{"id":"https://openalex.org/W4283024785","doi":"https://doi.org/10.1145/3524059.3532388","title":"Low overhead and context sensitive profiling of GPU-accelerated applications","display_name":"Low overhead and context sensitive profiling of GPU-accelerated applications","publication_year":2022,"publication_date":"2022-06-16","ids":{"openalex":"https://openalex.org/W4283024785","doi":"https://doi.org/10.1145/3524059.3532388"},"language":"en","primary_location":{"id":"doi:10.1145/3524059.3532388","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3524059.3532388","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 36th ACM International Conference on Supercomputing","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/A5063326523","display_name":"Keren Zhou","orcid":"https://orcid.org/0000-0002-7977-3182"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Keren Zhou","raw_affiliation_strings":["Rice University"],"affiliations":[{"raw_affiliation_string":"Rice University","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075245108","display_name":"Jonathon Anderson","orcid":"https://orcid.org/0000-0002-4506-2657"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathon Anderson","raw_affiliation_strings":["Rice University"],"affiliations":[{"raw_affiliation_string":"Rice University","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027198310","display_name":"Xiaozhu Meng","orcid":"https://orcid.org/0000-0003-3716-9072"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaozhu Meng","raw_affiliation_strings":["Rice University"],"affiliations":[{"raw_affiliation_string":"Rice University","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089709469","display_name":"John Mellor\u2010Crummey","orcid":"https://orcid.org/0000-0002-9026-5453"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Mellor-Crummey","raw_affiliation_strings":["Rice University"],"affiliations":[{"raw_affiliation_string":"Rice University","institution_ids":["https://openalex.org/I74775410"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5063326523"],"corresponding_institution_ids":["https://openalex.org/I74775410"],"apc_list":null,"apc_paid":null,"fwci":1.1353,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.75339661,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"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":0.9997000098228455,"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":0.9997000098228455,"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":0.9987000226974487,"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":0.9959999918937683,"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":0.891473650932312},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.7936223745346069},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5839143991470337},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5463157892227173},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5329189300537109},{"id":"https://openalex.org/keywords/context-switch","display_name":"Context switch","score":0.5182756781578064},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.5160293579101562},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4761352837085724},{"id":"https://openalex.org/keywords/critical-path-method","display_name":"Critical path method","score":0.4446031451225281},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4370194673538208},{"id":"https://openalex.org/keywords/gpu-cluster","display_name":"GPU cluster","score":0.42903009057044983},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4196361303329468},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.40739166736602783},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.34609007835388184},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.24192816019058228}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.891473650932312},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.7936223745346069},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5839143991470337},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5463157892227173},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5329189300537109},{"id":"https://openalex.org/C53833338","wikidata":"https://www.wikidata.org/wiki/Q1061424","display_name":"Context switch","level":2,"score":0.5182756781578064},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.5160293579101562},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4761352837085724},{"id":"https://openalex.org/C115874739","wikidata":"https://www.wikidata.org/wiki/Q825377","display_name":"Critical path method","level":2,"score":0.4446031451225281},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4370194673538208},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.42903009057044983},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4196361303329468},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.40739166736602783},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.34609007835388184},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.24192816019058228},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3524059.3532388","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3524059.3532388","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 