[42],"1.2":[43],"runtime":[44],"TensorFlow":[46],"framework":[47],"CUDA-on-CL":[49],"technology.":[50],"Enormous":[51],"amount":[52],"of":[53,66,74,95,112,133,152],"executing":[54],"threads":[55],"in":[56,70,138],"GPU":[57],"demands":[58],"critical":[59],"memory":[60,68],"performance.":[61],"HAS":[62],"exploits":[63],"history":[64],"table":[65],"related":[67],"accesses":[69],"intra-warp":[71],"inter-warp":[73],"same":[76],"workgroup":[77],"as":[78,80],"well":[79],"among":[81],"workgroups,":[82],"uses":[84],"address":[85],"strides":[86],"status":[89,106],"to":[90,104],"monitor":[91],"progress":[94],"executed":[97],"warp.":[98],"PTE":[99],"precisely":[100],"issues":[101],"warps":[102],"according":[103],"from":[107],"HAS.":[108],"The":[109,143],"experimental":[110],"results":[111],"LeNet-5":[113],"inference":[114],"11":[116],"PolyBench":[117],"test":[118],"programs":[119],"CAS-GPU":[121],"show":[122],"our":[124],"mechanism":[125],"can":[126,146],"achieve":[127],"an":[128],"average":[129],"IPC":[130],"improvement":[132],"10.4%,":[134],"7.8%":[136],"reduction":[137],"cache":[140],"miss":[141],"rate.":[142],"prefetch":[144,153],"accuracy":[145],"reach":[147],"67.7%,":[148],"proportion":[151],"request":[154],"arrived":[155],"at":[156],"appropriate":[158],"time":[159],"reaches":[160],"48.2%.":[161]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}