{"id":"https://openalex.org/W4388561296","doi":"https://doi.org/10.1145/3624062.3624256","title":"Asynchronous Multi-Level Checkpointing: An Enabler of Reproducibility using Checkpoint History Analytics","display_name":"Asynchronous Multi-Level Checkpointing: An Enabler of Reproducibility using Checkpoint History Analytics","publication_year":2023,"publication_date":"2023-11-10","ids":{"openalex":"https://openalex.org/W4388561296","doi":"https://doi.org/10.1145/3624062.3624256"},"language":"en","primary_location":{"id":"doi:10.1145/3624062.3624256","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3624062.3624256","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-04343694v1/file/2023_SuperCheck_RECUP.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017256448","display_name":"Kevin Assogba","orcid":"https://orcid.org/0000-0002-0377-4576"},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Assogba","raw_affiliation_strings":["Rochester Institute of Technology, United States of America","RIT - Rochester Institute of Technology (Rochester, NY 14623 - United States)"],"raw_orcid":"https://orcid.org/0000-0002-0377-4576","affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology, United States of America","institution_ids":["https://openalex.org/I155173764"]},{"raw_affiliation_string":"RIT - Rochester Institute of Technology (Rochester, NY 14623 - United States)","institution_ids":["https://openalex.org/I155173764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085745891","display_name":"Bogdan Nicolae","orcid":"https://orcid.org/0000-0002-0661-7509"},"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":"Bogdan Nicolae","raw_affiliation_strings":["Argonne National Laboratory, United States of America","ANL - Argonne National Laboratory [Lemont] (9700 S Cass Ave B109, Lemont, IL, 60439 - United States)"],"raw_orcid":"https://orcid.org/0000-0002-0661-7509","affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, United States of America","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"ANL - Argonne National Laboratory [Lemont] (9700 S Cass Ave B109, Lemont, IL, 60439 - United States)","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001274809","display_name":"Hubertus J. J. van Dam","orcid":"https://orcid.org/0000-0002-0876-3294"},"institutions":[{"id":"https://openalex.org/I200870766","display_name":"Brookhaven National Laboratory","ror":"https://ror.org/02ex6cf31","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I200870766","https://openalex.org/I39565521","https://openalex.org/I4210142672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hubertus Van Dam","raw_affiliation_strings":["Brookhaven National Laboratory, United States of America","BNL - Brookhaven National Laboratory [Upton, NY] (Brookhaven Avenue, Upton, NY 11973 - United States)"],"raw_orcid":"https://orcid.org/0000-0002-0876-3294","affiliations":[{"raw_affiliation_string":"Brookhaven National Laboratory, United States of America","institution_ids":["https://openalex.org/I200870766"]},{"raw_affiliation_string":"BNL - Brookhaven National Laboratory [Upton, NY] (Brookhaven Avenue, Upton, NY 11973 - United States)","institution_ids":["https://openalex.org/I200870766"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054011637","display_name":"M. Mustafa Rafique","orcid":"https://orcid.org/0000-0002-5034-2880"},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M. Mustafa Rafique","raw_affiliation_strings":["Rochester Institute of Technology, United States of America","RIT - Rochester Institute of Technology (Rochester, NY 14623 - United States)"],"raw_orcid":"https://orcid.org/0000-0002-5034-2880","affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology, United States of America","institution_ids":["https://openalex.org/I155173764"]},{"raw_affiliation_string":"RIT - Rochester Institute of Technology (Rochester, NY 14623 - United States)","institution_ids":["https://openalex.org/I155173764"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1748","last_page":"1756"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9994999766349792,"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":0.9994999766349792,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9973999857902527,"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/computer-science","display_name":"Computer science","score":0.839455246925354},{"id":"https://openalex.org/keywords/reproducibility","display_name":"Reproducibility","score":0.763984203338623},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.7096937298774719},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5380368828773499},{"id":"https://openalex.org/keywords/interleaving","display_name":"Interleaving","score":0.5137785077095032},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.46987849473953247},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4610084891319275},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4449726641178131},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2700433135032654},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.12965241074562073},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.11933356523513794}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.839455246925354},{"id":"https://openalex.org/C9893847","wikidata":"https://www.wikidata.org/wiki/Q1425625","display_name":"Reproducibility","level":2,"score":0.763984203338623},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.7096937298774719},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5380368828773499},{"id":"https://openalex.org/C28034677","wikidata":"https://www.wikidata.org/wiki/Q17092530","display_name":"Interleaving","level":2,"score":0.5137785077095032},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.46987849473953247},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4610084891319275},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4449726641178131},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2700433135032654},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.12965241074562073},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.11933356523513794},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3624062.3624256","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3624062.3624256","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04343694v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04343694","pdf_url":"https://hal.science/hal-04343694v1/file/2023_SuperCheck_RECUP.pdf","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SuperCheck\u201923: The 4th International Symposium on Checkpointing for Supercomputing (with SC'23), Nov 2023, Denver, United States. pp.1748-1756, ⟨10.1145/3624062.3624256⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04343694v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04343694","pdf_url":"https://hal.science/hal-04343694v1/file/2023_SuperCheck_RECUP.pdf","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SuperCheck\u201923: The 4th International Symposium on Checkpointing for Supercomputing (with SC'23), Nov 2023, Denver, United States. pp.1748-1756, ⟨10.1145/3624062.3624256⟩","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[{"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/G2131453672","display_name":"Collaborative Research: CNS Core: Medium:HardLambda: A new FaaS Abstraction for Cross-Stack Resource Management in Disaggregated Datacenters","funder_award_id":"2106635","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G255235230","display_name":null,"funder_award_id":"DEAC02-06CH11357","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"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/G484892034","display_name":null,"funder_award_id":"2106634,2106635","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"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/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/G6726936183","display_name":null,"funder_award_id":"0269227","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/G6918803902","display_name":null,"funder_award_id":"06CH11357","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"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/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/G8515454090","display_name":"Collaborative Research: CNS Core: Medium:HardLambda: A new FaaS Abstraction for Cross-Stack Resource Management in Disaggregated Datacenters","funder_award_id":"2106634","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G878601127","display_name":null,"funder_award_id":"DE-AC02-06CH11357","funder_id":"https://openalex.org/F4320337506","funder_display_name":"Advanced Scientific Computing Research"},{"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/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320337506","display_name":"Advanced Scientific Computing Research","ror":"https://ror.org/0012c7r22"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388561296.pdf","grobid_xml":"https://content.openalex.org/works/W4388561296.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1984564341","https://openalex.org/W2022950330","https://openalex.org/W2041591938","https://openalex.org/W2045406764","https://openalex.org/W2096718356","https://openalex.org/W2789037937","https://openalex.org/W2937207334","https://openalex.org/W2961595369","https://openalex.org/W3041193038","https://openalex.org/W3041643290","https://openalex.org/W3122350094","https://openalex.org/W3123222707","https://openalex.org/W3147109724","https://openalex.org/W4205739714","https://openalex.org/W4312803142","https://openalex.org/W4317214137","https://openalex.org/W4317928067","https://openalex.org/W4320067983","https://openalex.org/W4385623144","https://openalex.org/W4386707668","https://openalex.org/W6781857949"],"related_works":["https://openalex.org/W1655266410","https://openalex.org/W2413717610","https://openalex.org/W1973270181","https://openalex.org/W2417696084","https://openalex.org/W2389051085","https://openalex.org/W2368782778","https://openalex.org/W2330343234","https://openalex.org/W1901012776","https://openalex.org/W2087830269","https://openalex.org/W3106281778"],"abstract_inverted_index":{"High-performance":[0],"computing":[1],"applications":[2],"are":[3],"increasingly":[4],"integrating":[5],"checkpointing":[6,25,149],"libraries":[7],"for":[8,17,131],"reproducibility":[9,18,105,132],"analytics.":[10],"However,":[11],"capturing":[12,129],"an":[13,68],"entire":[14],"checkpoint":[15,79,125],"history":[16],"study":[19,58,95],"faces":[20],"the":[21,33,59,96,104,113,124,147],"challenges":[22],"of":[23,28,71,84,98,106,137],"high-frequency":[24],"across":[26],"thousands":[27],"processes.":[29],"As":[30],"a":[31,72,85,135],"result,":[32],"runtime":[34],"overhead":[35],"affects":[36],"application":[37,87],"performance":[38],"and":[39,77,140],"intermediate":[40,60],"results":[41,61,117],"when":[42,128],"interleaving":[43],"is":[44],"introduced":[45],"during":[46],"floating-point":[47],"calculations.":[48],"In":[49],"this":[50],"paper,":[51],"we":[52],"extend":[53],"asynchronous":[54],"multi-level":[55],"checkpoint/restart":[56],"to":[57,142,146],"generated":[62],"from":[63,81],"scientific":[64,86],"workflows.":[65],"We":[66,93],"present":[67],"initial":[69],"prototype":[70],"framework":[73],"that":[74,119],"captures,":[75],"caches,":[76],"compares":[78],"histories":[80],"different":[82],"runs":[83],"executed":[88,111],"using":[89,112],"identical":[90],"input":[91],"files.":[92],"also":[94],"impact":[97],"our":[99,120],"proposed":[100,121],"approach":[101,150],"by":[102,134],"evaluating":[103],"classical":[107],"molecular":[108],"dynamics":[109],"simulations":[110],"NWChem":[114],"software.":[115],"Experiment":[116],"show":[118],"solution":[122],"improves":[123],"write":[126],"bandwidth":[127],"checkpoints":[130],"analysis":[133],"minimum":[136],"30":[138],"\u00d7":[139,144],"up":[141],"211":[143],"compared":[145],"default":[148],"in":[151],"NWChem.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}