{"id":"https://openalex.org/W2798289565","doi":"https://doi.org/10.1145/3208040.3208050","title":"Improving performance of iterative methods by lossy checkponting","display_name":"Improving performance of iterative methods by lossy checkponting","publication_year":2018,"publication_date":"2018-06-11","ids":{"openalex":"https://openalex.org/W2798289565","doi":"https://doi.org/10.1145/3208040.3208050","mag":"2798289565"},"language":"en","primary_location":{"id":"doi:10.1145/3208040.3208050","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3208040.3208050","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3208040.3208050","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3208040.3208050","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Dingwen Tao","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":true,"raw_author_name":"Dingwen Tao","raw_affiliation_strings":["University of California, Riverside"],"affiliations":[{"raw_affiliation_string":"University of California, Riverside","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sheng Di","orcid":null},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sheng Di","raw_affiliation_strings":["Argonne National Laboratory"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xin Liang","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":"Xin Liang","raw_affiliation_strings":["University of California, Riverside"],"affiliations":[{"raw_affiliation_string":"University of California, Riverside","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zizhong Chen","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":"Zizhong Chen","raw_affiliation_strings":["University of California, Riverside"],"affiliations":[{"raw_affiliation_string":"University of California, Riverside","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"last","author":{"id":null,"display_name":"Franck Cappello","orcid":null},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Franck Cappello","raw_affiliation_strings":["Argonne National Laboratory"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory","institution_ids":["https://openalex.org/I1282105669"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I103635307"],"apc_list":null,"apc_paid":null,"fwci":3.7061,"has_fulltext":true,"cited_by_count":37,"citation_normalized_percentile":{"value":0.93625615,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"52","last_page":"65"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9983000159263611,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.998199999332428,"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/lossy-compression","display_name":"Lossy compression","score":0.9700000286102295},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.7437000274658203},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.6177999973297119},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5109000205993652},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.482699990272522},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.44530001282691956}],"concepts":[{"id":"https://openalex.org/C165021410","wikidata":"https://www.wikidata.org/wiki/Q55564","display_name":"Lossy compression","level":2,"score":0.9700000286102295},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7741000056266785},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.7437000274658203},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.6177999973297119},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5109000205993652},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.482699990272522},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.44530001282691956},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43209999799728394},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.3970000147819519},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.39010000228881836},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3400000035762787},{"id":"https://openalex.org/C2779089604","wikidata":"https://www.wikidata.org/wiki/Q7169333","display_name":"Permission","level":2,"score":0.3325999975204468},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.27410000562667847},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.25699999928474426}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3208040.3208050","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3208040.3208050","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3208040.3208050","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1804.11268","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1804.11268","pdf_url":"https://arxiv.org/pdf/1804.11268","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3208040.3208050","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3208040.3208050","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3208040.3208050","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1015216249","display_name":null,"funder_award_id":"DE-AC02-06CH1135","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G1116540683","display_name":null,"funder_award_id":"DE-AC02-06CH11","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G1313983767","display_name":null,"funder_award_id":"DE-AC02","funder_id":"https://openalex.org/F4320338284","funder_display_name":"Argonne National Laboratory"},{"id":"https://openalex.org/G1751644051","display_name":null,"funder_award_id":"DE-AC02-06CH11357","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G1844751952","display_name":null,"funder_award_id":"DE-AC02_06CH11357","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G2777053550","display_name":null,"funder_award_id":"AC02-06CH11357","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G3000213308","display_name":null,"funder_award_id":"DE-AC02-06CH113","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G3075337988","display_name":null,"funder_award_id":"06CH11357","funder_id":"https://openalex.org/F4320338284","funder_display_name":"Argonne National Laboratory"},{"id":"https://openalex.org/G3232922872","display_name":null,"funder_award_id":"17-SC-20-SC","funder_id":"https://openalex.org/F4320332369","funder_display_name":"National Nuclear Security Administration"},{"id":"https://openalex.org/G3318903820","display_name":null,"funder_award_id":"DE-AC02-06CH11357","funder_id":"https://openalex.org/F4320332369","funder_display_name":"National Nuclear Security Administration"},{"id":"https://openalex.org/G3801222974","display_name":null,"funder_award_id":"DE-AC02-06CH1135","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G4030212589","display_name":null,"funder_award_id":"contract DE-AC02-06CH11357","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G4145457401","display_name":null,"funder_award_id":"DE-AC02-06CH113","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G4290121262","display_name":null,"funder_award_id":"1619253","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4790718960","display_name":null,"funder_award_id":"DE-AC02-06CH11357","funder_id":"https://openalex.org/F4320338284","funder_display_name":"Argonne