{"id":"https://openalex.org/W2128523353","doi":"https://doi.org/10.1109/ispass.2011.5762713","title":"Evaluation and optimization of multicore performance bottlenecks in supercomputing applications","display_name":"Evaluation and optimization of multicore performance bottlenecks in supercomputing applications","publication_year":2011,"publication_date":"2011-04-01","ids":{"openalex":"https://openalex.org/W2128523353","doi":"https://doi.org/10.1109/ispass.2011.5762713","mag":"2128523353"},"language":"en","primary_location":{"id":"doi:10.1109/ispass.2011.5762713","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispass.2011.5762713","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"(IEEE ISPASS) IEEE INTERNATIONAL SYMPOSIUM ON PERFORMANCE ANALYSIS OF SYSTEMS AND SOFTWARE","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/A5081370131","display_name":"Jeff Diamond","orcid":null},"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":"Jeff Diamond","raw_affiliation_strings":["University of Texas, Austin, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas, Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103125276","display_name":"Martin Burtscher","orcid":"https://orcid.org/0000-0001-7717-3354"},"institutions":[{"id":"https://openalex.org/I13511017","display_name":"Texas State University","ror":"https://ror.org/05h9q1g27","country_code":"US","type":"education","lineage":["https://openalex.org/I13511017"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martin Burtscher","raw_affiliation_strings":["Texas State University, San Marcos, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas State University, San Marcos, USA","institution_ids":["https://openalex.org/I13511017"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061731648","display_name":"John D. McCalpin","orcid":"https://orcid.org/0000-0002-2535-1355"},"institutions":[{"id":"https://openalex.org/I4388891828","display_name":"Texas Advanced Computing Center","ror":"https://ror.org/00xg4bh43","country_code":null,"type":"facility","lineage":["https://openalex.org/I4388891828","https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John D. McCalpin","raw_affiliation_strings":["Texas Advanced Computing Center, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas Advanced Computing Center, USA","institution_ids":["https://openalex.org/I4388891828"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022949833","display_name":"Byoung-Do Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I4388891828","display_name":"Texas Advanced Computing Center","ror":"https://ror.org/00xg4bh43","country_code":null,"type":"facility","lineage":["https://openalex.org/I4388891828","https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Byoung-Do Kim","raw_affiliation_strings":["Texas Advanced Computing Center, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas Advanced Computing Center, USA","institution_ids":["https://openalex.org/I4388891828"]}]},{"author_position":"middle","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, India","University of Texas, Austin, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA, India","institution_ids":[]},{"raw_affiliation_string":"University of Texas, Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064263297","display_name":"James C. Browne","orcid":null},"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":"James C. Browne","raw_affiliation_strings":["University of Texas, Austin, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas, Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.6068,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.93703976,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"32","last_page":"43"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.998199999332428,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9965000152587891,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.9514864683151245},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.8295794725418091},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8040755987167358},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7532605528831482},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6628820896148682},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.6513429284095764},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.514807403087616},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.42810288071632385},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3010792136192322}],"concepts":[{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.9514864683151245},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8295794725418091},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8040755987167358},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7532605528831482},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6628820896148682},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.6513429284095764},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.514807403087616},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.42810288071632385},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3010792136192322},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ispass.2011.5762713","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispass.2011.5762713","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"(IEEE ISPASS) IEEE INTERNATIONAL SYMPOSIUM ON PERFORMANCE ANALYSIS OF SYSTEMS AND SOFTWARE","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.592.264","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.592.264","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cs.txstate.edu/~mb92/papers/ispass11.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8117787320","display_name":"SHF:Small: Locality-Driven Architectures for Scalable Multicore Systems","funder_award_id":"0916745","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8659196067","display_name":null,"funder_award_id":"0622780","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2002555321","https://openalex.org/W2043218878","https://openalex.org/W2049890071","https://openalex.org/W2059710204","https://openalex.org/W2074297515","https://openalex.org/W2101778912","https://openalex.org/W2103877122","https://openalex.org/W2128529779","https://openalex.org/W2134633067","https://openalex.org/W2136434791","https://openalex.org/W2144433126","https://openalex.org/W2154786353","https://openalex.org/W2916060623","https://openalex.org/W3046179202","https://openalex.org/W3152199537","https://openalex.org/W4239813889","https://openalex.org/W6759722295","https://openalex.org/W6781508511"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W4382618745","https://openalex.org/W2885125400","https://openalex.org/W1001352512","https://openalex.org/W1989889224","https://openalex.org/W4255172949","https://openalex.org/W3023876411","https://openalex.org/W123152114"],"abstract_inverted_index":{"The":[0,83],"computation":[1],"nodes":[2,144],"of":[3,8,16,94,145,171],"modern":[4],"supercomputers":[5,105,146],"commonly":[6],"consist":[7],"multiple":[9],"multicore":[10,28,46,68,117,124,172],"processors.":[11,114,173],"To":[12],"maximize":[13],"the":[14,95,116,136,152,156,160],"performance":[15,53,62,80,130],"such":[17],"systems":[18,69],"requires":[19],"measurement,":[20],"analysis,":[21],"and":[22,37,51,70,85,110,159],"optimization":[23,81],"techniques":[24],"that":[25,65,77,128,168],"specifically":[26],"target":[27,153],"environments.":[29],"This":[30],"paper":[31],"first":[32],"examines":[33,50],"traditional":[34],"unicore":[35],"metrics":[36],"demonstrates":[38],"how":[39],"they":[40],"can":[41],"be":[42],"misleading":[43],"in":[44,67],"a":[45,91],"system.":[47],"Second,":[48],"it":[49,60],"characterizes":[52],"bottlenecks":[54],"specific":[55],"to":[56,79,120,123,133,165],"multicore-based":[57],"systems.":[58],"Third,":[59],"describes":[61],"measurement":[63,84],"challenges":[64],"arise":[66],"outlines":[71],"methods":[72],"for":[73,154],"extracting":[74],"sound":[75],"measurements":[76],"lead":[78],"opportunities.":[82],"analysis":[86,119],"process":[87],"is":[88,169],"based":[89],"on":[90,104,142],"case":[92,137],"study":[93],"HOMME":[96,121],"atmospheric":[97],"modeling":[98],"benchmark":[99],"code":[100],"from":[101],"NCAR":[102],"running":[103],"built":[106],"upon":[107],"AMD":[108],"Barcelona":[109],"Intel":[111],"Nehalem":[112],"quad-core":[113],"Applying":[115],"bottleneck":[118],"led":[122],"aware":[125],"source-code":[126],"optimizations":[127],"increased":[129],"by":[131],"up":[132],"35%.":[134],"While":[135],"studies":[138],"were":[139],"carried":[140],"out":[141],"multichip":[143],"using":[147],"an":[148],"HPC":[149],"application":[150],"as":[151],"optimization,":[155],"pitfalls":[157],"identified":[158],"insights":[161],"obtained":[162],"should":[163],"apply":[164],"any":[166],"system":[167],"composed":[170]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}