{"id":"https://openalex.org/W2098290747","doi":"https://doi.org/10.1145/2749469.2750375","title":"Flexible software profiling of GPU architectures","display_name":"Flexible software profiling of GPU architectures","publication_year":2015,"publication_date":"2015-05-26","ids":{"openalex":"https://openalex.org/W2098290747","doi":"https://doi.org/10.1145/2749469.2750375","mag":"2098290747"},"language":"en","primary_location":{"id":"doi:10.1145/2749469.2750375","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2749469.2750375","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 42nd Annual International Symposium on Computer Architecture","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/A5015391591","display_name":"Mark W. Stephenson","orcid":"https://orcid.org/0000-0002-1350-0165"},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mark Stephenson","raw_affiliation_strings":["NVIDIA","Nvidia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]},{"raw_affiliation_string":"Nvidia","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054590774","display_name":"Siva Kumar Sastry Hari","orcid":"https://orcid.org/0000-0001-8346-7981"},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Siva Kumar Sastry Hari","raw_affiliation_strings":["NVIDIA","Nvidia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]},{"raw_affiliation_string":"Nvidia","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085686711","display_name":"Yunsup Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunsup Lee","raw_affiliation_strings":["University of California, Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089789557","display_name":"Eiman Ebrahimi","orcid":null},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Eiman Ebrahimi","raw_affiliation_strings":["NVIDIA","Nvidia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]},{"raw_affiliation_string":"Nvidia","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024222363","display_name":"Daniel Johnson","orcid":"https://orcid.org/0000-0003-1088-3460"},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Daniel R. Johnson","raw_affiliation_strings":["NVIDIA","Nvidia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]},{"raw_affiliation_string":"Nvidia","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031781240","display_name":"David Nellans","orcid":"https://orcid.org/0000-0001-5203-8367"},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"David Nellans","raw_affiliation_strings":["NVIDIA","Nvidia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]},{"raw_affiliation_string":"Nvidia","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055699570","display_name":"Mike O\u2019Connor","orcid":"https://orcid.org/0000-0003-0944-2393"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mike O'Connor","raw_affiliation_strings":["NVIDIA and The University of Texas at Austin","NVIDIA and The University of Texas at Austin#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA and The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"NVIDIA and The University of Texas at Austin#TAB#","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063354509","display_name":"Stephen W. Keckler","orcid":"https://orcid.org/0000-0001-6701-6099"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen W. Keckler","raw_affiliation_strings":["NVIDIA and The University of Texas at Austin","NVIDIA and The University of Texas at Austin#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA and The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"NVIDIA and The University of Texas at Austin#TAB#","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.8597,"has_fulltext":false,"cited_by_count":83,"citation_normalized_percentile":{"value":0.98946459,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"185","last_page":"197"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9995999932289124,"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":0.9994999766349792,"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":0.834985613822937},{"id":"https://openalex.org/keywords/instrumentation","display_name":"Instrumentation (computer programming)","score":0.748836874961853},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.7035800814628601},{"id":"https://openalex.org/keywords/debugging","display_name":"Debugging","score":0.5802565813064575},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4931947588920593},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4814009666442871},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.42880046367645264},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4108959436416626},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3788418769836426}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.834985613822937},{"id":"https://openalex.org/C118530786","wikidata":"https://www.wikidata.org/wiki/Q1134732","display_name":"Instrumentation (computer programming)","level":2,"score":0.748836874961853},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.7035800814628601},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.5802565813064575},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4931947588920593},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4814009666442871},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.42880046367645264},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4108959436416626},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3788418769836426},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2749469.2750375","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2749469.2750375","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 42nd Annual International Symposium on Computer Architecture","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W17142075","https://openalex.org/W1972663160","https://openalex.org/W1972971542","https://openalex.org/W1979527452","https://openalex.org/W1981473264","https://openalex.org/W1984222112","https://openalex.org/W1994270484","https://openalex.org/W1997162567","https://openalex.org/W2005961863","https://openalex.org/W2026213129","https://openalex.org/W2027716782","https://openalex.org/W2029577083","https://openalex.org/W2041330544","https://openalex.org/W2047226031","https://openalex.org/W2080592089","https://openalex.org/W2095954861","https://openalex.org/W2098040113","https://openalex.org/W2098505406","https://openalex.org/W2115157620","https://openalex.org/W2115824361","https://openalex.org/W2124007994","https://openalex.org/W2129663982","https://openalex.org/W2134633067","https://openalex.org/W2140384194","https://openalex.org/W2143798346","https://openalex.org/W2155943969","https://openalex.org/W2156831150","https://openalex.org/W2156858199","https://openalex.org/W2160610190","https://openalex.org/W2161522487","https://openalex.org/W2163935347","https://openalex.org/W2273440736","https://openalex.org/W4239813889","https://openalex.org/W4246906397","https://openalex.org/W4255365178"],"related_works":["https://openalex.org/W4321442002","https://openalex.org/W2015265939","https://openalex.org/W2284072287","https://openalex.org/W2611067230","https://openalex.org/W2480201319","https://openalex.org/W2387706296","https://openalex.org/W2155788121","https://openalex.org/W4235469518","https://openalex.org/W2059759476","https://openalex.org/W1618604010"],"abstract_inverted_index":{"To":[0,46],"aid":[1],"application":[2],"characterization":[3],"and":[4,10,24,43,64,124,173,190],"architecture":[5,176],"design":[6,177],"space":[7,178],"exploration,":[8],"researchers":[9],"engineers":[11],"have":[12,36],"developed":[13,37],"a":[14,91,105],"wide":[15],"range":[16],"of":[17,31,57,122,146,155,182],"tools":[18,39,49],"for":[19,96],"CPUs,":[20],"including":[21],"simulators,":[22],"profilers,":[23],"binary":[25,100],"instrumentation":[26,94,101,115,139],"tools.":[27],"With":[28],"the":[29,54,61,68,70,80,144,147,153,175,180],"advent":[30],"GPU":[32,34,127],"computing,":[33],"manufacturers":[35],"similar":[38],"leveraging":[40,143],"hardware":[41,136],"profiling":[42],"debugging":[44],"hooks.":[45],"date,":[47],"these":[48],"are":[50],"largely":[51],"limited":[52],"by":[53,60],"fixed":[55],"menu":[56],"options":[58],"provided":[59],"tool":[62,95],"developer":[63],"do":[65],"not":[66,78],"offer":[67],"user":[69,106],"flexibility":[71],"to":[72,107,112,130,152,170],"observe":[73],"or":[74],"act":[75],"on":[76],"events":[77],"in":[79],"menu.":[81],"This":[82],"paper":[83,158],"presents":[84],"SASSI":[85,103,138,166],"(NVIDIA":[86],"assembly":[87,128],"code":[88,125,129],"\"SASS\"":[89],"Instrumentor),":[90],"low-level":[92],"assembly-language":[93],"GPUs.":[97],"Like":[98],"CPU":[99],"tools,":[102],"allows":[104],"specify":[108],"instructions":[109],"at":[110,135],"which":[111],"inject":[113],"user-provided":[114],"code.":[116],"These":[117],"facilities":[118],"allow":[119],"strategic":[120],"placement":[121],"counters":[123],"into":[126],"collect":[131],"user-directed,":[132],"fine-grained":[133],"statistics":[134],"speeds.":[137],"is":[140],"inherently":[141],"parallel,":[142],"concurrency":[145],"underlying":[148],"hardware.":[149],"In":[150],"addition":[151],"details":[154],"SASSI,":[156],"this":[157],"provides":[159],"four":[160],"case":[161],"studies":[162],"that":[163],"show":[164],"how":[165],"can":[167],"be":[168],"used":[169],"characterize":[171],"applications":[172],"explore":[174],"along":[179],"dimensions":[181],"instruction":[183],"control":[184],"flow,":[185],"memory":[186],"systems,":[187],"value":[188],"similarity,":[189],"resilience.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":15},{"year":2017,"cited_by_count":14},{"year":2016,"cited_by_count":7}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
