{"id":"https://openalex.org/W2250845294","doi":"https://doi.org/10.1145/2822893","title":"Scalable Energy Efficiency with Resilience for High Performance Computing Systems","display_name":"Scalable Energy Efficiency with Resilience for High Performance Computing Systems","publication_year":2015,"publication_date":"2015-11-16","ids":{"openalex":"https://openalex.org/W2250845294","doi":"https://doi.org/10.1145/2822893","mag":"2250845294"},"language":"en","primary_location":{"id":"doi:10.1145/2822893","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2822893","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2822893","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/2822893","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110252248","display_name":"Li Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li Tan","raw_affiliation_strings":["University of California, Riverside, California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Riverside, California","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061737717","display_name":"Zizhong Chen","orcid":"https://orcid.org/0000-0003-2578-4940"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zizhong Chen","raw_affiliation_strings":["University of California, Riverside, California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Riverside, California","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043209884","display_name":"Shuaiwen Leon Song","orcid":"https://orcid.org/0000-0002-8402-1436"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuaiwen Leon Song","raw_affiliation_strings":["Pacific Northwest National Laboratory, Richland, Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory, Richland, Washington","institution_ids":["https://openalex.org/I142606810"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6128,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.84210526,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"12","issue":"4","first_page":"1","last_page":"27"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9993000030517578,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9990000128746033,"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/resilience","display_name":"Resilience (materials science)","score":0.7788186073303223},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7766095399856567},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.7045195698738098},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6692451238632202},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.6253766417503357},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5544704794883728},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.48227718472480774},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.45883411169052124},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.44274285435676575},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.4298953711986542},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.2445451319217682},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1306699514389038},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0905725359916687},{"id":"https://openalex.org/keywords/operations-management","display_name":"Operations management","score":0.07776153087615967}],"concepts":[{"id":"https://openalex.org/C2779585090","wikidata":"https://www.wikidata.org/wiki/Q3457762","display_name":"Resilience (materials science)","level":2,"score":0.7788186073303223},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7766095399856567},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.7045195698738098},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6692451238632202},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.6253766417503357},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5544704794883728},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.48227718472480774},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.45883411169052124},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.44274285435676575},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.4298953711986542},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2445451319217682},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1306699514389038},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0905725359916687},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.07776153087615967},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2822893","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2822893","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2822893","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/2822893","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2822893","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2822893","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8899999856948853,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G1063054902","display_name":null,"funder_award_id":"62855","funder_id":"https://openalex.org/F4320337506","funder_display_name":"Advanced Scientific Computing Research"},{"id":"https://openalex.org/G3442558166","display_name":null,"funder_award_id":"ACI-1305624","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G527974540","display_name":"SHF: Medium: Energy Efficient Computing on GPU-based Heterogeneous Systems","funder_award_id":"1513201","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G536053718","display_name":"SHF: Small: FTLA: Fault Tolerant Linear Algebra Software for Massively Parallel