36th ACM International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6899999976158142}],"awards":[{"id":"https://openalex.org/G3446422041","display_name":null,"funder_award_id":"B645220","funder_id":"https://openalex.org/F4320338286","funder_display_name":"Lawrence Livermore National Laboratory"},{"id":"https://openalex.org/G6859237865","display_name":null,"funder_award_id":"17-SC-20-SC","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G706472662","display_name":null,"funder_award_id":"9F-60073","funder_id":"https://openalex.org/F4320338284","funder_display_name":"Argonne National Laboratory"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320338284","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63"},{"id":"https://openalex.org/F4320338286","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1902930330","https://openalex.org/W1961751213","https://openalex.org/W2019465613","https://openalex.org/W2020009542","https://openalex.org/W2049440937","https://openalex.org/W2064644032","https://openalex.org/W2067673417","https://openalex.org/W2073727874","https://openalex.org/W2078794610","https://openalex.org/W2090943890","https://openalex.org/W2136269217","https://openalex.org/W2194775991","https://openalex.org/W2302787158","https://openalex.org/W2506485539","https://openalex.org/W2563277009","https://openalex.org/W2944412207","https://openalex.org/W2979340153","https://openalex.org/W2979878940","https://openalex.org/W2983717258","https://openalex.org/W2999812057","https://openalex.org/W3012871709","https://openalex.org/W3040626038","https://openalex.org/W3046751266","https://openalex.org/W3104308872","https://openalex.org/W3132094421","https://openalex.org/W3199133416","https://openalex.org/W3200843682","https://openalex.org/W3201201825","https://openalex.org/W4200503332","https://openalex.org/W4238089251","https://openalex.org/W4248649658","https://openalex.org/W4253782958","https://openalex.org/W4255185178","https://openalex.org/W6713134421"],"related_works":["https://openalex.org/W2151046618","https://openalex.org/W1972148443","https://openalex.org/W1969233021","https://openalex.org/W2167646277","https://openalex.org/W2063573318","https://openalex.org/W2388314963","https://openalex.org/W3158047141","https://openalex.org/W1656096860","https://openalex.org/W2027443981","https://openalex.org/W2375309128"],"abstract_inverted_index":{"As":[0],"we":[1,112],"near":[2],"the":[3,9,25,46,110,168,173,201,208,221],"end":[4],"of":[5,49,213,226,236],"Moore's":[6],"law":[7],"scaling,":[8],"next-generation":[10],"computing":[11],"platforms":[12],"are":[13,24,32],"increasingly":[14],"exploring":[15],"heterogeneous":[16],"processors":[17],"for":[18,41,64,143,210,223],"acceleration.":[19],"Graphics":[20],"Processing":[21],"Units":[22],"(GPUs)":[23],"most":[26],"widely":[27],"used":[28],"accelerators.":[29],"Meanwhile,":[30],"applications":[31,190],"evolving":[33],"by":[34],"adopting":[35],"new":[36],"programming":[37],"models":[38],"and":[39,59,73,79,100,120,127,171,187,220,238],"algorithms":[40],"emerging":[42],"platforms.":[43],"To":[44,75,108],"harness":[45],"full":[47,105],"power":[48],"GPUs,":[50],"performance":[51,82,87,94,102],"tools":[52,83,95],"serve":[53],"a":[54,114,192],"critical":[55],"role":[56],"in":[57,240],"understanding":[58],"tuning":[60],"application":[61],"performance,":[62],"especially":[63],"those":[65],"that":[66,116],"involve":[67],"complex":[68],"executions":[69],"spanning":[70],"both":[71,118],"CPU":[72,119],"GPU.":[74,198],"help":[76],"developers":[77],"analyze":[78],"tune":[80],"applications,":[81],"need":[84],"to":[85,104,161,166,218,231],"associate":[86],"metrics":[88,103],"with":[89,124,146,195,200,233],"calling":[90,106,122,151,174],"contexts.":[91,107],"However,":[92],"existing":[93],"incur":[96],"high":[97,128],"overhead":[98,126,209,222],"collecting":[99],"attributing":[101],"address":[109],"problem,":[111],"developed":[113],"tool":[115,138,154,183,206],"constructs":[117],"GPU":[121,144,150,163,203,214,227],"contexts":[123,175],"low":[125],"accuracy.":[129],"With":[130],"an":[131,156,196,234],"innovative":[132],"call":[133,141],"path":[134],"memoization":[135],"mechanism,":[136],"our":[137,153,182,205],"can":[139],"obtain":[140],"paths":[142],"operations":[145,215],"negligible":[147],"cost.":[148],"For":[149],"contexts,":[152],"uses":[155],"adaptive":[157],"epoch":[158],"profiling":[159,212,225],"method":[160],"collect":[162],"instruction":[164],"samples":[165],"reduce":[167],"synchronization":[169],"cost":[170],"reconstruct":[172],"using":[176],"postmortem":[177],"analysis.":[178],"We":[179],"have":[180],"evaluated":[181],"on":[184,191],"nine":[185],"HPC":[186],"machine":[188,193],"learning":[189],"equipped":[194],"NVIDIA":[197],"Compared":[199],"state-of-the-art":[202],"profilers,":[204],"reduces":[207],"coarse-grained":[211],"from":[216,229],"2.07X":[217],"1.42X":[219],"fine-grained":[224],"instructions":[228],"27.51X":[230],"4.61X":[232],"accuracy":[235],"99.93%":[237],"96.16%":[239],"each":[241],"mode.":[242]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-02-25T08:12:03.925757","created_date":"2025-10-10T00:00:00"}