{"id":"https://openalex.org/W2296030857","doi":"https://doi.org/10.1109/tpds.2015.2430852","title":"Exploring the Design Tradeoffs for Extreme-Scale High-Performance Computing System Software","display_name":"Exploring the Design Tradeoffs for Extreme-Scale High-Performance Computing System Software","publication_year":2015,"publication_date":"2015-05-07","ids":{"openalex":"https://openalex.org/W2296030857","doi":"https://doi.org/10.1109/tpds.2015.2430852","mag":"2296030857"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2015.2430852","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2015.2430852","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-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/A5101954500","display_name":"Ke Wang","orcid":"https://orcid.org/0000-0003-1826-9406"},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ke Wang","raw_affiliation_strings":["Department of Computer Science, Illinois Institute of Technology, Chicago, IL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Illinois Institute of Technology, Chicago, IL","institution_ids":["https://openalex.org/I180949307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056024226","display_name":"Abhishek Kulkarni","orcid":"https://orcid.org/0000-0003-3789-002X"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhishek Kulkarni","raw_affiliation_strings":["Department of Computer Science, Indiana University, Bloomington, IN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Indiana University, Bloomington, IN","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078475557","display_name":"Michael Lang","orcid":"https://orcid.org/0000-0002-3498-6352"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Lang","raw_affiliation_strings":["Los Alamos National Laboratory, Los Alamos, NM"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory, Los Alamos, NM","institution_ids":["https://openalex.org/I1343871089"]}]},{"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/I169521973","display_name":"University of New Mexico","ror":"https://ror.org/05fs6jp91","country_code":"US","type":"education","lineage":["https://openalex.org/I169521973"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dorian Arnold","raw_affiliation_strings":["Department of Computer Science, University of New Mexico, Albuquerque, NM"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of New Mexico, Albuquerque, NM","institution_ids":["https://openalex.org/I169521973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030599558","display_name":"Ioan Raicu","orcid":"https://orcid.org/0000-0002-5477-439X"},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ioan Raicu","raw_affiliation_strings":["Department of Computer Science, Illinois Institute of Technology, Chicago, IL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Illinois Institute of Technology, Chicago, IL","institution_ids":["https://openalex.org/I180949307"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.939,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.97620061,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"27","issue":"4","first_page":"1070","last_page":"1084"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9998999834060669,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9994000196456909,"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":0.8535006642341614},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6902667284011841},{"id":"https://openalex.org/keywords/software-system","display_name":"Software system","score":0.6272234320640564},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5826443433761597},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5773648023605347},{"id":"https://openalex.org/keywords/component-based-software-engineering","display_name":"Component-based software engineering","score":0.5450719594955444},{"id":"https://openalex.org/keywords/software-framework","display_name":"Software framework","score":0.5140055418014526},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5041476488113403},{"id":"https://openalex.org/keywords/system-software","display_name":"System software","score":0.49424174427986145},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.4796864688396454},{"id":"https://openalex.org/keywords/software-construction","display_name":"Software construction","score":0.450057715177536},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.42556071281433105},{"id":"https://openalex.org/keywords/software-evolution","display_name":"Software evolution","score":0.4141327738761902},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.40421274304389954},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.31274908781051636}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8535006642341614},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6902667284011841},{"id":"https://openalex.org/C149091818","wikidata":"https://www.wikidata.org/wiki/Q2429814","display_name":"Software system","level":3,"score":0.6272234320640564},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5826443433761597},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5773648023605347},{"id":"https://openalex.org/C174683762","wikidata":"https://www.wikidata.org/wiki/Q609588","display_name":"Component-based software engineering","level":4,"score":0.5450719594955444},{"id":"https://openalex.org/C76518257","wikidata":"https://www.wikidata.org/wiki/Q271680","display_name":"Software framework","level":5,"score":0.5140055418014526},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5041476488113403},{"id":"https://openalex.org/C2779960034","wikidata":"https://www.wikidata.org/wiki/Q676202","display_name":"System software","level":3,"score":0.49424174427986145},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.4796864688396454},{"id":"https://openalex.org/C186846655","wikidata":"https://www.wikidata.org/wiki/Q3398377","display_name":"Software construction","level":4,"score":0.450057715177536},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.42556071281433105},{"id":"https://openalex.org/C202105479","wikidata":"https://www.wikidata.org/wiki/Q265013","display_name":"Software evolution","level":5,"score":0.4141327738761902},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.40421274304389954},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.31274908781051636}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpds.2015.2430852","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2015.2430852","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.702.3805","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.702.3805","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://datasys.cs.iit.edu/publications/2015_TPDS_DKVS.