{"id":"https://openalex.org/W2807022070","doi":"https://doi.org/10.1109/tpds.2018.2840992","title":"LWPTool: A Lightweight Profiler to Guide Data Layout Optimization","display_name":"LWPTool: A Lightweight Profiler to Guide Data Layout Optimization","publication_year":2018,"publication_date":"2018-05-28","ids":{"openalex":"https://openalex.org/W2807022070","doi":"https://doi.org/10.1109/tpds.2018.2840992","mag":"2807022070"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2018.2840992","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2018.2840992","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-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/A5101920789","display_name":"Chao Yu","orcid":"https://orcid.org/0000-0002-2602-9798"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chao Yu","raw_affiliation_strings":["Beihang University, Beijing, CN"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, CN","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036385652","display_name":"Probir Roy","orcid":"https://orcid.org/0000-0001-8877-0787"},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]},{"id":"https://openalex.org/I267592682","display_name":"Williams (United States)","ror":"https://ror.org/007zhvp17","country_code":"US","type":"company","lineage":["https://openalex.org/I267592682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Probir Roy","raw_affiliation_strings":["College of William and Mary, Williamsburg, VA, US"],"affiliations":[{"raw_affiliation_string":"College of William and Mary, Williamsburg, VA, US","institution_ids":["https://openalex.org/I16285277","https://openalex.org/I267592682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101593745","display_name":"Yuebin Bai","orcid":"https://orcid.org/0000-0002-2544-3989"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuebin Bai","raw_affiliation_strings":["Beihang University, Beijing, CN"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, CN","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018705589","display_name":"Hailong Yang","orcid":"https://orcid.org/0000-0003-1101-7927"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hailong Yang","raw_affiliation_strings":["Beihang University, Beijing, CN"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, CN","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100331713","display_name":"Xu Liu","orcid":"https://orcid.org/0000-0002-8984-5485"},"institutions":[{"id":"https://openalex.org/I267592682","display_name":"Williams (United States)","ror":"https://ror.org/007zhvp17","country_code":"US","type":"company","lineage":["https://openalex.org/I267592682"]},{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xu Liu","raw_affiliation_strings":["College of William and Mary, Williamsburg, VA, US"],"affiliations":[{"raw_affiliation_string":"College of William and Mary, Williamsburg, VA, US","institution_ids":["https://openalex.org/I16285277","https://openalex.org/I267592682"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101920789"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":1.2623,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.78061599,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"29","issue":"11","first_page":"2489","last_page":"2502"},"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":0.9997000098228455,"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"}},{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9941999912261963,"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/computer-science","display_name":"Computer science","score":0.9118131399154663},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.6408369541168213},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.5973713994026184},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.575046956539154},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5704343914985657},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.5608115196228027},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5443524718284607},{"id":"https://openalex.org/keywords/executable","display_name":"Executable","score":0.503030002117157},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.4876440763473511},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4770702123641968},{"id":"https://openalex.org/keywords/data-access","display_name":"Data access","score":0.4626738727092743},{"id":"https://openalex.org/keywords/non-uniform-memory-access","display_name":"Non-uniform memory access","score":0.430886447429657},{"id":"https://openalex.org/keywords/flat-memory-model","display_name":"Flat memory model","score":0.3825110197067261},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.36150169372558594},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.3481314182281494},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.322505384683609},{"id":"https://openalex.org/keywords/overlay","display_name":"Overlay","score":0.29976940155029297},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.264375239610672},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.21639326214790344},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.13931065797805786}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9118131399154663},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.6408369541168213},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.5973713994026184},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.575046956539154},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5704343914985657},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.5608115196228027},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5443524718284607},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.503030002117157},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.4876440763473511},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4770702123641968},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.4626738727092743},{"id":"https://openalex.org/C133371097","wikidata":"https://www.wikidata.org/wiki/Q868014","display_name":"Non-uniform