{"id":"https://openalex.org/W2142769604","doi":"https://doi.org/10.1145/2145816.2145819","title":"A performance analysis framework for identifying potential benefits in GPGPU applications","display_name":"A performance analysis framework for identifying potential benefits in GPGPU applications","publication_year":2012,"publication_date":"2012-02-25","ids":{"openalex":"https://openalex.org/W2142769604","doi":"https://doi.org/10.1145/2145816.2145819","mag":"2142769604"},"language":"en","primary_location":{"id":"doi:10.1145/2145816.2145819","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2145816.2145819","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM SIGPLAN symposium on Principles and Practice of Parallel Programming","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/A5004251886","display_name":"Jaewoong Sim","orcid":"https://orcid.org/0000-0002-0403-9928"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jaewoong Sim","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA","Georgia Institute of Technology Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074348299","display_name":"Aniruddha Dasgupta","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aniruddha Dasgupta","raw_affiliation_strings":["Advanced Micro Devices, Austin, TX, USA"],"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Austin, TX, USA","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000822269","display_name":"Hyesoon Kim","orcid":"https://orcid.org/0000-0002-6061-7825"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hyesoon Kim","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA","Georgia Institute of Technology Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016738770","display_name":"Richard Vuduc","orcid":"https://orcid.org/0000-0003-2178-138X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard Vuduc","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA","Georgia Institute of Technology Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5004251886"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":21.9577,"has_fulltext":false,"cited_by_count":192,"citation_normalized_percentile":{"value":0.99764834,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"11","last_page":"22"},"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/T12127","display_name":"Software System Performance and Reliability","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/T10933","display_name":"Real-Time Systems Scheduling","score":0.996999979019165,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8643405437469482},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.8202242851257324},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.8094338774681091},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.6500152349472046},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.6021116375923157},{"id":"https://openalex.org/keywords/programmer","display_name":"Programmer","score":0.5927614569664001},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5392237305641174},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4384489357471466},{"id":"https://openalex.org/keywords/root-cause","display_name":"Root cause","score":0.4153003692626953},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.36405813694000244},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.20836228132247925},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16327562928199768},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.15518969297409058},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12552964687347412},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10478910803794861}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8643405437469482},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8202242851257324},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.8094338774681091},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.6500152349472046},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.6021116375923157},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.5927614569664001},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5392237305641174},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4384489357471466},{"id":"https://openalex.org/C84945661","wikidata":"https://www.wikidata.org/wiki/Q7366567","display_name":"Root cause","level":2,"score":0.4153003692626953},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.36405813694000244},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.20836228132247925},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16327562928199768},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.15518969297409058},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12552964687347412},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10478910803794861},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2145816.2145819","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2145816.2145819","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM SIGPLAN symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.226.3542","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.226.3542","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cis.udel.edu/%7Ecavazos/cisc879/papers/p11-sim.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1979527452","https://openalex.org/W1981896890","https://openalex.org/W1987588924","https://openalex.org/W2002555321","https://openalex.org/W2063774307","https://openalex.org/W2083206954","https://openalex.org/W2113282196","https://openalex.org/W2128046183","https://openalex.org/W2128539477","https://openalex.org/W2129232868","https://openalex.org/W2130336316","https://openalex.org/W2151195685","https://openalex.org/W2153492376","https://openalex.org/W2153667821","https://openalex.org/W2158261096","https://openalex.org/W2167334577"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2379153735","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W4382618745","https://openalex.org/W1973775000","https://openalex.org/W2748922771","https://openalex.org/W1987128138"],"abstract_inverted_index":{"Tuning":[0],"code":[1,140],"for":[2,43,136],"GPGPU":[3,44,50],"and":[4,68,74,118,128,141],"other":[5],"emerging":[6],"many-core":[7],"platforms":[8],"is":[9,76],"a":[10,31,47,64,137,157,164],"challenge":[11],"because":[12],"few":[13],"models":[14],"or":[15],"tools":[16,52],"can":[17,36,114,146],"precisely":[18,115],"pinpoint":[19],"the":[20,56,85,101,144,148],"root":[21,86],"cause":[22],"of":[23,49,55,66,88,159,166],"performance":[24,32,111,117,134,150],"bottlenecks.":[25],"In":[26,103],"this":[27],"paper,":[28],"we":[29,106,125],"present":[30],"analysis":[33],"framework":[34,155],"that":[35,113],"help":[37],"shed":[38],"light":[39],"on":[40,156],"such":[41],"bottlenecks":[42],"applications.":[45],"Although":[46],"handful":[48],"profiling":[51,130],"exist,":[53],"most":[54],"traditional":[57],"tools,":[58],"unfortunately,":[59],"simply":[60],"provide":[61,121],"programmers":[62],"with":[63],"variety":[65,165],"measurements":[67],"metrics":[69,82],"obtained":[70],"by":[71],"running":[72],"applications,":[73],"it":[75],"often":[77],"difficult":[78],"to":[79,83,97,99,120,131],"map":[80],"these":[81],"understand":[84],"causes":[87],"slowdowns,":[89],"much":[90],"less":[91],"decide":[92],"what":[93],"next":[94],"optimization":[95],"step":[96],"take":[98],"alleviate":[100],"bottleneck.":[102],"our":[104,133,154],"approach,":[105],"first":[107],"develop":[108],"an":[109],"analytical":[110],"model":[112,135,145],"predict":[116,147],"aims":[119],"programmer-interpretable":[122],"metrics.":[123],"Then,":[124],"apply":[126],"static":[127],"dynamic":[129],"instantiate":[132],"particular":[138],"input":[139],"show":[142],"how":[143],"potential":[149],"benefits.":[151],"We":[152],"demonstrate":[153],"suite":[158],"micro-benchmarks":[160],"as":[161,163],"well":[162],"computations":[167],"extracted":[168],"from":[169],"real":[170],"codes.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":20},{"year":2018,"cited_by_count":17},{"year":2017,"cited_by_count":22},{"year":2016,"cited_by_count":23},{"year":2015,"cited_by_count":16},{"year":2014,"cited_by_count":28},{"year":2013,"cited_by_count":21},{"year":2012,"cited_by_count":10}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}