{"id":"https://openalex.org/W2339228518","doi":"https://doi.org/10.1177/1094342015628056","title":"Complex scientific applications made fault-tolerant with the sparse grid combination technique","display_name":"Complex scientific applications made fault-tolerant with the sparse grid combination technique","publication_year":2016,"publication_date":"2016-02-12","ids":{"openalex":"https://openalex.org/W2339228518","doi":"https://doi.org/10.1177/1094342015628056","mag":"2339228518"},"language":"en","primary_location":{"id":"doi:10.1177/1094342015628056","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342015628056","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","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/A5002760131","display_name":"Md. Mohsin Ali","orcid":"https://orcid.org/0000-0002-9080-7339"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Md Mohsin Ali","raw_affiliation_strings":["Research School of Computer Science, The Australian National University, Canberra, Australia"],"affiliations":[{"raw_affiliation_string":"Research School of Computer Science, The Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009849948","display_name":"Peter Strazdins","orcid":"https://orcid.org/0000-0001-8541-1551"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Peter E Strazdins","raw_affiliation_strings":["Research School of Computer Science, The Australian National University, Canberra, Australia"],"affiliations":[{"raw_affiliation_string":"Research School of Computer Science, The Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082473393","display_name":"Brendan Harding","orcid":"https://orcid.org/0000-0002-6755-9998"},"institutions":[{"id":"https://openalex.org/I2802631561","display_name":"Australian Mathematical Sciences Institute","ror":"https://ror.org/00yn60108","country_code":"AU","type":"other","lineage":["https://openalex.org/I2802631561"]},{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Brendan Harding","raw_affiliation_strings":["Mathematical Sciences Institute, The Australian National University, Canberra, Australia"],"affiliations":[{"raw_affiliation_string":"Mathematical Sciences Institute, The Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I2802631561","https://openalex.org/I118347636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009262102","display_name":"Markus Hegland","orcid":"https://orcid.org/0000-0002-5136-2883"},"institutions":[{"id":"https://openalex.org/I2802631561","display_name":"Australian Mathematical Sciences Institute","ror":"https://ror.org/00yn60108","country_code":"AU","type":"other","lineage":["https://openalex.org/I2802631561"]},{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Markus Hegland","raw_affiliation_strings":["Mathematical Sciences Institute, The Australian National University, Canberra, Australia"],"affiliations":[{"raw_affiliation_string":"Mathematical Sciences Institute, The Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I2802631561","https://openalex.org/I118347636"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5002760131"],"corresponding_institution_ids":["https://openalex.org/I118347636"],"apc_list":null,"apc_paid":null,"fwci":2.0268,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.87624289,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"30","issue":"3","first_page":"335","last_page":"359"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9969000220298767,"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/T11751","display_name":"Lattice Boltzmann Simulation Studies","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7455382347106934},{"id":"https://openalex.org/keywords/sparse-grid","display_name":"Sparse grid","score":0.7233396172523499},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.7203982472419739},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.6623901128768921},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6459312438964844},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.5387197136878967},{"id":"https://openalex.org/keywords/message-passing-interface","display_name":"Message Passing Interface","score":0.4778030514717102},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.45118317008018494},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.42953288555145264},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4024338722229004},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.38923022150993347},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.32781076431274414},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.1892528533935547},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10856673121452332}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7455382347106934},{"id":"https://openalex.org/C156439662","wikidata":"https://www.wikidata.org/wiki/Q7573793","display_name":"Sparse grid","level":2,"score":0.7233396172523499},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.7203982472419739},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.6623901128768921},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6459312438964844},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.5387197136878967},{"id":"https://openalex.org/C166782233","wikidata":"https://www.wikidata.org/wiki/Q127879","display_name":"Message Passing Interface","level":3,"score":0.4778030514717102},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45118317008018494},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.42953288555145264},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4024338722229004},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.38923022150993347},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.32781076431274414},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.1892528533935547},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10856673121452332},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1177/1094342015628056","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342015628056","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},{"id":"pmh:oai:digital.library.adelaide.edu.au:2440/118288","is_oa":false,"landing_page_url":"http://hdl.handle.net/2440/118288","pdf_url":null,"source":{"id":"https://openalex.org/S4306401835","display_name":"Adelaide