{"id":"https://openalex.org/W3037894007","doi":"https://doi.org/10.1007/s42514-020-00035-8","title":"APMT: an automatic hardware counter-based performance modeling tool for HPC applications","display_name":"APMT: an automatic hardware counter-based performance modeling tool for HPC applications","publication_year":2020,"publication_date":"2020-06-01","ids":{"openalex":"https://openalex.org/W3037894007","doi":"https://doi.org/10.1007/s42514-020-00035-8","mag":"3037894007"},"language":"en","primary_location":{"id":"doi:10.1007/s42514-020-00035-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s42514-020-00035-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s42514-020-00035-8.pdf","source":{"id":"https://openalex.org/S4210190911","display_name":"CCF Transactions on High Performance Computing","issn_l":"2524-4922","issn":["2524-4922","2524-4930"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"CCF Transactions on High Performance Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s42514-020-00035-8.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011195132","display_name":"Nan Ding","orcid":"https://orcid.org/0000-0001-9624-9449"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Nan Ding","raw_affiliation_strings":["Computational Research Division, Lawrence Berkeley National Laboratory, Berkeley, CA, 94720, USA","Department of Computer Science and Technology, Tsinghua University, Beijing, 100084, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Research Division, Lawrence Berkeley National Laboratory, Berkeley, CA, 94720, USA","institution_ids":["https://openalex.org/I148283060"]},{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, 100084, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109971580","display_name":"Victor W. Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Victor W. Lee","raw_affiliation_strings":["Intel Corporation, Santa Clara, CA, 95054, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Corporation, Santa Clara, CA, 95054, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091437474","display_name":"Wei Xue","orcid":"https://orcid.org/0000-0001-9740-6581"},"institutions":[{"id":"https://openalex.org/I4210158984","display_name":"National Supercomputing Center in Wuxi","ror":"https://ror.org/04ypjrs34","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210158984"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Xue","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, 100084, China","National Supercomputing Center in Wuxi, Wuxi, 214000, China"],"raw_orcid":"https://orcid.org/0000-0001-9740-6581","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, 100084, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"National Supercomputing Center in Wuxi, Wuxi, 214000, China","institution_ids":["https://openalex.org/I4210158984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108050911","display_name":"Weimin Zheng","orcid":"https://orcid.org/0000-0002-4450-5428"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weimin Zheng","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, 100084, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, 100084, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2190,"currency":"EUR","value_usd":2790},"apc_paid":{"value":2190,"currency":"EUR","value_usd":2790},"fwci":0.4721,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.59135089,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"2","issue":"2","first_page":"135","last_page":"148"},"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/T12127","display_name":"Software System Performance and Reliability","score":0.9984999895095825,"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":0.9983000159263611,"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":0.7756670713424683},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.703581690788269},{"id":"https://openalex.org/keywords/performance-metric","display_name":"Performance metric","score":0.5177092552185059},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.5050347447395325},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4612419009208679},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4467049539089203},{"id":"https://openalex.org/keywords/performance-prediction","display_name":"Performance prediction","score":0.4204919934272766},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4128704071044922},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.2695005536079407},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.2086668312549591},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.18781358003616333},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09405246376991272}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7756670713424683},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.703581690788269},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.5177092552185059},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.5050347447395325},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4612419009208679},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4467049539089203},{"id":"https://openalex.org/C2777115002","wikidata":"https://www.wikidata.org/wiki/Q7168246","display_name":"Performance prediction","level":2,"score":0.4204919934272766},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4128704071044922},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2695005536079407},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.2086668312549591},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.18781358003616333},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09405246376991272},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s42514-020-00035-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s42514-020-00035-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s42514-020-00035-8.pdf","source":{"id":"https://openalex.org/S4210190911","display_name":"CCF