{"id":"https://openalex.org/W4402056198","doi":"https://doi.org/10.1177/10943420241277839","title":"Refining HPCToolkit for application performance analysis at exascale","display_name":"Refining HPCToolkit for application performance analysis at exascale","publication_year":2024,"publication_date":"2024-08-30","ids":{"openalex":"https://openalex.org/W4402056198","doi":"https://doi.org/10.1177/10943420241277839"},"language":"en","primary_location":{"id":"doi:10.1177/10943420241277839","is_oa":true,"landing_page_url":"https://doi.org/10.1177/10943420241277839","pdf_url":"https://journals.sagepub.com/doi/pdf/10.1177/10943420241277839","source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://journals.sagepub.com/doi/pdf/10.1177/10943420241277839","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056557942","display_name":"Laksono Adhianto","orcid":"https://orcid.org/0000-0001-9637-0089"},"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":"Laksono Adhianto","raw_affiliation_strings":["Department of Computer Science, Rice University, Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rice University, Houston, TX, USA","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":true,"raw_author_name":"Jonathon Anderson","raw_affiliation_strings":["Department of Computer Science, Rice University, Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rice University, Houston, TX, USA","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055543893","display_name":"Robert Matthew Barnett","orcid":"https://orcid.org/0000-0003-2375-2988"},"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":"Robert Matthew Barnett","raw_affiliation_strings":["Department of Computer Science, Rice University, Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rice University, Houston, TX, USA","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106874009","display_name":"Dragana Grbic","orcid":"https://orcid.org/0009-0008-5786-755X"},"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":"Dragana Grbic","raw_affiliation_strings":["Department of Computer Science, Rice University, Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rice University, Houston, TX, USA","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025499412","display_name":"Vladimir In\u0111i\u0107","orcid":"https://orcid.org/0000-0003-0636-0501"},"institutions":[{"id":"https://openalex.org/I170726198","display_name":"University of Novi Sad","ror":"https://ror.org/00xa57a59","country_code":"RS","type":"education","lineage":["https://openalex.org/I170726198"]}],"countries":["RS"],"is_corresponding":false,"raw_author_name":"Vladimir Indic","raw_affiliation_strings":["Faculty of Technical Sciences, University of Novi Sad, Novi Sad, Serbia"],"affiliations":[{"raw_affiliation_string":"Faculty of Technical Sciences, University of Novi Sad, Novi Sad, Serbia","institution_ids":["https://openalex.org/I170726198"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011636515","display_name":"Mark W. Krentel","orcid":"https://orcid.org/0009-0008-2890-0920"},"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":"Mark Krentel","raw_affiliation_strings":["Department of Computer Science, Rice University, Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rice University, Houston, TX, USA","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100637928","display_name":"Yumeng Liu","orcid":null},"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":"Yumeng Liu","raw_affiliation_strings":["Department of Computer Science, Rice University, Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rice University, Houston, TX, USA","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084153657","display_name":"Sr\u0111an Milakovi\u0107","orcid":"https://orcid.org/0000-0002-6550-7115"},"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":"Sr\u0111an Milakovi\u0107","raw_affiliation_strings":["Department of Computer Science, Rice University, Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rice University, Houston, TX, USA","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106874010","display_name":"Wileam Phan","orcid":"https://orcid.org/0000-0001-5621-5949"},"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":"Wileam Phan","raw_affiliation_strings":["Department of Computer Science, Rice University, Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rice University, Houston, TX, USA","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":["Department of Computer Science, Rice University, Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rice