memory access","level":5,"score":0.430886447429657},{"id":"https://openalex.org/C57863822","wikidata":"https://www.wikidata.org/wiki/Q905488","display_name":"Flat memory model","level":4,"score":0.3825110197067261},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.36150169372558594},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.3481314182281494},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.322505384683609},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.29976940155029297},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.264375239610672},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.21639326214790344},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.13931065797805786},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2018.2840992","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2018.2840992","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4018218200","display_name":null,"funder_award_id":"2016YFB1000503","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G4779907915","display_name":null,"funder_award_id":"61502019","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8010902239","display_name":null,"funder_award_id":"1464157","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8351171912","display_name":null,"funder_award_id":"61572062","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1518474679","https://openalex.org/W1539430313","https://openalex.org/W1810689312","https://openalex.org/W1842336537","https://openalex.org/W1963963558","https://openalex.org/W1968797199","https://openalex.org/W1971578705","https://openalex.org/W1984005572","https://openalex.org/W1991707635","https://openalex.org/W2018052702","https://openalex.org/W2024362434","https://openalex.org/W2027038566","https://openalex.org/W2030058342","https://openalex.org/W2063364927","https://openalex.org/W2067471095","https://openalex.org/W2068424089","https://openalex.org/W2068810256","https://openalex.org/W2080046548","https://openalex.org/W2080592089","https://openalex.org/W2082318969","https://openalex.org/W2086663426","https://openalex.org/W2101462267","https://openalex.org/W2105506259","https://openalex.org/W2111367353","https://openalex.org/W2122858224","https://openalex.org/W2129305676","https://openalex.org/W2132260309","https://openalex.org/W2132511032","https://openalex.org/W2137702271","https://openalex.org/W2139165932","https://openalex.org/W2141170493","https://openalex.org/W2144038733","https://openalex.org/W2160468841","https://openalex.org/W2168900306","https://openalex.org/W2170088834","https://openalex.org/W2171034968","https://openalex.org/W2171392117","https://openalex.org/W2415142660","https://openalex.org/W2759488747","https://openalex.org/W3009653888","https://openalex.org/W3041169337","https://openalex.org/W4240326407","https://openalex.org/W4250066315","https://openalex.org/W6630920759","https://openalex.org/W6632220093","https://openalex.org/W6638329847","https://openalex.org/W6716039864","https://openalex.org/W6744167158"],"related_works":["https://openalex.org/W1500809736","https://openalex.org/W254684032","https://openalex.org/W1531802798","https://openalex.org/W1971683480","https://openalex.org/W2570594754","https://openalex.org/W1979384060","https://openalex.org/W4281924108","https://openalex.org/W2531213384","https://openalex.org/W1655459528","https://openalex.org/W2934889147"],"abstract_inverted_index":{"Memory":[0],"access":[1,120,141],"latency":[2],"continues":[3],"to":[4,25,82,103,117,122,187,197],"be":[5],"a":[6,10,80,112],"dominant":[7],"bottleneck":[8],"in":[9,29],"large":[11],"class":[12],"of":[13,66,114,182],"applications":[14],"on":[15,146,151,199],"modern":[16],"architectures.":[17],"To":[18,73,169],"optimize":[19],"memory":[20,31,39,60,107,119,140],"performance,":[21],"it":[22,98],"is":[23,53,195],"important":[24],"utilize":[26],"the":[27,30,64,180,193],"locality":[28],"hierarchy.":[32],"Data":[33],"layout":[34,51,90,125],"optimization":[35,52],"can":[36],"significantly":[37,188],"improve":[38,189],"locality.":[40],"However,":[41],"pinpointing":[42],"inefficient":[43],"code":[44],"and":[45,105,161,176],"providing":[46],"insightful":[47],"guidance":[48,181],"for":[49,69],"data":[50,89,124],"challenging.":[54],"Existing":[55],"tools":[56,68],"typically":[57],"leverage":[58],"heavyweight":[59],"instrumentations,":[61],"which":[62],"hinders":[63],"applicability":[65],"these":[67,191],"real":[70],"long-running":[71],"programs.":[72],"address":[74,101],"this":[75],"issue,":[76],"we":[77,172,184],"develop":[78],"LWPTool,":[79,171,183],"profiler":[81],"pinpoint":[83],"top":[84],"candidates":[85],"that":[86,131],"benefit":[87],"from":[88,158],"optimization.":[91,126],"LWPTool":[92,110,144,149],"makes":[93],"three":[94],"unique":[95],"contributions.":[96],"First,":[97],"adopts":[99],"lightweight":[100],"sampling":[102],"collect":[104],"analyze":[106],"traces.":[108],"Second,":[109],"employs":[111],"set":[113],"novel":[115],"methods":[116],"determine":[118],"patterns":[121],"guide":[123],"We":[127],"also":[128],"formally":[129],"prove":[130],"our":[132],"method":[133],"has":[134],"high":[135],"accuracy":[136],"even":[137],"with":[138],"sparse":[139],"samples.":[142],"Third,":[143],"scales":[145],"multithreaded":[147],"machines.":[148],"works":[150],"fully":[152],"optimized,":[153],"unmodified":[154],"binary":[155],"executables":[156],"independently":[157],"their":[159],"compiler":[160],"language,":[162],"incurring":[163],"around":[164],"6.2":[165],"percent":[166],"runtime":[167],"overhead.":[168],"evaluate":[170],"study":[173],"ten":[174],"sequential":[175],"parallel":[177],"benchmarks.":[178],"With":[179],"are":[185],"able":[186],"all":[190],"benchmarks;":[192],"speedup":[194],"up":[196],"1.39\u00d7":[198],"average.":[200]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}