Transactions on High Performance Computing","issn_l":"2524-4922","issn":["2524-4922","2524-4930"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"CCF Transactions on High Performance Computing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s42514-020-00035-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s42514-020-00035-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s42514-020-00035-8.pdf","source":{"id":"https://openalex.org/S4210190911","display_name":"CCF Transactions on High Performance Computing","issn_l":"2524-4922","issn":["2524-4922","2524-4930"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"CCF Transactions on High Performance Computing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","score":0.44999998807907104,"display_name":"Climate action"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320328788","display_name":"Polit National Laboratory for Marine Science and Technology","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W3037894007.pdf"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W1532687722","https://openalex.org/W1545299942","https://openalex.org/W1545880915","https://openalex.org/W1602306860","https://openalex.org/W1644620247","https://openalex.org/W1906219896","https://openalex.org/W1961751213","https://openalex.org/W1966695753","https://openalex.org/W1968244180","https://openalex.org/W1989146297","https://openalex.org/W2002555321","https://openalex.org/W2004618765","https://openalex.org/W2010714123","https://openalex.org/W2021384817","https://openalex.org/W2025983224","https://openalex.org/W2030553163","https://openalex.org/W2038769854","https://openalex.org/W2052801483","https://openalex.org/W2075244932","https://openalex.org/W2076514761","https://openalex.org/W2089320150","https://openalex.org/W2101778912","https://openalex.org/W2107158148","https://openalex.org/W2108177987","https://openalex.org/W2112121929","https://openalex.org/W2114458082","https://openalex.org/W2115920894","https://openalex.org/W2121082877","https://openalex.org/W2124695036","https://openalex.org/W2125955291","https://openalex.org/W2127900800","https://openalex.org/W2145705994","https://openalex.org/W2146438362","https://openalex.org/W2146451581","https://openalex.org/W2146710186","https://openalex.org/W2152419477","https://openalex.org/W2161973644","https://openalex.org/W2167334577","https://openalex.org/W2276621164","https://openalex.org/W2293735149","https://openalex.org/W2465756754","https://openalex.org/W2503956315","https://openalex.org/W2767224631","https://openalex.org/W2997701623","https://openalex.org/W3103104567","https://openalex.org/W4231947996","https://openalex.org/W4240916550","https://openalex.org/W4252521241","https://openalex.org/W4254879828"],"related_works":["https://openalex.org/W4361804730","https://openalex.org/W2142113611","https://openalex.org/W2334467465","https://openalex.org/W2018387840","https://openalex.org/W2087870008","https://openalex.org/W2162534555","https://openalex.org/W2752178021","https://openalex.org/W2045629210","https://openalex.org/W2143024819","https://openalex.org/W4386869550"],"abstract_inverted_index":{"Abstract":[0],"The":[1],"ever-growing":[2],"complexity":[3],"of":[4,42,124,135,138,149],"HPC":[5],"applications":[6],"and":[7,35,46,66,69,145,172],"the":[8,25,40,63,92,114,139,146,156,168,173],"computer":[9],"architectures":[10],"cost":[11],"more":[12],"efforts":[13],"than":[14],"ever":[15],"to":[16,33,44,61,75,89,112,167],"learn":[17],"application":[18],"behaviors.":[19],"In":[20,54],"this":[21],"paper,":[22],"we":[23,56,81],"propose":[24],"APMT":[26,109,154],",":[27],"an":[28,84],"Automatic":[29],"Performance":[30],"Modeling":[31],"Tool,":[32],"understand":[34,91],"predict":[36],"performance":[37,47,77,94,122],"efficiently":[38],"in":[39,126,162],"regimes":[41],"interest":[43],"developers":[45],"analysts":[48],"while":[49],"outperforming":[50],"many":[51],"traditional":[52],"techniques.":[53],"APMT,":[55],"use":[57],"hardware":[58],"counter-assisted":[59],"profiling":[60],"identify":[62],"key":[64,93],"kernels":[65,68],"non-scalable":[67],"build":[70],"each":[71],"kernel":[72],"model":[73,137,157,171],"according":[74],"our":[76],"modeling":[78,87],"framework.":[79],"Meantime,":[80],"also":[82],"provide":[83],"optional":[85],"refinement":[86],"framework":[88],"further":[90],"metric,":[95],"cycles-per-instruction":[96],"(CPI).":[97],"Our":[98],"evaluations":[99],"show":[100],"that":[101],"by":[102,160],"only":[103],"performing":[104],"a":[105],"few":[106],"small-scale":[107],"profiling,":[108],"is":[110],"able":[111],"keep":[113],"average":[115,121],"error":[116],"rate":[117],"around":[118],"15%":[119],"with":[120],"overheads":[123],"3%":[125],"different":[127],"scenarios,":[128],"including":[129],"NAS":[130],"parallel":[131],"benchmarks,":[132],"dynamical":[133],"core":[134],"atmosphere":[136],"Community":[140],"Earth":[141],"System":[142],"Model":[143],"(CESM),":[144],"ice":[147],"component":[148],"CESM":[150],"on":[151],"commodity":[152],"clusters.":[153],"improve":[155],"prediction":[158],"accuracies":[159],"25\u201352%":[161],"strong":[163],"scaling":[164],"tests":[165],"comparing":[166],"well-known":[169],"analytical":[170],"empirical":[174],"model.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}