{"id":"https://openalex.org/W4361197980","doi":"https://doi.org/10.1145/3578244.3583736","title":"DrGPU: A Top-Down Profiler for GPU Applications","display_name":"DrGPU: A Top-Down Profiler for GPU Applications","publication_year":2023,"publication_date":"2023-03-29","ids":{"openalex":"https://openalex.org/W4361197980","doi":"https://doi.org/10.1145/3578244.3583736"},"language":"en","primary_location":{"id":"doi:10.1145/3578244.3583736","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3578244.3583736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM/SPEC International Conference on Performance Engineering","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/A5015357791","display_name":"Yueming Hao","orcid":"https://orcid.org/0000-0002-4792-6244"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yueming Hao","raw_affiliation_strings":["North Carolina State University, Raleigh, NC, USA"],"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC, USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025115023","display_name":"Nikhil Jain","orcid":"https://orcid.org/0009-0002-1555-9125"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nikhil Jain","raw_affiliation_strings":["Nvidia Corporation, Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"Nvidia Corporation, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066479345","display_name":"Rob Van der Wijngaart","orcid":"https://orcid.org/0009-0008-4609-6403"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rob Van der Wijngaart","raw_affiliation_strings":["Nvidia Corporation, Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"Nvidia Corporation, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058543385","display_name":"N.R. Saxena","orcid":"https://orcid.org/0009-0001-1248-0721"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nirmal Saxena","raw_affiliation_strings":["Nvidia Corporation, Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"Nvidia Corporation, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028651607","display_name":"Yuanbo Fan","orcid":"https://orcid.org/0000-0001-6123-006X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuanbo Fan","raw_affiliation_strings":["Tenstorrent Incorporated, San Francisco, CA, USA"],"affiliations":[{"raw_affiliation_string":"Tenstorrent Incorporated, San Francisco, CA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013392225","display_name":"Xu Liu","orcid":"https://orcid.org/0000-0002-1487-963X"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xu Liu","raw_affiliation_strings":["North Carolina State University, Raleigh, NC, USA"],"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC, USA","institution_ids":["https://openalex.org/I137902535"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5015357791"],"corresponding_institution_ids":["https://openalex.org/I137902535"],"apc_list":null,"apc_paid":null,"fwci":4.5375,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.95473377,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"43","last_page":"53"},"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":0.9991999864578247,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8639665246009827},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.6072515845298767},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5210170745849609},{"id":"https://openalex.org/keywords/program-optimization","display_name":"Program optimization","score":0.4638604521751404},{"id":"https://openalex.org/keywords/root-cause","display_name":"Root cause","score":0.43394190073013306},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4143562912940979},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.410905659198761},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.34528958797454834},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20837834477424622},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.19176256656646729}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8639665246009827},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.6072515845298767},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5210170745849609},{"id":"https://openalex.org/C139571649","wikidata":"https://www.wikidata.org/wiki/Q1156793","display_name":"Program optimization","level":3,"score":0.4638604521751404},{"id":"https://openalex.org/C84945661","wikidata":"https://www.wikidata.org/wiki/Q7366567","display_name":"Root cause","level":2,"score":0.43394190073013306},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4143562912940979},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.410905659198761},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.34528958797454834},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20837834477424622},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.19176256656646729},{"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},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3578244.3583736","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3578244.3583736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G2643413432","display_name":null,"funder_award_id":"2125813, 2050007","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1483717008","https://openalex.org/W2011324636","https://openalex.org/W2120230074","https://openalex.org/W2128046183","https://openalex.org/W2136434791","https://openalex.org/W2292282166","https://openalex.org/W2479763664","https://openalex.org/W2789572737","https://openalex.org/W2979340153","https://openalex.org/W3008227512","https://openalex.org/W3040626038","https://openalex.org/W3136358373","https://openalex.org/W3195186037"],"related_works":["https://openalex.org/W2329500892","https://openalex.org/W28991112","https://openalex.org/W2370726991","https://openalex.org/W2369710579","https://openalex.org/W2545348020","https://openalex.org/W4327728159","https://openalex.org/W2912751582","https://openalex.org/W2130893381","https://openalex.org/W3013131386","https://openalex.org/W582278231"],"abstract_inverted_index":{"GPUs":[0,103],"have":[1],"become":[2],"common":[3],"in":[4,36,101],"HPC":[5],"systems":[6],"to":[7,19,51,67,86,104,130,143],"accelerate":[8],"scientific":[9],"computing":[10],"and":[11,61,117,135,137,147],"machine":[12],"learning":[13],"applications.":[14],"Efficiently":[15],"mapping":[16],"these":[17,53],"applications":[18,41,136],"rapid":[20],"evolutions":[21],"of":[22,125],"GPU":[23,37,88,133],"architectures":[24],"for":[25,72],"high":[26],"performance":[27,33,98],"is":[28],"a":[29,79],"well-known":[30],"challenge.":[31],"Various":[32],"inefficiencies":[34],"exist":[35],"kernels":[38],"that":[39,82],"impede":[40],"from":[42],"obtaining":[43],"bare-metal":[44],"performance.":[45],"While":[46],"existing":[47],"tools":[48],"are":[49,128],"able":[50,129],"measure":[52],"inefficiencies,":[54],"they":[55],"mostly":[56],"focus":[57],"on":[58,145,149],"data":[59],"collection":[60],"presentation,":[62],"requiring":[63],"significant":[64],"manual":[65],"efforts":[66],"understand":[68],"the":[69,123],"root":[70,115],"causes":[71],"actionable":[73],"optimization.":[74,90],"Thus,":[75],"we":[76,127],"develop":[77],"DrGPU,":[78,126],"novel":[80],"profiler":[81],"performs":[83],"top-down":[84],"analysis":[85],"guide":[87],"code":[89],"As":[91],"its":[92],"salient":[93],"feature,":[94],"DrGPU":[95],"leverages":[96],"hardware":[97],"counters":[99],"available":[100],"commodity":[102],"quantify":[105],"stall":[106,112],"cycles,":[107],"decompose":[108],"them":[109],"into":[110],"various":[111],"reasons,":[113],"pinpoint":[114],"causes,":[116],"provide":[118],"intuitive":[119],"optimization":[120],"guidance.":[121],"With":[122],"help":[124],"analyze":[131],"important":[132],"benchmarks":[134],"obtain":[138],"nontrivial":[139],"speedups":[140],"---":[141],"up":[142],"1.77X":[144],"V100":[146],"2.03X":[148],"GTX":[150],"1650.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