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2340147074","display_name":null,"funder_award_id":"CNS-1042543","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3516749101","display_name":null,"funder_award_id":"DE-FC02-06ER25750","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G3906604551","display_name":null,"funder_award_id":"DEAC02-06CH11357","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8258169708","display_name":null,"funder_award_id":"NSF-1054974","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"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320338284","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W47974043","https://openalex.org/W1521117430","https://openalex.org/W1530638770","https://openalex.org/W1536870558","https://openalex.org/W1565868544","https://openalex.org/W1570621506","https://openalex.org/W1596936080","https://openalex.org/W1836955865","https://openalex.org/W1963494026","https://openalex.org/W1971514365","https://openalex.org/W1978347128","https://openalex.org/W1984848758","https://openalex.org/W1997126580","https://openalex.org/W2008559335","https://openalex.org/W2010042648","https://openalex.org/W2016559894","https://openalex.org/W2019438923","https://openalex.org/W2020653682","https://openalex.org/W2020765652","https://openalex.org/W2025577327","https://openalex.org/W2034698773","https://openalex.org/W2036551003","https://openalex.org/W2044829989","https://openalex.org/W2079031056","https://openalex.org/W2085407655","https://openalex.org/W2085573357","https://openalex.org/W2087946700","https://openalex.org/W2090575249","https://openalex.org/W2093882679","https://openalex.org/W2103803358","https://openalex.org/W2105599110","https://openalex.org/W2108841814","https://openalex.org/W2109987947","https://openalex.org/W2114936722","https://openalex.org/W2121531691","https://openalex.org/W2134015819","https://openalex.org/W2146087795","https://openalex.org/W2150697658","https://openalex.org/W2152501970","https://openalex.org/W2153527920","https://openalex.org/W2153704625","https://openalex.org/W2158049821","https://openalex.org/W2165606466","https://openalex.org/W2168067900","https://openalex.org/W2171371822","https://openalex.org/W2336021669","https://openalex.org/W2341655714","https://openalex.org/W2898724554","https://openalex.org/W4248722156","https://openalex.org/W4250390143","https://openalex.org/W4255938980","https://openalex.org/W6601954144","https://openalex.org/W6631795981","https://openalex.org/W6632112766","https://openalex.org/W6634005266","https://openalex.org/W6788151078"],"related_works":["https://openalex.org/W2293483733","https://openalex.org/W1519914673","https://openalex.org/W2013315991","https://openalex.org/W2378851924","https://openalex.org/W1764030237","https://openalex.org/W2093407393","https://openalex.org/W2097691581","https://openalex.org/W1965643255","https://openalex.org/W2379987995","https://openalex.org/W2386418808"],"abstract_inverted_index":{"Owing":[0],"to":[1,21,54,111,127,146,173,217],"the":[2,6,37,67,133,143,211,219],"extreme":[3,75,228],"parallelism":[4],"and":[5,25,31,50,57,138,193],"high":[7],"component":[8],"failure":[9],"rates":[10],"of":[11,36,60,135,162,175,182,221],"tomorrow's":[12],"exascale,":[13],"high-performance":[14],"computing":[15],"(HPC)":[16],"system":[17,29,33,40,72,81,88,100,114,129,165,185,225],"software":[18,41,73,82,89,101,115,130,226],"will":[19],"need":[20],"be":[22],"scalable,":[23],"failure-resistant,":[24],"adaptive":[26],"for":[27,70,148,227],"sustained":[28],"operation":[30],"full":[32],"utilizations.":[34],"Many":[35],"existing":[38],"HPC":[39,87,190,224],"are":[42,52],"still":[43],"designed":[44],"around":[45],"a":[46,79,108,163],"centralized":[47],"server":[48],"paradigm":[49],"hence":[51],"susceptible":[53],"scaling":[55],"issues":[56],"single":[58],"points":[59],"failure.":[61],"In":[62],"this":[63,206,214],"article,":[64],"we":[65,157,178],"explore":[66],"design":[68,149,160],"tradeoffs":[69],"scalable":[71,113],"at":[74],"scales.":[76,229],"We":[77,208],"propose":[78],"general":[80],"taxonomy":[83,95],"by":[84,116],"deconstructing":[85],"common":[86],"into":[90,119],"their":[91,120],"basic":[92,121],"components.":[93],"The":[94],"helps":[96],"us":[97,107,126],"reason":[98],"about":[99],"as":[102],"follows:":[103],"(1)":[104],"it":[105,124,141],"gives":[106],"systematic":[109],"way":[110],"architect":[112],"decomposing":[117],"them":[118],"components;":[122],"(2)":[123],"allows":[125],"categorize":[128],"based":[131,202],"on":[132,203],"features":[134],"these":[136],"components,":[137],"finally":[139],"(3)":[140],"suggests":[142],"configuration":[144],"space":[145],"consider":[147],"evaluation":[150,180],"via":[151],"simulations":[152,171],"or":[153],"real":[154],"implementations.":[155],"Further,":[156],"evaluate":[158],"different":[159],"choices":[161],"representative":[164],"software,":[166,186],"i.e.":[167],"key-value":[168],"store,":[169],"through":[170],"up":[172],"millions":[174],"nodes.":[176],"Finally,":[177],"show":[179],"results":[181,212],"two":[183],"distributed":[184,189,196],"Slurm++":[187],"(a":[188,195],"resource":[191],"manager)":[192],"MATRIX":[194],"task":[197],"execution":[198],"framework),":[199],"both":[200],"developed":[201],"insights":[204],"from":[205],"work.":[207],"envision":[209],"that":[210],"in":[213],"article":[215],"help":[216],"lay":[218],"foundations":[220],"developing":[222],"next-generation":[223]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}