{"id":"https://openalex.org/W2064677272","doi":"https://doi.org/10.1109/hipc.2012.6507475","title":"GMProf: A low-overhead, fine-grained profiling approach for GPU programs","display_name":"GMProf: A low-overhead, fine-grained profiling approach for GPU programs","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W2064677272","doi":"https://doi.org/10.1109/hipc.2012.6507475","mag":"2064677272"},"language":"en","primary_location":{"id":"doi:10.1109/hipc.2012.6507475","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipc.2012.6507475","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 19th International Conference on High Performance Computing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5004195454","display_name":"Mai Zheng","orcid":"https://orcid.org/0000-0002-0741-3436"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mai Zheng","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State University, Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086667064","display_name":"Vignesh T. Ravi","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vignesh T. Ravi","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State University, Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100695928","display_name":"Wenjing Ma","orcid":"https://orcid.org/0000-0002-1795-4498"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]},{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenjing Ma","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State University, Columbus, OH, USA","Pacific Northwest National Laboratory, Richland, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Pacific Northwest National Laboratory, Richland, WA, USA","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028781688","display_name":"Feng Qin","orcid":"https://orcid.org/0000-0001-9134-4711"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Feng Qin","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State University, Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025342178","display_name":"Gagan Agrawal","orcid":"https://orcid.org/0000-0002-2923-5327"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gagan Agrawal","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State University, Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3783,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.51966993,"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":"1","last_page":"10"},"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":0.9987999796867371,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9909999966621399,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.897121787071228},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.8388382792472839},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6338539123535156},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.6081041693687439},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5932148694992065},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.36566591262817383},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3598145842552185},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.32985028624534607},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.22391486167907715},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.103838711977005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.897121787071228},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.8388382792472839},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6338539123535156},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.6081041693687439},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5932148694992065},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.36566591262817383},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3598145842552185},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.32985028624534607},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.22391486167907715},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.103838711977005}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/hipc.2012.6507475","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipc.2012.6507475","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 19th International Conference on High Performance Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.297.9614","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.297.9614","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.ohio-state.edu/~qin/pub-papers/GMProf-HiPC12.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W123564486","https://openalex.org/W262335958","https://openalex.org/W1491178396","https://openalex.org/W1834380891","https://openalex.org/W1969399184","https://openalex.org/W2024717934","https://openalex.org/W2029891792","https://openalex.org/W2032404709","https://openalex.org/W2049381173","https://openalex.org/W2064677272","https://openalex.org/W2065773673","https://openalex.org/W2070122234","https://openalex.org/W2108418581","https://openalex.org/W2109900312","https://openalex.org/W2116963870","https://openalex.org/W2120062497","https://openalex.org/W2128329055","https://openalex.org/W2136434791","https://openalex.org/W2153131460","https://openalex.org/W2155479707","https://openalex.org/W2155528875","https://openalex.org/W2156858199","https://openalex.org/W2162528816","https://openalex.org/W2170634604","https://openalex.org/W2295862081","https://openalex.org/W4205854416","https://openalex.org/W4233973673","https://openalex.org/W4241057782","https://openalex.org/W4242340158","https://openalex.org/W4250981202","https://openalex.org/W4254296432","https://openalex.org/W4285719527","https://openalex.org/W6604995708","https://openalex.org/W6675809078"],"related_works":["https://openalex.org/W2120447654","https://openalex.org/W2977179488","https://openalex.org/W2144453115","https://openalex.org/W2128223750","https://openalex.org/W4238532390","https://openalex.org/W2188872161","https://openalex.org/W2961779879","https://openalex.org/W797688974","https://openalex.org/W2002978035","https://openalex.org/W2611230223"],"abstract_inverted_index":{"Driven":[0],"by":[1],"the":[2,5,96,121,133,216,230,240,250],"cost-effectiveness":[3],"and":[4,29,41,57,75,120,167,228],"power-efficiency,":[6],"GPUs":[7],"are":[8,51,164,175],"being":[9],"increasingly":[10],"used":[11],"to":[12,86,93,113,125,131],"accelerate":[13],"computations":[14],"in":[15,145,161,172],"many":[16],"domains.":[17],"However,":[18],"developing":[19],"highly":[20],"efficient":[21],"GPU":[22,36,110,185],"implementations":[23,255],"requires":[24],"a":[25,73,107,200,257],"lot":[26],"of":[27,98,109,135,141,215,243,259],"expertise":[28],"effort.":[30],"Thus,":[31],"tool":[32],"support":[33],"for":[34,46,81,208,213,229],"tuning":[35],"programs":[37],"is":[38,124,225],"urgently":[39],"needed,":[40],"more":[42],"specifically,":[43],"low-overhead":[44,74],"mechanisms":[45,58],"collecting":[47,99],"fine-grained":[48,76,100],"runtime":[49,136],"information":[50,117],"critically":[52],"required.":[53],"Unfortunately,":[54],"profiling":[55,77],"tools":[56],"available":[59],"today":[60],"either":[61],"collect":[62,114],"very":[63,118],"coarse-grained":[64],"information,":[65],"or":[66],"have":[67,179],"prohibitive":[68],"overheads.":[69],"This":[70],"paper":[71,147],"presents":[72],"technique":[78],"developed":[79],"specifically":[80],"GPUs,":[82],"which":[83,159,169],"we":[84,143,154],"refer":[85],"as":[87],"GMProf.":[88],"GMProf":[89,142,181,220],"uses":[90],"two":[91],"ideas":[92],"help":[94,155],"reduce":[95,132],"overheads":[97],"information.":[101],"The":[102,138,252],"first":[103],"idea":[104,123],"involves":[105],"exploiting":[106],"number":[108],"architectural":[111],"features":[112],"reasonably":[115],"accurate":[116],"efficiently,":[119],"second":[122],"use":[126,242],"simple":[127],"static":[128],"analysis":[129],"methods":[130],"overhead":[134],"profiling.":[137,211],"specific":[139],"implementation":[140],"report":[144],"this":[146],"focuses":[148],"on":[149,206,262],"shared":[150,162,209,223,244],"memory":[151,163,174,210,224],"usage.":[152],"Particularly,":[153],"programmers":[156],"understand":[157],"(1)":[158],"locations":[160],"infrequently":[165],"accessed?":[166,177],"(2)":[168],"data":[170],"elements":[171],"device":[173],"frequently":[176],"We":[178],"evaluated":[180,218],"using":[182],"six":[183,217],"popular":[184],"kernels":[186],"with":[187,196],"different":[188],"characteristics.":[189],"Our":[190],"experimental":[191],"results":[192],"show":[193],"that":[194,222],"GMProf,":[195],"all":[197],"optimizations,":[198],"incurs":[199],"moderate":[201],"overhead,":[202],"e.g.,":[203],"1.36":[204],"times":[205,261],"average":[207],"Furthermore,":[212],"three":[214,232],"kernels,":[219,233],"verified":[221],"effectively":[226],"used,":[227],"remaining":[231],"it":[234],"not":[235],"only":[236],"helped":[237,248],"accurately":[238],"identify":[239],"inefficient":[241],"memory,":[245],"but":[246],"also":[247],"tune":[249],"implementations.":[251],"resulting":[253],"tuned":[254],"had":[256],"speedup":[258],"15.18":[260],"average.":[263]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}