{"id":"https://openalex.org/W2170031755","doi":"https://doi.org/10.1109/clade.2003.1209999","title":"A diskless checkpointing algorithm for super-scale architectures applied to the fast fourier transform","display_name":"A diskless checkpointing algorithm for super-scale architectures applied to the fast fourier transform","publication_year":2004,"publication_date":"2004-06-22","ids":{"openalex":"https://openalex.org/W2170031755","doi":"https://doi.org/10.1109/clade.2003.1209999","mag":"2170031755"},"language":"en","primary_location":{"id":"doi:10.1109/clade.2003.1209999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/clade.2003.1209999","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 Workshop on Challenges of Large Applications in Distributed Environments, 2003.","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/A5019453159","display_name":"Christian Engelmann","orcid":"https://orcid.org/0000-0003-4365-6416"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C. Engelmann","raw_affiliation_strings":["Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113512005","display_name":"Anton Geist","orcid":null},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A. Geist","raw_affiliation_strings":["Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1289243028"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"47","last_page":"52"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9998000264167786,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9998000264167786,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9987000226974487,"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":0.8155176043510437},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.6847683787345886},{"id":"https://openalex.org/keywords/fast-fourier-transform","display_name":"Fast Fourier transform","score":0.5947248339653015},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.571789026260376},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.566088080406189},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.4329950213432312},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3507182002067566},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.2755982577800751},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06546923518180847}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8155176043510437},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.6847683787345886},{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.5947248339653015},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.571789026260376},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.566088080406189},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.4329950213432312},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3507182002067566},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2755982577800751},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06546923518180847},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/clade.2003.1209999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/clade.2003.1209999","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 Workshop on Challenges of Large Applications in Distributed Environments, 2003.","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.4.45","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.4.45","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.csm.ornl.gov/~engelman/publications/engelmann03diskless.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.492.3049","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.492.3049","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://web.ornl.gov/~webworks/cppr/y2001/pres/116978.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W169659540","https://openalex.org/W1570906644","https://openalex.org/W1971952282","https://openalex.org/W1985734797","https://openalex.org/W2013639878","https://openalex.org/W2018743852","https://openalex.org/W2068092015","https://openalex.org/W2074176412","https://openalex.org/W2134572726","https://openalex.org/W2296772319","https://openalex.org/W4232225775","https://openalex.org/W4247100129","https://openalex.org/W6606943569","https://openalex.org/W6643050054"],"related_works":["https://openalex.org/W4327521644","https://openalex.org/W3132558499","https://openalex.org/W2978884468","https://openalex.org/W2005846134","https://openalex.org/W2168413811","https://openalex.org/W2369237035","https://openalex.org/W2948041274","https://openalex.org/W4226515754","https://openalex.org/W2087878472","https://openalex.org/W2322333442"],"abstract_inverted_index":{"This":[0],"paper":[1],"discusses":[2],"the":[3,24,33,67,91,113,119],"issue":[4],"of":[5,15,17,70,93,112],"fault-tolerance":[6],"in":[7,32,78],"dis-tributed":[8],"computer":[9],"systems":[10,77],"with":[11,85],"tens":[12],"or":[13],"hundreds":[14],"thou-sands":[16],"diskless":[18,71,94],"processor":[19],"units.":[20],"Such":[21],"systems,":[22],"like":[23],"IBM":[25],"BlueGene/L,":[26],"are":[27],"predicted":[28],"to":[29,36,45,52,55,73,80,101,122],"be":[30,46,53],"deployed":[31],"next":[34],"five":[35],"ten":[37],"years.":[38],"Since":[39],"a":[40],"100,000-processor":[41],"system":[42],"is":[43],"go-ing":[44],"less":[47],"reliable,":[48],"scientific":[49,83],"applications":[50],"need":[51],"able":[54],"recover":[56],"from":[57,109],"occurring":[58],"failures":[59],"more":[60],"efficiently.":[61],"In":[62],"this":[63,99],"paper,":[64],"we":[65,89,97,106],"adapt":[66,98],"present":[68,107],"technique":[69,100,121],"checkpointing":[72],"such":[74],"huge":[75],"distributed":[76],"order":[79],"equip":[81],"existing":[82],"algorithms":[84],"super-scalable":[86],"fault-tolerance.":[87,125],"First,":[88],"discuss":[90],"method":[92],"checkpointing,":[95],"then":[96],"super-scale":[102,124],"architectures":[103],"and":[104],"finally":[105],"results":[108],"an":[110],"im-plementation":[111],"Fast":[114],"Fourier":[115],"Transform":[116],"that":[117],"uses":[118],"adapted":[120],"achieve":[123],"1":[126]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
