{"id":"https://openalex.org/W4205335453","doi":"https://doi.org/10.1109/nvmsa53655.2021.9628829","title":"Scheduling-Aware Prefetching: Enabling the PCIe SSD to Extend the Global Memory of GPU Device","display_name":"Scheduling-Aware Prefetching: Enabling the PCIe SSD to Extend the Global Memory of GPU Device","publication_year":2021,"publication_date":"2021-08-18","ids":{"openalex":"https://openalex.org/W4205335453","doi":"https://doi.org/10.1109/nvmsa53655.2021.9628829"},"language":"en","primary_location":{"id":"doi:10.1109/nvmsa53655.2021.9628829","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nvmsa53655.2021.9628829","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 10th Non-Volatile Memory Systems and Applications Symposium (NVMSA)","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/A5020602495","display_name":"Tse-Yuan Wang","orcid":"https://orcid.org/0000-0003-0919-7252"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]},{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Tse-Yuan Wang","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Taiwan University, Taiwan","Institute of Information Science, Academia Sinica, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064046587","display_name":"Chun-Feng Wu","orcid":"https://orcid.org/0000-0002-6367-0517"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]},{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chun-Feng Wu","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Taiwan University, Taiwan","Institute of Information Science, Academia Sinica, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105297329","display_name":"Che-Wei Tsao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]},{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Che-Wei Tsao","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Taiwan University, Taiwan","Institute of Information Science, Academia Sinica, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073534245","display_name":"Yuan-Hao Chang","orcid":"https://orcid.org/0000-0002-1282-2111"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yuan-Hao Chang","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056407308","display_name":"Tei\u2010Wei Kuo","orcid":"https://orcid.org/0000-0003-1974-0394"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]},{"id":"https://openalex.org/I4210107525","display_name":"National Center for High-Performance Computing","ror":"https://ror.org/01jpzd518","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210107525","https://openalex.org/I4210128167","https://openalex.org/I4210166867"]},{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK","TW"],"is_corresponding":false,"raw_author_name":"Tei-Wei Kuo","raw_affiliation_strings":["College of Engineering, City University of Hong Kong, Hong Kong","Department of Computer Science and Information Engineering, National Taiwan University, Taiwan","NTU High Performance and Scientific Computing Center, National Taiwan University, Taiwan"],"affiliations":[{"raw_affiliation_string":"College of Engineering, City University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]},{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"NTU High Performance and Scientific Computing Center, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I4210107525","https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5020602495"],"corresponding_institution_ids":["https://openalex.org/I16733864","https://openalex.org/I4210098366"],"apc_list":null,"apc_paid":null,"fwci":0.1528,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53988384,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"5","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":1.0,"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/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/T11478","display_name":"Caching and Content Delivery","score":0.9980999827384949,"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/pci-express","display_name":"PCI Express","score":0.8843680620193481},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8232863545417786},{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.814547598361969},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.6399391293525696},{"id":"https://openalex.org/keywords/cas-latency","display_name":"CAS latency","score":0.585666835308075},{"id":"https://openalex.org/keywords/memory-controller","display_name":"Memory controller","score":0.5266245007514954},{"id":"https://openalex.org/keywords/host","display_name":"Host (biology)","score":0.5121159553527832},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4989166259765625},{"id":"https://openalex.org/keywords/remote-direct-memory-access","display_name":"Remote direct memory access","score":0.4750542640686035},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.4715799391269684},{"id":"https://openalex.org/keywords/universal-memory","display_name":"Universal memory","score":0.420022189617157},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.36199578642845154},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3505299389362335},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.31832972168922424},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.23336735367774963},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.22023648023605347},{"id":"https://openalex.org/keywords/interleaved-memory","display_name":"Interleaved memory","score":0.17488056421279907},{"id":"https://openalex.org/keywords/semiconductor-memory","display_name":"Semiconductor memory","score":0.16623413562774658}],"concepts":[{"id":"https://openalex.org/C64270927","wikidata":"https://www.wikidata.org/wiki/Q206924","display_name":"PCI