Research & Scholarship (AR&S) (University of Adelaide)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I5681781","host_organization_name":"The University of Adelaide","host_organization_lineage":["https://openalex.org/I5681781"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://dx.doi.org/10.1177/1094342015628056","raw_type":"Journal article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W91323585","https://openalex.org/W170768260","https://openalex.org/W210390770","https://openalex.org/W773579520","https://openalex.org/W992660394","https://openalex.org/W1540969907","https://openalex.org/W1557253686","https://openalex.org/W1558516248","https://openalex.org/W1576341769","https://openalex.org/W1593553932","https://openalex.org/W1604544834","https://openalex.org/W1613353403","https://openalex.org/W1975238525","https://openalex.org/W1986905947","https://openalex.org/W1992361819","https://openalex.org/W2000870360","https://openalex.org/W2021234574","https://openalex.org/W2033656974","https://openalex.org/W2035093540","https://openalex.org/W2035724233","https://openalex.org/W2049644498","https://openalex.org/W2060138396","https://openalex.org/W2060194781","https://openalex.org/W2066533186","https://openalex.org/W2125707440","https://openalex.org/W2136434791","https://openalex.org/W2149053506","https://openalex.org/W2155662278","https://openalex.org/W2263277353","https://openalex.org/W2296772319","https://openalex.org/W2313840090","https://openalex.org/W2342958595","https://openalex.org/W2344350406","https://openalex.org/W4245503759","https://openalex.org/W4255975175"],"related_works":["https://openalex.org/W2153096481","https://openalex.org/W2148616436","https://openalex.org/W2102525122","https://openalex.org/W4245282135","https://openalex.org/W4306316843","https://openalex.org/W2130594209","https://openalex.org/W2036953450","https://openalex.org/W4300955944","https://openalex.org/W2170004886","https://openalex.org/W2108317625"],"abstract_inverted_index":{"Ultra-large\u2013scale":[0],"simulations":[1],"via":[2,234],"solving":[3,75],"partial":[4],"differential":[5],"equations":[6],"(PDEs)":[7],"require":[8],"very":[9],"large":[10,278],"computational":[11],"systems":[12],"for":[13,74,252,279,289],"their":[14],"timely":[15],"solution.":[16],"Studies":[17],"shown":[18],"the":[19,25,42,50,94,101,131,151,172,178,194,207,214,228,267,284],"rate":[20],"of":[21,60,100,169,171,301,305],"failure":[22,140],"grows":[23],"with":[24,185,197,261,266],"system":[26],"size,":[27],"and":[28,41,113,153,161,164,223],"these":[29],"trends":[30],"are":[31],"likely":[32],"to":[33,48,52,83,133,149,190,193,217,245],"worsen":[34],"in":[35,264,299],"future":[36],"machines.":[37],"Thus,":[38],"as":[39,277],"systems,":[40],"problems":[43],"solved":[44],"on":[45,130,270],"them,":[46],"continue":[47],"grow,":[49],"ability":[51,216],"survive":[53],"failures":[54,160],"is":[55,70,147,156,174,210],"becoming":[56],"a":[57,71,198,253,280,290,297],"critical":[58],"aspect":[59],"algorithm":[61],"development.":[62],"The":[63,203],"sparse":[64],"grid":[65,123],"combination":[66,124],"technique":[67],"(SGCT)":[68],"which":[69,272],"cost-effective":[72],"method":[73],"higher":[76],"dimensional":[77],"PDEs":[78],"can":[79,96],"be":[80],"easily":[81],"modified":[82],"provide":[84],"algorithm-based":[85],"fault":[86],"tolerance.":[87],"In":[88],"this":[89],"article,":[90],"we":[91],"describe":[92],"how":[93],"SGCT":[95,132,180,209,226,269],"produce":[97],"fault-tolerant":[98],"versions":[99],"Gyrokinetic":[102],"Electromagnetic":[103],"Numerical":[104],"Experiment":[105],"plasma":[106],"application,":[107,112],"Taxila":[108],"Lattice":[109],"Boltzmann":[110],"Method":[111],"Solid":[114],"Fuel":[115],"Ignition":[116],"application.":[117],"We":[118],"use":[119],"an":[120,303],"alternate":[121],"component":[122],"formula":[125],"by":[126],"adding":[127],"some":[128],"redundancy":[129],"recover":[134,150,219],"data":[135],"from":[136,220,238],"lost":[137],"processes.":[138],"User-level":[139],"mitigation":[141],"(ULFM)":[142],"message":[143],"passing":[144],"interface":[145],"(MPI)":[146],"used":[148],"processes,":[152],"our":[154],"implementation":[155],"robust":[157],"over":[158,302],"multiple":[159,221,225],"recovery":[162,233],"(processes":[163],"nodes).":[165],"An":[166,287],"acceptable":[167,186],"degree":[168],"modification":[170],"applications":[173,215],"required.":[175],"Results":[176],"using":[177],"2-D":[179],"show":[181,213],"competitive":[182],"execution":[183],"times":[184,276,295],"error":[187],"(within":[188],"0.1%":[189],"1.0%),":[191],"compared":[192],"same":[195],"simulation":[196],"single":[199,281],"full":[200],"resolution":[201],"grid.":[202],"benefits":[204],"improve":[205],"when":[206],"3-D":[208],"used.":[211],"Experiments":[212],"successfully":[218],"failures,":[222],"applying":[224],"reduces":[227],"computed":[229],"solution":[230],"error.":[231],"Process":[232],"ULFM":[235],"MPI":[236],"increases":[237],"approximately":[239,246],"1.5":[240],"sec":[241,248],"at":[242,249],"64":[243],"cores":[244,251],"5":[247],"2048":[250],"one-off":[254],"failure.":[255],"This":[256],"compares":[257],"applications\u2019":[258],"built-in":[259],"checkpointing":[260],"job":[262],"restart":[263],"conjunction":[265],"classical":[268],"failure,":[271,282],"have":[273],"overheads":[274],"four":[275],"excluding":[283],"recomputation":[285,294],"overhead.":[286],"analysis":[288],"long-running":[291],"application":[292],"considering":[293],"indicates":[296],"reduction":[298],"overhead":[300],"order":[304],"magnitude.":[306]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
