{"id":"https://openalex.org/W2060573894","doi":"https://doi.org/10.1145/2503210.2503228","title":"A 'cool' way of improving the reliability of HPC machines","display_name":"A 'cool' way of improving the reliability of HPC machines","publication_year":2013,"publication_date":"2013-10-30","ids":{"openalex":"https://openalex.org/W2060573894","doi":"https://doi.org/10.1145/2503210.2503228","mag":"2060573894"},"language":"en","primary_location":{"id":"doi:10.1145/2503210.2503228","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2503210.2503228","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"conference-paper","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/A5021321150","display_name":"Osman Sarood","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Osman Sarood","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL","[University of Illinois at Urbana-Champaign,Urbana,IL]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"[University of Illinois at Urbana-Champaign,Urbana,IL]","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046704108","display_name":"Esteban Meneses","orcid":"https://orcid.org/0000-0002-4307-6000"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Esteban Meneses","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL","[University of Illinois at Urbana-Champaign,Urbana,IL]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"[University of Illinois at Urbana-Champaign,Urbana,IL]","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051465480","display_name":"Laxmikant V. Kal\u00e9","orcid":"https://orcid.org/0000-0001-9673-8445"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Laxmikant V. Kale","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL","[University of Illinois at Urbana-Champaign,Urbana,IL]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"[University of Illinois at Urbana-Champaign,Urbana,IL]","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":5.0982,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.96752049,"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":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994000196456909,"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":0.9984999895095825,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7716919779777527},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.6303778886795044},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.601996898651123},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.5464942455291748},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.5338370203971863},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.5152168869972229},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.46684157848358154},{"id":"https://openalex.org/keywords/software-quality","display_name":"Software quality","score":0.43384161591529846},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3337612748146057},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.2910064458847046},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.24238580465316772},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1950860619544983},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.12041476368904114},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.08287122845649719},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07357069849967957}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7716919779777527},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.6303778886795044},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.601996898651123},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.5464942455291748},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.5338370203971863},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.5152168869972229},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.46684157848358154},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.43384161591529846},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3337612748146057},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2910064458847046},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.24238580465316772},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1950860619544983},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.12041476368904114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.08287122845649719},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07357069849967957},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2503210.2503228","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2503210.2503228","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.367.6146","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.367.6146","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://charm.cs.illinois.edu/newPapers/13-25/paper.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.9100000262260437,"display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G1970165029","display_name":null,"funder_award_id":"NSF ITR-HECURA-0833188, NSF CNS 09-58314","funder_id":"https://openalex.org/F4320337388","funder_display_name":"Division of Computer and Network Systems"},{"id":"https://openalex.org/G3287182735","display_name":"Simplifying Parallel Programming for CSE Applications using a Multi-Paradigm Approach","funder_award_id":"0833188","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7396478822","display_name":"\"NEW; HPC COLONY II; PI - LAXMIKANT KALE\"","funder_award_id":"DESC0001845","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"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/F4320337388","display_name":"Division of Computer and Network Systems","ror":"https://ror.org/02rdzmk74"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W68041361","https://openalex.org/W1539436949","https://openalex.org/W1979594720","https://openalex.org/W1981432246","https://openalex.org/W1983959114","https://openalex.org/W1984564341","https://openalex.org/W1989874002","https://openalex.org/W1991872262","https://openalex.org/W2014546690","https://openalex.org/W2022865998","https://openalex.org/W2033656974","https://openalex.org/W2056390551","https://openalex.org/W2063924830","https://openalex.org/W2089536264","https://openalex.org/W2104086123","https://openalex.org/W2106753104","https://openalex.org/W2113273853","https://openalex.org/W2116115793","https://openalex.org/W2132914442","https://openalex.org/W2133046454","https://openalex.org/W2141514639","https://openalex.org/W2145812623","https://openalex.org/W2155204206","https://openalex.org/W2165071510","https://openalex.org/W2166734474","https://openalex.org/W2171007672","https://openalex.org/W2171506849","https://openalex.org/W4229619734","https://openalex.org/W6646442782","https://openalex.org/W6811276039"],"related_works":["https://openalex.org/W2787993192","https://openalex.org/W2158269427","https://openalex.org/W4381280689","https://openalex.org/W2847365777","https://openalex.org/W3128025644","https://openalex.org/W2355048207","https://openalex.org/W2165143308","https://openalex.org/W179829755","https://openalex.org/W2064849136","https://openalex.org/W2200913013"],"abstract_inverted_index":{"Soaring":[0],"energy":[1,177],"consumption,":[2],"accompanied":[3],"by":[4,142,157,167,179,208,213],"declining":[5],"reliability,":[6,61,65],"together":[7],"loom":[8],"as":[9,180,182],"the":[10,14,32,83,118,152,164,210],"biggest":[11],"hurdles":[12],"for":[13,104],"next":[15],"generation":[16],"of":[17,85,95,120,133,154,160,206,216],"supercomputers.":[18],"Recent":[19],"reports":[20],"have":[21],"expressed":[22],"concern":[23],"that":[24,148],"reliability":[25,94,132,153,212],"at":[26],"exascale":[27],"level":[28],"could":[29],"degrade":[30],"to":[31,53,77,102,115,127,192,218],"point":[33],"where":[34],"failures":[35],"become":[36],"a":[37,155,158,185,214],"norm":[38],"rather":[39],"than":[40,196],"an":[41,204],"exception.":[42],"HPC":[43,96],"researchers":[44],"are":[45,100],"focusing":[46],"on":[47,58],"improving":[48,59,93,131,209],"existing":[49],"fault":[50],"tolerance":[51],"protocols":[52],"address":[54],"these":[55],"concerns.":[56],"Research":[57],"hardware":[60,90],"i.e.,":[62],"machine":[63,156,176,211],"component":[64],"has":[66],"also":[67,174],"been":[68],"making":[69],"progress":[70,194],"independently.":[71],"In":[72,169],"this":[73,79,113],"paper,":[74],"we":[75,149],"try":[76],"bridge":[78],"gap":[80],"and":[81,89,124,136,162],"explore":[82],"potential":[84,119],"combining":[86],"both":[87],"software":[88],"aspects":[91],"towards":[92],"machines.":[97],"Fault":[98],"rates":[99],"known":[101],"double":[103],"every":[105],"10\u00b0C":[106],"rise":[107],"in":[108],"core":[109,122],"temperature.":[110],"We":[111],"leverage":[112],"notion":[114],"experimentally":[116],"demonstrate":[117],"restraining":[121],"temperatures":[123],"load":[125],"balancing":[126],"achieve":[128],"two-fold":[129],"benefits:":[130],"parallel":[134],"machines":[135],"reducing":[137],"total":[138],"execution":[139,165],"time":[140,166],"required":[141],"applications.":[143],"Our":[144],"experimental":[145],"results":[146],"show":[147],"can":[150,173],"improve":[151],"factor":[159,215],"2.3":[161],"reduce":[163,175],"12%.":[168],"addition,":[170],"our":[171,200],"scheme":[172],"consumption":[178],"much":[181],"25%.":[183],"For":[184],"350K":[186],"socket":[187],"machine,":[188],"regular":[189],"checkpoint/restart":[190],"fails":[191],"make":[193],"(less":[195],"1%":[197],"efficiency),":[198],"whereas":[199],"validated":[201],"model":[202],"predicts":[203],"efficiency":[205],"20%":[207],"up":[217],"2.29.":[219]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":1}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}