Express","level":3,"score":0.8843680620193481},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8232863545417786},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.814547598361969},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.6399391293525696},{"id":"https://openalex.org/C189930140","wikidata":"https://www.wikidata.org/wiki/Q1112878","display_name":"CAS latency","level":4,"score":0.585666835308075},{"id":"https://openalex.org/C100800780","wikidata":"https://www.wikidata.org/wiki/Q1175867","display_name":"Memory controller","level":3,"score":0.5266245007514954},{"id":"https://openalex.org/C126831891","wikidata":"https://www.wikidata.org/wiki/Q221673","display_name":"Host (biology)","level":2,"score":0.5121159553527832},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4989166259765625},{"id":"https://openalex.org/C130795937","wikidata":"https://www.wikidata.org/wiki/Q2561570","display_name":"Remote direct memory access","level":2,"score":0.4750542640686035},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.4715799391269684},{"id":"https://openalex.org/C195053848","wikidata":"https://www.wikidata.org/wiki/Q7894141","display_name":"Universal memory","level":5,"score":0.420022189617157},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.36199578642845154},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3505299389362335},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.31832972168922424},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.23336735367774963},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.22023648023605347},{"id":"https://openalex.org/C63511323","wikidata":"https://www.wikidata.org/wiki/Q908936","display_name":"Interleaved memory","level":4,"score":0.17488056421279907},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.16623413562774658},{"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/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/nvmsa53655.2021.9628829","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nvmsa53655.2021.9628829","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 10th Non-Volatile Memory Systems and Applications Symposium (NVMSA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.9100000262260437,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309618","display_name":"Ministry of Science and Technology","ror":"https://ror.org/02b207r52"},{"id":"https://openalex.org/F4320321041","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W41212852","https://openalex.org/W1541729506","https://openalex.org/W1578858535","https://openalex.org/W1669357676","https://openalex.org/W1815525760","https://openalex.org/W1860107648","https://openalex.org/W1979527452","https://openalex.org/W2000335122","https://openalex.org/W2018384083","https://openalex.org/W2090584832","https://openalex.org/W2379559066","https://openalex.org/W2757759139","https://openalex.org/W2769084511","https://openalex.org/W2781905729","https://openalex.org/W2803016101","https://openalex.org/W2897904688","https://openalex.org/W2979642427","https://openalex.org/W2999459628","https://openalex.org/W3089883684","https://openalex.org/W3091233059","https://openalex.org/W6601607671","https://openalex.org/W6634647146","https://openalex.org/W6637356722","https://openalex.org/W6638532397","https://openalex.org/W6639025630"],"related_works":["https://openalex.org/W2555826082","https://openalex.org/W4288804802","https://openalex.org/W4293430534","https://openalex.org/W2335743642","https://openalex.org/W4297812927","https://openalex.org/W2800412005","https://openalex.org/W2172300487","https://openalex.org/W2154976966","https://openalex.org/W2216509856","https://openalex.org/W2624248631"],"abstract_inverted_index":{"The":[0,202],"evolution":[1],"of":[2,8,104,149,210],"Cyber-Physical":[3],"Systems":[4],"(CPSs)":[5],"and":[6,13,32,85,95,139,213],"Internet":[7],"Things":[9],"(IoTs)":[10],"enables":[11],"mobile":[12],"smart":[14],"embedded":[15,21],"devices":[16],"to":[17,43,74,81,89,113,126,164,189],"be":[18,72],"equipped":[19],"with":[20,47],"GPUs":[22,37,96,112],"for":[23,111],"accelerating":[24],"data-intensive":[25],"applications.":[26],"To":[27,145],"cut":[28],"down":[29],"device":[30],"prices":[31],"reduce":[33,177],"energy":[34],"consumption,":[35],"current":[36],"adopt":[38],"the":[39,49,58,62,66,75,82,98,102,109,116,121,132,136,140,147,150,168,172,178,195,198,214],"unified":[40,67],"memory":[41,45,68,154,161],"architecture":[42],"extend":[44],"size":[46],"using":[48],"PCIe":[50,117,141],"SSD":[51,118,142],"which":[52],"is":[53,143],"cheaper":[54],"than":[55],"directly":[56,114],"enlarging":[57],"off-chip":[59,83,137],"DRAM":[60,77,84,138,174],"on":[61,97,171],"GPU.":[63],"However,":[64],"adopting":[65],"architecture,":[69],"data":[70,128,179,191],"shall":[71],"moved":[73,80],"host":[76,99,122,173],"before":[78],"being":[79],"thus":[86],"it":[87,124],"leads":[88,125],"serious":[90],"contention":[91,169],"issues":[92,170],"among":[93],"CPUs":[94],"DRAM.":[100],"Although":[101],"advent":[103],"new":[105],"communication":[106],"technology":[107],"provides":[108],"opportunity":[110],"access":[115],"without":[119],"passing":[120],"DRAM,":[123],"high":[127],"movement":[129,180],"costs":[130],"because":[131],"latency":[133],"gap":[134],"between":[135],"large.":[144],"enhance":[146],"performance":[148],"low-cost":[151],"energy-efficient":[152],"GPU":[153],"systems,":[155],"this":[156],"work":[157],"advocates":[158],"a":[159,185,208],"hardware-controller-based":[160],"extension":[162],"solution":[163,204],"not":[165],"only":[166],"avoid":[167],"but":[175],"also":[176],"costs.":[181],"Particularly,":[182],"we":[183],"propose":[184],"scheduling-aware":[186],"prefetching":[187,192],"design":[188],"perform":[190],"by":[193,207],"utilizing":[194],"information":[196],"from":[197],"hardware":[199],"warp":[200],"scheduler.":[201],"proposed":[203],"was":[205],"evaluated":[206],"series":[209],"intensive":[211],"experiments":[212],"results":[215],"are":[216],"encouraging.":[217]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
