{"id":"https://openalex.org/W2621069494","doi":"https://doi.org/10.1109/tcc.2017.2710311","title":"Fault Tolerant Stencil Computation on Cloud-Based GPU Spot Instances","display_name":"Fault Tolerant Stencil Computation on Cloud-Based GPU Spot Instances","publication_year":2017,"publication_date":"2017-05-31","ids":{"openalex":"https://openalex.org/W2621069494","doi":"https://doi.org/10.1109/tcc.2017.2710311","mag":"2621069494"},"language":"en","primary_location":{"id":"doi:10.1109/tcc.2017.2710311","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcc.2017.2710311","pdf_url":null,"source":{"id":"https://openalex.org/S2492498579","display_name":"IEEE Transactions on Cloud Computing","issn_l":"2168-7161","issn":["2168-7161","2372-0018"],"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 Cloud Computing","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/A5101917143","display_name":"Jun Zhou","orcid":"https://orcid.org/0000-0001-7899-2909"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jun Zhou","raw_affiliation_strings":["National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-7899-2909","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100456188","display_name":"Yan Zhang","orcid":"https://orcid.org/0000-0002-0451-2949"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yan Zhang","raw_affiliation_strings":["National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023989495","display_name":"Weng\u2010Fai Wong","orcid":"https://orcid.org/0000-0002-4281-2053"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Weng-Fai Wong","raw_affiliation_strings":["National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":6.4482,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.96744687,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":"7","issue":"4","first_page":"1013","last_page":"1024"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9988999962806702,"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":0.9988999962806702,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9984999895095825,"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/stencil","display_name":"Stencil","score":0.8630928993225098},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8426272869110107},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7014245390892029},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6853237152099609},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6456637978553772},{"id":"https://openalex.org/keywords/bidding","display_name":"Bidding","score":0.44859588146209717},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.42947399616241455},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3007754683494568},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.2905271649360657},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24677860736846924},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.18908554315567017}],"concepts":[{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.8630928993225098},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8426272869110107},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7014245390892029},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6853237152099609},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6456637978553772},{"id":"https://openalex.org/C9233905","wikidata":"https://www.wikidata.org/wiki/Q3276328","display_name":"Bidding","level":2,"score":0.44859588146209717},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.42947399616241455},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3007754683494568},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2905271649360657},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24677860736846924},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.18908554315567017},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcc.2017.2710311","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcc.2017.2710311","pdf_url":null,"source":{"id":"https://openalex.org/S2492498579","display_name":"IEEE Transactions on Cloud Computing","issn_l":"2168-7161","issn":["2168-7161","2372-0018"],"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 Cloud Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5653142996","display_name":null,"funder_award_id":"MOE2013-T2-2-033","funder_id":"https://openalex.org/F4320320751","funder_display_name":"Ministry of Education - Singapore"}],"funders":[{"id":"https://openalex.org/F4320320751","display_name":"Ministry of Education - Singapore","ror":"https://ror.org/01kcva023"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W363203313","https://openalex.org/W1968858811","https://openalex.org/W1983771518","https://openalex.org/W1987659801","https://openalex.org/W2000842323","https://openalex.org/W2003264742","https://openalex.org/W2015935981","https://openalex.org/W2016618963","https://openalex.org/W2035975621","https://openalex.org/W2044666931","https://openalex.org/W2057317268","https://openalex.org/W2074833026","https://openalex.org/W2082819362","https://openalex.org/W2098424235","https://openalex.org/W2099393515","https://openalex.org/W2104512032","https://openalex.org/W2113754927","https://openalex.org/W2122677725","https://openalex.org/W2132777761","https://openalex.org/W2153985054","https://openalex.org/W2154786353","https://openalex.org/W2162570510","https://openalex.org/W2165751385","https://openalex.org/W2167523268","https://openalex.org/W2535067972","https://openalex.org/W2549366874","https://openalex.org/W2549711633","https://openalex.org/W2550527757","https://openalex.org/W3087488422","https://openalex.org/W3152199537","https://openalex.org/W4210691403","https://openalex.org/W4299547616","https://openalex.org/W6729295790","https://openalex.org/W6729382712","https://openalex.org/W6783252855"],"related_works":["https://openalex.org/W3105129168","https://openalex.org/W2804920739","https://openalex.org/W4316371992","https://openalex.org/W2186216222","https://openalex.org/W2392765154","https://openalex.org/W2564509292","https://openalex.org/W2008005532","https://openalex.org/W2177020196","https://openalex.org/W1429949169","https://openalex.org/W3139770841"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,72,87,114],"fault":[4],"tolerant":[5],"framework":[6,93,108],"for":[7,97,101,119],"distributed":[8],"stencil":[9,41,92],"computation":[10,24,49],"on":[11,43,52,71,123],"cloud-based":[12],"GPU":[13,57],"clusters.":[14],"It":[15],"uses":[16],"pipelining":[17],"to":[18,64,76,144],"overlap":[19],"the":[20,26,36,48,53,78,82,110,130,139],"data":[21,33],"movement":[22,34],"with":[23,86],"in":[25],"halo":[27],"region":[28],"as":[29,31],"well":[30],"parallelises":[32],"within":[35],"GPUs.":[37],"Instead":[38],"of":[39,81,116,132],"running":[40,122],"codes":[42],"traditional":[44],"clusters":[45],"and":[46,59],"supercomputers,":[47],"is":[50,69],"performed":[51],"Amazon":[54],"Web":[55],"Service":[56],"cloud,":[58],"utilizes":[60],"its":[61],"spot":[62,83,133],"instances":[63,134],"improve":[65],"cost-efficiency.":[66],"The":[67],"implementation":[68],"based":[70],"low-cost":[73],"fault-tolerant":[74],"mechanism":[75],"handle":[77],"possible":[79],"termination":[80],"instances.":[84],"Coupled":[85],"price":[88],"bidding":[89],"module,":[90],"our":[91,107],"not":[94],"only":[95],"optimizes":[96],"performance":[98],"but":[99],"also":[100,127],"cost.":[102],"Experimental":[103],"results":[104],"show":[105,128],"that":[106,129],"outperforms":[109],"state-of-the-art":[111],"solutions":[112],"achieving":[113],"peak":[115],"25":[117],"TFLOPS":[118],"2-D":[120],"decomposition":[121],"512":[124],"nodes.":[125],"We":[126],"use":[131],"yields":[135],"good":[136],"cost-efficiency,":[137],"increasing":[138],"average":[140],"TFLOPS/USD":[141],"from":[142],"132":[143],"360.":[145]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