National Laboratory"},{"id":"https://openalex.org/G498139845","display_name":null,"funder_award_id":"DE-AC02","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G5001603810","display_name":null,"funder_award_id":"17-SC-20-S","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G5085543421","display_name":null,"funder_award_id":"AC02-06CH11357","funder_id":"https://openalex.org/F4320338284","funder_display_name":"Argonne National Laboratory"},{"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/G6085113958","display_name":null,"funder_award_id":"E-AC02-06CH11357","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G650626725","display_name":null,"funder_award_id":"E-AC02-06CH11357","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G6558272803","display_name":null,"funder_award_id":"DE-AC02","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6848031779","display_name":null,"funder_award_id":"06CH11357","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6859237865","display_name":null,"funder_award_id":"17-SC-20-SC","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6918803902","display_name":null,"funder_award_id":"06CH11357","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G7230044214","display_name":null,"funder_award_id":"DE-AC02-06CH1135","funder_id":"https://openalex.org/F4320338284","funder_display_name":"Argonne National Laboratory"},{"id":"https://openalex.org/G7351994996","display_name":null,"funder_award_id":"DE-AC02-06CH11357","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7822115964","display_name":null,"funder_award_id":"under contract DE-AC02-06CH11357","funder_id":"https://openalex.org/F4320338284","funder_display_name":"Argonne National Laboratory"},{"id":"https://openalex.org/G8143874970","display_name":null,"funder_award_id":"AC02-06CH11357","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"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"},{"id":"https://openalex.org/G8253304997","display_name":null,"funder_award_id":"17-SC-20-SC","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G8314672274","display_name":null,"funder_award_id":"DE-AC02-06CH11","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8320508866","display_name":null,"funder_award_id":"DE-AC02-06CH11357,","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8414908677","display_name":null,"funder_award_id":"DE-AC0","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G969889393","display_name":null,"funder_award_id":"DE-AC02-","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/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320332369","display_name":"National Nuclear Security Administration","ror":"https://ror.org/03sk1we31"},{"id":"https://openalex.org/F4320338284","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2798289565.pdf","grobid_xml":"https://content.openalex.org/works/W2798289565.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1499782454","https://openalex.org/W1777016212","https://openalex.org/W1823244711","https://openalex.org/W1981257396","https://openalex.org/W1981432246","https://openalex.org/W1984564341","https://openalex.org/W1995746640","https://openalex.org/W1999776923","https://openalex.org/W2033656974","https://openalex.org/W2035080386","https://openalex.org/W2035448730","https://openalex.org/W2035492130","https://openalex.org/W2037523067","https://openalex.org/W2038238534","https://openalex.org/W2043382734","https://openalex.org/W2052440657","https://openalex.org/W2076077791","https://openalex.org/W2078837027","https://openalex.org/W2081598885","https://openalex.org/W2097269032","https://openalex.org/W2104486653","https://openalex.org/W2124192278","https://openalex.org/W2128511938","https://openalex.org/W2138660187","https://openalex.org/W2140153041","https://openalex.org/W2142265837","https://openalex.org/W2164566630","https://openalex.org/W2170079961","https://openalex.org/W2242118751","https://openalex.org/W2296772319","https://openalex.org/W2343351966","https://openalex.org/W2412349256","https://openalex.org/W2418331349","https://openalex.org/W2475126267","https://openalex.org/W2485331474","https://openalex.org/W2486202470","https://openalex.org/W2580243656","https://openalex.org/W2625759119","https://openalex.org/W2767694495","https://openalex.org/W2785907813","https://openalex.org/W6685854194"],"related_works":[],"abstract_inverted_index":{"Iterative":[0],"methods":[1,25,97,215],"are":[2,13,26],"commonly":[3],"used":[4],"approaches":[5],"to":[6,38,68,133],"solve":[7],"large,":[8],"sparse":[9],"linear":[10],"systems,":[11],"which":[12],"fundamental":[14],"operations":[15],"for":[16,116,161,213],"many":[17],"modern":[18],"scientific":[19,189],"simulations.":[20],"When":[21],"the":[22,40,63,70,92,117,124,135,139,146,170,209,229],"large-scale":[23],"iterative":[24,74,96,165,214],"running":[27],"with":[28,174,183,219,225],"a":[29,83,105,179,187,194],"large":[30,55],"number":[31,119,153],"of":[32,46,73,95,120,126,148,154,164,231],"ranks":[33],"in":[34,44,128,131,228],"parallel,":[35],"they":[36],"have":[37],"checkpoint":[39],"dynamic":[41],"variables":[42],"periodically":[43],"case":[45],"unavoidable":[47],"fail-stop":[48],"errors,":[49],"requiring":[50],"fast":[51],"I/O":[52],"systems":[53],"and":[54,110,193,222],"storage":[56],"space.":[57],"To":[58],"this":[59],"end,":[60],"significantly":[61,90,207],"reducing":[62],"checkpointing":[64,86,93,107,141,150,159,172,176,204,221],"overhead":[65,212],"is":[66,78],"critical":[67],"improving":[69],"overall":[71],"performance":[72,94,108,136],"methods.":[75,166],"Our":[76],"contribution":[77],"fourfold.":[79],"(1)":[80],"We":[81,103,144,168],"propose":[82],"novel":[84],"lossy":[85,100,106,129,140,149,158,171,203],"scheme":[87,173,205],"that":[88,200],"can":[89,206],"improve":[91],"by":[98,123,157,216],"leveraging":[99],"compressors.":[101],"(2)":[102],"formulate":[104],"model":[109],"derive":[111],"theoretically":[112],"an":[113],"upper":[114],"bound":[115],"extra":[118,152],"iterations":[121,155],"caused":[122,156],"distortion":[125],"data":[127],"checkpoints,":[130],"order":[132],"guarantee":[134],"improvement":[137],"under":[138],"scheme.":[142],"(3)":[143],"analyze":[145],"impact":[147],"(i.e.,":[151],"files)":[160],"multiple":[162],"types":[163],"(4)":[167],"evaluate":[169],"optimal":[175],"intervals":[177],"on":[178],"high-performance":[180],"computing":[181],"environment":[182],"2,048":[184],"cores,":[185],"using":[186],"well-known":[188],"computation":[190],"package":[191],"PETSc":[192],"state-of-the-art":[195],"checkpoint/restart":[196],"toolkit.":[197],"Experiments":[198],"show":[199],"our":[201],"optimized":[202],"reduce":[208],"fault":[210],"tolerance":[211],"23%\u223c70%":[217],"compared":[218,224],"traditional":[220],"20%\u223c58%":[223],"lossless-compressed":[226],"checkpointing,":[227],"presence":[230],"system":[232],"failures.":[233]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2018-05-07T00:00:00"}