University, Houston, TX, USA","institution_ids":["https://openalex.org/I74775410"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5075245108"],"corresponding_institution_ids":["https://openalex.org/I74775410"],"apc_list":null,"apc_paid":null,"fwci":1.9576,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.87368684,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"38","issue":"6","first_page":"612","last_page":"632"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9998000264167786,"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/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/terabyte","display_name":"Terabyte","score":0.9035671949386597},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8814507722854614},{"id":"https://openalex.org/keywords/exascale-computing","display_name":"Exascale computing","score":0.628088653087616},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.6071164608001709},{"id":"https://openalex.org/keywords/multithreading","display_name":"Multithreading","score":0.5198331475257874},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.5007503032684326},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.49486202001571655},{"id":"https://openalex.org/keywords/petascale-computing","display_name":"Petascale computing","score":0.47681161761283875},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4619292616844177},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.350420743227005},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.15922480821609497}],"concepts":[{"id":"https://openalex.org/C199683683","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Terabyte","level":2,"score":0.9035671949386597},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8814507722854614},{"id":"https://openalex.org/C2778837361","wikidata":"https://www.wikidata.org/wiki/Q2450880","display_name":"Exascale computing","level":3,"score":0.628088653087616},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.6071164608001709},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.5198331475257874},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.5007503032684326},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.49486202001571655},{"id":"https://openalex.org/C185410017","wikidata":"https://www.wikidata.org/wiki/Q7171778","display_name":"Petascale computing","level":3,"score":0.47681161761283875},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4619292616844177},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.350420743227005},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.15922480821609497}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1177/10943420241277839","is_oa":true,"landing_page_url":"https://doi.org/10.1177/10943420241277839","pdf_url":"https://journals.sagepub.com/doi/pdf/10.1177/10943420241277839","source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},{"id":"pmh:oai:osti.gov:2438631","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/2438631","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"doi:10.1177/10943420241277839","is_oa":true,"landing_page_url":"https://doi.org/10.1177/10943420241277839","pdf_url":"https://journals.sagepub.com/doi/pdf/10.1177/10943420241277839","source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.5600000023841858,"display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G2892156025","display_name":null,"funder_award_id":"B650752","funder_id":"https://openalex.org/F4320338286","funder_display_name":"Lawrence Livermore National Laboratory"},{"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/G4792039875","display_name":null,"funder_award_id":"B658833","funder_id":"https://openalex.org/F4320338286","funder_display_name":"Lawrence Livermore National Laboratory"},{"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"},{"id":"https://openalex.org/G7768399475","display_name":null,"funder_award_id":"B639429","funder_id":"https://openalex.org/F4320338286","funder_display_name":"Lawrence Livermore National Laboratory"},{"id":"https://openalex.org/G8253304997","display_name":null,"funder_award_id":"17-SC-20-SC","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"}],"funders":[{"id":"https://openalex.org/F4320307102","display_name":"Intel Corporation","ror":"https://ror.org/01ek73717"},{"id":"https://openalex.org/F4320307757","display_name":"Advanced Micro Devices","ror":"https://ror.org/04kd6c783"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320332369","display_name":"National Nuclear Security