{"id":"https://openalex.org/W4251782551","doi":"https://doi.org/10.1109/sc.2008.5218557","title":"Lessons learned at 208K: Towards debugging millions of cores","display_name":"Lessons learned at 208K: Towards debugging millions of cores","publication_year":2008,"publication_date":"2008-11-01","ids":{"openalex":"https://openalex.org/W4251782551","doi":"https://doi.org/10.1109/sc.2008.5218557"},"language":"en","primary_location":{"id":"doi:10.1109/sc.2008.5218557","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sc.2008.5218557","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 SC - International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/biblio/945138","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084741371","display_name":"Gregory L. Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gregory L. Lee","raw_affiliation_strings":["Computation Directorate, Lawrence Livemore National Laboratory, Livermore, CA, USA"],"affiliations":[{"raw_affiliation_string":"Computation Directorate, Lawrence Livemore National Laboratory, Livermore, CA, USA","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006598908","display_name":"Dong H. Ahn","orcid":"https://orcid.org/0000-0001-6722-0532"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong H. Ahn","raw_affiliation_strings":["Computation Directorate, Lawrence Livemore National Laboratory, Livermore, CA, USA"],"affiliations":[{"raw_affiliation_string":"Computation Directorate, Lawrence Livemore National Laboratory, Livermore, CA, USA","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084153776","display_name":"Dorian Arnold","orcid":"https://orcid.org/0000-0002-9425-1884"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dorian C. Arnold","raw_affiliation_strings":["Computer Sciences Department, University of Wisconsin, Madison, WI, USA"],"affiliations":[{"raw_affiliation_string":"Computer Sciences Department, University of Wisconsin, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058719424","display_name":"Bronis R. de Supinski","orcid":"https://orcid.org/0000-0002-0339-1006"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bronis R. de Supinski","raw_affiliation_strings":["Computation Directorate, Lawrence Livemore National Laboratory, Livermore, CA, USA"],"affiliations":[{"raw_affiliation_string":"Computation Directorate, Lawrence Livemore National Laboratory, Livermore, CA, USA","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109361411","display_name":"Matthew LeGendre","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Legendre","raw_affiliation_strings":["Computer Sciences Department, University of Wisconsin, Madison, WI, USA"],"affiliations":[{"raw_affiliation_string":"Computer Sciences Department, University of Wisconsin, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010187794","display_name":"Barton P. Miller","orcid":"https://orcid.org/0000-0002-9435-8315"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Barton P. Miller","raw_affiliation_strings":["Computer Sciences Department, University of Wisconsin, Madison, WI, USA"],"affiliations":[{"raw_affiliation_string":"Computer Sciences Department, University of Wisconsin, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045289712","display_name":"Martin Schulz","orcid":"https://orcid.org/0000-0001-9013-435X"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martin Schulz","raw_affiliation_strings":["Computation Directorate, Lawrence Livemore National Laboratory, Livermore, CA, USA"],"affiliations":[{"raw_affiliation_string":"Computation Directorate, Lawrence Livemore National Laboratory, Livermore, CA, USA","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030632138","display_name":"Ben Liblit","orcid":"https://orcid.org/0000-0002-2245-2839"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ben Liblit","raw_affiliation_strings":["Computer Sciences Department, University of Wisconsin, Madison, WI, USA"],"affiliations":[{"raw_affiliation_string":"Computer Sciences Department, University of Wisconsin, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5084741371"],"corresponding_institution_ids":["https://openalex.org/I1282311441"],"apc_list":null,"apc_paid":null,"fwci":0.3544,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.74268293,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"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":0.9998999834060669,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9991000294685364,"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/petascale-computing","display_name":"Petascale computing","score":0.968109130859375},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8953903913497925},{"id":"https://openalex.org/keywords/debugging","display_name":"Debugging","score":0.7616564035415649},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7448042631149292},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.5277348756790161},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.48115718364715576},{"id":"https://openalex.org/keywords/infiniband","display_name":"InfiniBand","score":0.4450817406177521},{"id":"https://openalex.org/keywords/exascale-computing","display_name":"Exascale computing","score":0.43689465522766113},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.41872337460517883},{"id":"https://openalex.org/keywords/java","display_name":"Java","score":0.41182494163513184},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.41012951731681824},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.38768649101257324},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.3238838315010071},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15778642892837524}],"concepts":[{"id":"https://openalex.org/C185410017","wikidata":"https://www.wikidata.org/wiki/Q7171778","display_name":"Petascale