Architectures","funder_award_id":"1305622","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7117328668","display_name":null,"funder_award_id":"CCF-1513201","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7445705250","display_name":null,"funder_award_id":"62855","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8160623262","display_name":"CAREER: Dependable High Performance Scientific Computing at Extreme Scale  via Algorithmic Fault Tolerance","funder_award_id":"1305624","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/F4320309106","display_name":"Clemson University","ror":"https://ror.org/037s24f05"},{"id":"https://openalex.org/F4320310013","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06"},{"id":"https://openalex.org/F4320337506","display_name":"Advanced Scientific Computing Research","ror":"https://ror.org/0012c7r22"},{"id":"https://openalex.org/F4320338354","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2250845294.pdf","grobid_xml":"https://content.openalex.org/works/W2250845294.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W1963651058","https://openalex.org/W1964588245","https://openalex.org/W1973923004","https://openalex.org/W1991872262","https://openalex.org/W1993847789","https://openalex.org/W1995746640","https://openalex.org/W1997021720","https://openalex.org/W2001937343","https://openalex.org/W2006312753","https://openalex.org/W2009571103","https://openalex.org/W2022983552","https://openalex.org/W2026441832","https://openalex.org/W2027885534","https://openalex.org/W2032839380","https://openalex.org/W2049533325","https://openalex.org/W2050462122","https://openalex.org/W2069238642","https://openalex.org/W2091229785","https://openalex.org/W2091913208","https://openalex.org/W2093029285","https://openalex.org/W2093796545","https://openalex.org/W2098163907","https://openalex.org/W2098631346","https://openalex.org/W2099714261","https://openalex.org/W2102061396","https://openalex.org/W2103798727","https://openalex.org/W2104196799","https://openalex.org/W2105876415","https://openalex.org/W2108218040","https://openalex.org/W2119819594","https://openalex.org/W2130388542","https://openalex.org/W2133046454","https://openalex.org/W2138692126","https://openalex.org/W2139613807","https://openalex.org/W2140179600","https://openalex.org/W2140438747","https://openalex.org/W2150857739","https://openalex.org/W2150871235","https://openalex.org/W2151587416","https://openalex.org/W2154596969","https://openalex.org/W2159811471","https://openalex.org/W2161648335","https://openalex.org/W2163976529","https://openalex.org/W2165778700","https://openalex.org/W2168159483","https://openalex.org/W2170542648","https://openalex.org/W4238002809"],"related_works":["https://openalex.org/W2384867379","https://openalex.org/W3214280620","https://openalex.org/W2329539859","https://openalex.org/W3191490922","https://openalex.org/W2227905990","https://openalex.org/W2765823764","https://openalex.org/W2794038527","https://openalex.org/W2151092287","https://openalex.org/W2113265763","https://openalex.org/W2185314374"],"abstract_inverted_index":{"Ever-growing":[0],"performance":[1,136,179],"of":[2,8,22,135,150,162,185,214],"supercomputers":[3],"nowadays":[4],"brings":[5],"demanding":[6],"requirements":[7],"energy":[9,32,50,74,104,131,181,209],"efficiency":[10,33,51,105,132],"and":[11,18,34,52,76,88,98,106,118,139,153,180,183,192,216],"resilience,":[12],"due":[13],"to":[14,96],"rapidly":[15],"expanding":[16],"size":[17],"duration":[19],"in":[20,133,176,211],"use":[21],"the":[23,46,69,101,115,119,129,141,171,187,196,201,206,212],"large-scale":[24,61],"computing":[25],"systems.":[26],"Many":[27],"application/architecture-dependent":[28],"parameters":[29],"that":[30,170],"determine":[31],"resilience":[35,53,77,107,123,193,218],"individually":[36],"have":[37],"causal":[38],"effects":[39,71],"with":[40],"each":[41],"other,":[42],"which":[43],"directly":[44],"affect":[45],"trade-offs":[47,142],"among":[48,72,143,189],"performance,":[49,73],"at":[54,108],"scale.":[55,109],"To":[56],"enable":[57],"high-efficiency":[58],"management":[59],"for":[60,158,205],"High-Performance":[62],"Computing":[63],"(HPC)":[64],"systems":[65,168],"nowadays,":[66],"quantitatively":[67,127],"understanding":[68],"entangled":[70],"efficiency,":[75,182,210],"is":[78],"thus":[79],"required.":[80],"While":[81],"previous":[82],"work":[83],"focuses":[84],"on":[85,165],"exploring":[86],"energy-saving":[87,191],"resilience-enhancing":[89],"opportunities":[90],"separately,":[91],"little":[92],"has":[93],"been":[94],"done":[95],"theoretically":[97],"empirically":[99],"investigate":[100],"interplay":[102,188],"between":[103],"In":[110],"this":[111],"article,":[112],"by":[113],"extending":[114],"Amdahl\u2019s":[116],"Law":[117],"Karp-Flatt":[120],"Metric,":[121],"taking":[122],"into":[124],"consideration,":[125],"we":[126],"model":[128],"integrated":[130,208],"terms":[134],"per":[137],"Watt":[138],"showcase":[140],"typical":[144],"HPC":[145,163,167,203],"parameters,":[146],"such":[147],"as":[148],"number":[149],"cores,":[151],"frequency/voltage,":[152],"failure":[154],"rates.":[155],"Experimental":[156],"results":[157],"a":[159],"wide":[160],"spectrum":[161],"benchmarks":[164],"two":[166],"show":[169],"proposed":[172],"models":[173,197],"are":[174],"accurate":[175],"extrapolating":[177],"resilience-aware":[178],"capable":[184],"capturing":[186],"various":[190],"factors.":[194],"Moreover,":[195],"can":[198],"help":[199],"find":[200],"optimal":[202],"configuration":[204],"highest":[207],"presence":[213],"failures":[215],"applied":[217],"techniques.":[219]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}