Administration","ror":"https://ror.org/03sk1we31"},{"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":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402056198.pdf"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W12500326","https://openalex.org/W1984222112","https://openalex.org/W1989137746","https://openalex.org/W2014780580","https://openalex.org/W2033787161","https://openalex.org/W2101939036","https://openalex.org/W2130055503","https://openalex.org/W2136434791","https://openalex.org/W2156371428","https://openalex.org/W2157692945","https://openalex.org/W2342249984","https://openalex.org/W2480131775","https://openalex.org/W2521473756","https://openalex.org/W2979340153","https://openalex.org/W2987414305","https://openalex.org/W2999812057","https://openalex.org/W3017260797","https://openalex.org/W3040626038","https://openalex.org/W3117551848","https://openalex.org/W3130699858","https://openalex.org/W3132094421","https://openalex.org/W3136358373","https://openalex.org/W3191672350","https://openalex.org/W3199133416","https://openalex.org/W3200843682","https://openalex.org/W3201073812","https://openalex.org/W4214707742","https://openalex.org/W4283835675","https://openalex.org/W4285200049","https://openalex.org/W4361197980","https://openalex.org/W4381573384","https://openalex.org/W4385623175","https://openalex.org/W4388581328"],"related_works":["https://openalex.org/W2021702679","https://openalex.org/W3038449658","https://openalex.org/W1525924016","https://openalex.org/W1582746211","https://openalex.org/W3129378740","https://openalex.org/W2607572736","https://openalex.org/W2266027327","https://openalex.org/W2249929881","https://openalex.org/W1569809235","https://openalex.org/W2278366184"],"abstract_inverted_index":{"As":[0],"part":[1,223],"of":[2,6,27,38,76,86,103,128,149,161,165,182,208,218,224,243],"the":[3,84],"US":[4],"Department":[5],"Energy\u2019s":[7],"Exascale":[8],"Computing":[9],"Project":[10],"(ECP),":[11],"Rice":[12],"University":[13],"has":[14,211],"been":[15,212],"refining":[16],"its":[17],"HPCToolkit":[18,41,72,111,154,174,244],"performance":[19,36,49,59,104,145,183],"tools":[20],"to":[21,47,63,90,131,143,175,214],"better":[22],"support":[23,125,203],"measurement":[24,205],"and":[25,54,68,79,97,119,159,163,179,194,206,241],"analysis":[26,75,122,207],"applications":[28,167,210,220],"executing":[29],"on":[30,198,229],"exascale":[31,88],"supercomputers.":[32],"To":[33,57,100,124],"efficiently":[34,176],"collect":[35],"measurements":[37,50,105],"GPU-accelerated":[39,166,209],"applications,":[40,239],"employs":[42,112],"novel":[43],"non-blocking":[44],"data":[45,117,184],"structures":[46],"communicate":[48],"between":[51,94],"tool":[52],"threads":[53],"application":[55,89],"threads.":[56],"attribute":[58],"information":[60],"in":[61,83,133,251],"detail":[62],"source":[64,98],"lines,":[65],"loop":[66],"nests,":[67],"inlined":[69],"call":[70],"chains,":[71],"performs":[73],"parallel":[74],"large":[77],"CPU":[78],"GPU":[80,196],"binaries":[81],"involved":[82],"execution":[85],"an":[87],"rapidly":[91],"recover":[92],"mappings":[93],"machine":[95],"instructions":[96],"code.":[99],"analyze":[101,178],"terabytes":[102,132,181],"gathered":[106],"during":[107],"executions":[108,186,252],"at":[109,168,253],"exascale,":[110],"distributed-memory":[113],"parallelism,":[114],"multithreading,":[115],"sparse":[116],"structures,":[118],"out-of-core":[120,141],"streaming":[121],"algorithms.":[123],"interactive":[126],"exploration":[127],"profiles":[129,162],"up":[130],"size,":[134],"HPCToolkit\u2019s":[135,202],"hpcviewer":[136],"graphical":[137],"user":[138],"interface":[139],"uses":[140],"methods":[142],"visualize":[144],"data.":[146],"The":[147],"result":[148],"these":[150,230],"efforts":[151],"is":[152],"that":[153],"now":[155],"supports":[156],"collection,":[157],"analysis,":[158],"presentation":[160],"traces":[164],"exascale.":[169,254],"These":[170],"improvements":[171],"have":[172],"enabled":[173],"measure,":[177],"explore":[180],"for":[185,204,237],"using":[187],"as":[188,190,222,246,248],"many":[189],"64K":[191,195],"MPI":[192],"ranks":[193],"tiles":[197],"ORNL\u2019s":[199],"Frontier":[200],"supercomputer.":[201],"employed":[213],"study":[215],"a":[216],"collection":[217],"open-science":[219],"developed":[221],"ECP.":[225],"This":[226],"paper":[227],"reports":[228],"experiences,":[231],"which":[232],"provided":[233],"insight":[234],"into":[235],"opportunities":[236],"tuning":[238],"strengths":[240],"weaknesses":[242],"itself,":[245],"well":[247],"unexpected":[249],"behaviors":[250]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
