{"id":"https://openalex.org/W2915018956","doi":"https://doi.org/10.1109/pmbs.2018.8641666","title":"Is Data Placement Optimization Still Relevant on Newer GPUs?","display_name":"Is Data Placement Optimization Still Relevant on Newer GPUs?","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2915018956","doi":"https://doi.org/10.1109/pmbs.2018.8641666","mag":"2915018956"},"language":"en","primary_location":{"id":"doi:10.1109/pmbs.2018.8641666","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pmbs.2018.8641666","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/ACM Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS)","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/A5021828140","display_name":"Md Abdullah Shahneous Bari","orcid":null},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Md Abdullah Shahneous Bari","raw_affiliation_strings":["Stony Brook University, Stony Brook, NY, 11790, USA","Stony Brook University, Stony Brook, NY, US"],"affiliations":[{"raw_affiliation_string":"Stony Brook University, Stony Brook, NY, 11790, USA","institution_ids":["https://openalex.org/I59553526"]},{"raw_affiliation_string":"Stony Brook University, Stony Brook, NY, US","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025215862","display_name":"Larisa Stoltzfus","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Larisa Stoltzfus","raw_affiliation_strings":["University of Edinburgh, Edinburgh, UK","The University of Edinburgh, Edinburgh, Edinburgh, GB"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"The University of Edinburgh, Edinburgh, Edinburgh, GB","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035121838","display_name":"Pei\u2010Hung Lin","orcid":"https://orcid.org/0000-0003-4977-814X"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pei-Hung Lin","raw_affiliation_strings":["Lawrence Livermore National Laboratory, Livermore, CA, 94550, USA","Lawrence Livermore National Laboratory, Livermore, CA, US"],"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, CA, 94550, USA","institution_ids":["https://openalex.org/I1282311441"]},{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, CA, US","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034222191","display_name":"Chunhua Liao","orcid":"https://orcid.org/0000-0001-6477-0547"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chunhua Liao","raw_affiliation_strings":["Lawrence Livermore National Laboratory, Livermore, CA, 94550, USA","Lawrence Livermore National Laboratory, Livermore, CA, US"],"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, CA, 94550, USA","institution_ids":["https://openalex.org/I1282311441"]},{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, CA, US","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014448094","display_name":"Murali Emani","orcid":"https://orcid.org/0000-0002-6279-0007"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Murali Emani","raw_affiliation_strings":["Lawrence Livermore National Laboratory, Livermore, CA, 94550, USA","Lawrence Livermore National Laboratory, Livermore, CA, US"],"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, CA, 94550, USA","institution_ids":["https://openalex.org/I1282311441"]},{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, CA, US","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053733660","display_name":"Barbara Chapman","orcid":"https://orcid.org/0000-0001-8449-8579"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Barbara Chapman","raw_affiliation_strings":["Stony Brook University, Stony Brook, NY, 11790, USA","Stony Brook University, Stony Brook, NY, US"],"affiliations":[{"raw_affiliation_string":"Stony Brook University, Stony Brook, NY, 11790, USA","institution_ids":["https://openalex.org/I59553526"]},{"raw_affiliation_string":"Stony Brook University, Stony Brook, NY, US","institution_ids":["https://openalex.org/I59553526"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5021828140"],"corresponding_institution_ids":["https://openalex.org/I59553526"],"apc_list":null,"apc_paid":null,"fwci":1.5148,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.82877047,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"83","last_page":"96"},"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":0.9998000264167786,"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":0.9997000098228455,"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":0.8193241357803345},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5462372899055481},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3907593786716461}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8193241357803345},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5462372899055481},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3907593786716461}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/pmbs.2018.8641666","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pmbs.2018.8641666","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/ACM Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.9100000262260437,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G5811753289","display_name":null,"funder_award_id":"EP/M507258/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1604898313","https://openalex.org/W2117014006","https://openalex.org/W4233815414","https://openalex.org/W2372170743","https://openalex.org/W1491899005","https://openalex.org/W1558545464","https://openalex.org/W2172791042","https://openalex.org/W2074301136","https://openalex.org/W1997145140","https://openalex.org/W2034384303"],"abstract_inverted_index":{"Modern":[0],"supercomputers":[1],"often":[2],"use":[3],"Graphic":[4],"Processing":[5],"Units":[6],"(or":[7],"GPUs)":[8],"to":[9,99,137,161,166,171,173],"meet":[10],"the":[11,49,79,101],"evergrowing":[12],"demands":[13],"for":[14],"energy":[15],"efficient":[16],"high":[17],"performance":[18,63],"computing.":[19],"GPUs":[20,77,157],"have":[21,86],"a":[22,58,95,122,130],"complex":[23],"memory":[24,82,88,125,175],"architecture":[25],"with":[26],"various":[27],"types":[28],"of":[29,51,64,71,76,97,103,110,124,156],"memories":[30],"and":[31,41,85,117,129,146],"caches,":[32],"in":[33],"particular":[34],"global":[35,174],"memory,":[36,38,40],"shared":[37],"constant":[39],"texture":[42],"memory.":[43],"Data":[44],"placement":[45,50,105,148,163],"optimization,":[46],"i.e.":[47],"optimizing":[48],"data":[52,104,143,147,162],"among":[53],"these":[54],"different":[55,139],"memories,":[56],"has":[57],"significant":[59],"impact":[60],"on":[61,68,107],"Hie":[62],"HPC":[65],"applications":[66],"running":[67],"early":[69],"generations":[70,75,109,155],"GPUs.":[72],"However,":[73],"newer":[74,154],"implement":[78],"same":[80],"high-level":[81],"hierarchy":[83],"differently":[84],"new":[87],"features.":[89],"In":[90],"this":[91],"paper,":[92],"we":[93],"design":[94],"set":[96,123],"experiments":[98,120,134],"explore":[100],"relevance":[102],"optimizations":[106],"several":[108],"NVIDIA":[111],"GPUs,":[112],"including":[113],"Kepler,":[114],"Maxwell,":[115],"Pascal,":[116],"Volta.":[118],"Our":[119],"include":[121,138],"microbenchmarks,":[126],"CUDA":[127,140],"kernels":[128],"proxy":[131],"application.":[132],"The":[133,150],"are":[135,158],"configured":[136],"thread":[141],"blocks,":[142],"input":[144],"sizes,":[145],"choices.":[149],"results":[151],"show":[152],"that":[153],"less":[159],"sensitive":[160],"optimization":[164],"compared":[165],"older":[167],"ones,":[168],"mostly":[169],"due":[170],"improvements":[172],"caches.":[176]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}