computing","level":3,"score":0.968109130859375},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8953903913497925},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.7616564035415649},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7448042631149292},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.5277348756790161},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48115718364715576},{"id":"https://openalex.org/C2781030343","wikidata":"https://www.wikidata.org/wiki/Q922437","display_name":"InfiniBand","level":2,"score":0.4450817406177521},{"id":"https://openalex.org/C2778837361","wikidata":"https://www.wikidata.org/wiki/Q2450880","display_name":"Exascale computing","level":3,"score":0.43689465522766113},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.41872337460517883},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.41182494163513184},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.41012951731681824},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.38768649101257324},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3238838315010071},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15778642892837524}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/sc.2008.5218557","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sc.2008.5218557","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 SC - International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:945138","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/945138","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":"pmh:oai:osti.gov:945138","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/945138","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},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.6399999856948853,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1515668834","https://openalex.org/W1555873941","https://openalex.org/W1631513913","https://openalex.org/W2035562244","https://openalex.org/W2036048726","https://openalex.org/W2089405485","https://openalex.org/W2100006263","https://openalex.org/W2106913893","https://openalex.org/W2148952547","https://openalex.org/W2160468841","https://openalex.org/W2166656891","https://openalex.org/W2171371822","https://openalex.org/W3147626894","https://openalex.org/W4233711641","https://openalex.org/W6630975882","https://openalex.org/W6636444237","https://openalex.org/W6659415785","https://openalex.org/W6681732262","https://openalex.org/W6683751365","https://openalex.org/W6793269206"],"related_works":["https://openalex.org/W2021702679","https://openalex.org/W3038449658","https://openalex.org/W1582746211","https://openalex.org/W3129378740","https://openalex.org/W2607572736","https://openalex.org/W2266027327","https://openalex.org/W2963147607","https://openalex.org/W2249929881","https://openalex.org/W2481709551","https://openalex.org/W1569809235"],"abstract_inverted_index":{"Petascale":[0],"systems":[1],"will":[2,44,174],"present":[3,106,182],"several":[4],"new":[5],"challenges":[6,107,172,187],"to":[7,29,32,108,138,158,164,185,199],"performance":[8,192],"and":[9,26,31,73,82,130,155,188],"correctness":[10],"tools.":[11],"Such":[12],"machines":[13],"may":[14,97],"contain":[15],"millions":[16],"of":[17,149,204],"cores,":[18],"requiring":[19],"that":[20,128,173],"tools":[21,75],"use":[22,77,144],"scalable":[23,79],"data":[24],"structures":[25],"analysis":[27,116],"algorithms":[28],"collect":[30],"process":[33,140],"application":[34,49,137],"data.":[35],"In":[36,102],"addition,":[37],"at":[38,58,147,177],"such":[39,71,92],"scales,":[40],"each":[41],"tool":[42,67,86,100,110,117,127],"itself":[43],"become":[45,99],"a":[46,78,120,125,135],"large":[47],"parallel":[48,136],"-":[50],"already,":[51],"debugging":[52,202],"the":[53,59,94,113,178,190,201],"full":[54],"Blue-Gene/L":[55],"(BG/L)":[56],"installation":[57],"Lawrence":[60],"Livermore":[61],"National":[62],"Laboratory":[63],"requires":[64],"employing":[65],"1664":[66],"daemons.":[68],"To":[69],"reach":[70],"sizes":[72],"beyond,":[74],"must":[76],"communication":[80],"infrastructure":[81],"manage":[83],"their":[84],"own":[85],"processes":[87,161],"efficiently.":[88],"Some":[89],"system":[90],"resources,":[91],"as":[93,119,169,171],"file":[95],"system,":[96],"also":[98,195],"bottlenecks.":[101],"this":[103],"paper,":[104],"we":[105],"petascale":[109,205],"development,":[111],"using":[112],"stack":[114,132],"trace":[115],"(STAT)":[118],"case":[121],"study.":[122],"STAT":[123],"is":[124],"lightweight":[126],"gathers":[129],"merges":[131],"traces":[133],"from":[134],"identify":[139,165],"equivalence":[141],"classes.":[142],"We":[143,180,194],"results":[145,156],"gathered":[146],"thousands":[148],"tasks":[150],"on":[151,162],"an":[152],"Infiniband":[153],"cluster":[154],"up":[157],"208":[159],"K":[160],"BG/L":[163],"current":[166],"scalability":[167],"issues":[168],"well":[170],"be":[175],"faced":[176],"petascale.":[179],"then":[181],"implemented":[183],"solutions":[184],"these":[186],"show":[189],"resulting":[191],"improvements.":[193],"discuss":[196],"future":[197],"plans":[198],"meet":[200],"demands":[203],"machines.":[206]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":5}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}