{"id":"https://openalex.org/W3040223855","doi":"https://doi.org/10.1145/3392717.3392759","title":"Identifying and (automatically) remedying performance problems in CPU/GPU applications","display_name":"Identifying and (automatically) remedying performance problems in CPU/GPU applications","publication_year":2020,"publication_date":"2020-06-29","ids":{"openalex":"https://openalex.org/W3040223855","doi":"https://doi.org/10.1145/3392717.3392759","mag":"3040223855"},"language":"en","primary_location":{"id":"doi:10.1145/3392717.3392759","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3392717.3392759","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3392717.3392759","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3392717.3392759","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000862743","display_name":"Benjamin Welton","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Benjamin Welton","raw_affiliation_strings":["University of Wisconsin - Madison"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin - Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010187794","display_name":"Barton P. Miller","orcid":"https://orcid.org/0000-0002-9435-8315"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Barton P. Miller","raw_affiliation_strings":["University of Wisconsin - Madison"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin - Madison","institution_ids":["https://openalex.org/I135310074"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5000862743"],"corresponding_institution_ids":["https://openalex.org/I135310074"],"apc_list":null,"apc_paid":null,"fwci":0.4715,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.59326096,"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":"13"},"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":0.9998000264167786,"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":0.9983999729156494,"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":0.8597332239151001},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.7630300521850586},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.7052793502807617},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.549996554851532},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5299970507621765},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.5025451183319092},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.5011203289031982},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.5000355243682861},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4649924337863922},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.44388455152511597},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4375265836715698},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.4135463237762451},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19281065464019775},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.14523619413375854},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08096140623092651}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8597332239151001},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.7630300521850586},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.7052793502807617},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.549996554851532},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5299970507621765},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.5025451183319092},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.5011203289031982},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.5000355243682861},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4649924337863922},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.44388455152511597},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4375265836715698},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.4135463237762451},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19281065464019775},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14523619413375854},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08096140623092651},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3392717.3392759","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3392717.3392759","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3392717.3392759","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3392717.3392759","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3392717.3392759","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3392717.3392759","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1645119126","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G1719536385","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G2296932962","display_name":null,"funder_award_id":"DE-AC05-00OR227","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G3299391273","display_name":null,"funder_award_id":"E-AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G4069127689","display_name":null,"funder_award_id":"4000151982","funder_id":"https://openalex.org/F4320338287","funder_display_name":"Oak Ridge National Laboratory"},{"id":"https://openalex.org/G4423657506","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320338287","funder_display_name":"Oak Ridge National Laboratory"},{"id":"https://openalex.org/G4544114593","display_name":null,"funder_award_id":"B617863","funder_id":"https://openalex.org/F4320338286","funder_display_name":"Lawrence Livermore National Laboratory"},{"id":"https://openalex.org/G5042132475","display_name":"SI2-SSI: Collaborative Research: A Sustainable Infrastructure for Performance, Security, and Correctness Tools","funder_award_id":"1449918","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6086734019","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320338286","funder_display_name":"Lawrence Livermore National Laboratory"},{"id":"https://openalex.org/G6495930337","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6891739399","display_name":null,"funder_award_id":"ACI-1449918","funder_id":"https://openalex.org/F4320315254","funder_display_name":"Innovative Research Group Project of the National Natural Science Foundation of China"},{"id":"https://openalex.org/G691578896","display_name":null,"funder_award_id":"DE-AC05-00OR2272","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G7114708214","display_name":null,"funder_award_id":"DE-AC05-00OR2272","funder_id":"https://openalex.org/F4320338287","funder_display_name":"Oak Ridge National Laboratory"},{"id":"https://openalex.org/G7995982022","display_name":null,"funder_award_id":"DE-AC05","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8414908677","display_name":null,"funder_award_id":"DE-AC0","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8799952057","display_name":null,"funder_award_id":"DE-AC05-00OR22","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8906985441","display_name":null,"funder_award_id":"00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320315254","display_name":"Innovative Research Group Project of the National Natural Science Foundation of China","ror":null},{"id":"https://openalex.org/F4320338286","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53"},{"id":"https://openalex.org/F4320338287","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3040223855.pdf","grobid_xml":"https://content.openalex.org/works/W3040223855.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W75999661","https://openalex.org/W77419049","https://openalex.org/W1515668834","https://openalex.org/W1515687962","https://openalex.org/W1545880915","https://openalex.org/W1615522416","https://openalex.org/W1969399184","https://openalex.org/W1977263182","https://openalex.org/W1987497701","https://openalex.org/W1990832096","https://openalex.org/W1992221070","https://openalex.org/W2002125998","https://openalex.org/W2030400507","https://openalex.org/W2042992924","https://openalex.org/W2084531306","https://openalex.org/W2094190665","https://openalex.org/W2100218206","https://openalex.org/W2100688122","https://openalex.org/W2116672403","https://openalex.org/W2122002474","https://openalex.org/W2126258136","https://openalex.org/W2136434791","https://openalex.org/W2147370410","https://openalex.org/W2157456548","https://openalex.org/W2158626113","https://openalex.org/W2160786443","https://openalex.org/W2219888463","https://openalex.org/W2290349115","https://openalex.org/W2293873148","https://openalex.org/W2856394295","https://openalex.org/W2883504296","https://openalex.org/W2885998509","https://openalex.org/W2941113209","https://openalex.org/W2952416601","https://openalex.org/W2983717258","https://openalex.org/W3137220996","https://openalex.org/W3162259881","https://openalex.org/W4235600583","https://openalex.org/W4238566657","https://openalex.org/W4239537162","https://openalex.org/W4248045917","https://openalex.org/W4251875201","https://openalex.org/W4392251494"],"related_works":["https://openalex.org/W2045183646","https://openalex.org/W2162409446","https://openalex.org/W2109463584","https://openalex.org/W2504075107","https://openalex.org/W2354058185","https://openalex.org/W3014500535","https://openalex.org/W2319812372","https://openalex.org/W1482096554","https://openalex.org/W2915501980","https://openalex.org/W2368611950"],"abstract_inverted_index":{"GPU":[0],"accelerators":[1],"have":[2],"become":[3],"common":[4],"on":[5],"today's":[6],"leadership-class":[7],"computing":[8],"platforms.":[9],"Effective":[10],"exploitation":[11],"of":[12,58,69,110,161],"the":[13,34,40,46,63,87,162],"additional":[14],"parallelism":[15],"offered":[16],"by":[17,28,37,99,116,123,131],"GPUs":[18],"is":[19,30,66],"fraught":[20],"with":[21],"challenges.":[22],"A":[23],"key":[24],"performance":[25,51,105,165],"challenge":[26],"faced":[27],"developers":[29],"how":[31],"to":[32,96,170],"limit":[33],"time":[35,189],"consumed":[36],"synchronizations":[38],"between":[39,190],"CPU":[41],"and":[42,89,127,144,152,167,172,192],"GPU.":[43],"We":[44,157],"introduce":[45],"extended":[47,103,136,163],"feed-forward":[48],"measurement":[49],"(FFM)":[50],"tool":[52,106,166],"that":[53,73,84],"provides":[54],"an":[55,78,159,183],"automated":[56],"detection":[57],"synchronization":[59,64,80],"problems,":[60],"identifies":[61,82,107],"if":[62],"problem":[65,76,114,121,129],"a":[67,70,75,113,117,120,128,132],"component":[68],"larger":[71,100],"construct":[72,143],"exhibits":[74],"beyond":[77],"individual":[79],"operation,":[81,119],"remedies":[83,95,140,148],"can":[85,145],"correct":[86,174],"issue,":[88],"in":[90,176,182,187],"some":[91],"cases":[92],"automatically":[93,146,173,184],"applies":[94],"problems":[97,175],"exhibited":[98],"constructs.":[101],"The":[102,135],"FFM":[104,137,164],"three":[108,177],"causes":[109],"unnecessary":[111],"synchronizations:":[112],"caused":[115,122,130],"single":[118],"memory":[124,133,150,153],"management":[125,151],"issues,":[126],"transfer.":[134],"model":[138],"prescribes":[139],"for":[141,149],"each":[142],"apply":[147],"transfer":[154],"cause":[155],"problems.":[156],"created":[158],"implementation":[160],"employed":[168],"it":[169],"identify":[171],"real-world":[178],"scientific":[179],"applications,":[180],"resulting":[181],"obtained":[185],"reduction":[186],"execution":[188],"9%":[191],"43%.":[193]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}
