{"id":"https://openalex.org/W4414210053","doi":"https://doi.org/10.1145/3731545.3735116","title":"On Optimizing Checkpoint Restoration for HPC Applications: Leveraging Merkle Trees and Asynchronous I/O","display_name":"On Optimizing Checkpoint Restoration for HPC Applications: Leveraging Merkle Trees and Asynchronous I/O","publication_year":2025,"publication_date":"2025-07-20","ids":{"openalex":"https://openalex.org/W4414210053","doi":"https://doi.org/10.1145/3731545.3735116"},"language":"en","primary_location":{"id":"doi:10.1145/3731545.3735116","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731545.3735116","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-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/A5119624308","display_name":"Zackary Malkmus","orcid":null},"institutions":[{"id":"https://openalex.org/I2802706902","display_name":"Knoxville College","ror":"https://ror.org/02bxrp522","country_code":"US","type":"education","lineage":["https://openalex.org/I2802706902"]},{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zackary Malkmus","raw_affiliation_strings":["University of Tennessee Knoxville, Knoxville, USA"],"affiliations":[{"raw_affiliation_string":"University of Tennessee Knoxville, Knoxville, USA","institution_ids":["https://openalex.org/I2802706902","https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019570466","display_name":"Nigel Tan","orcid":"https://orcid.org/0000-0003-4699-8657"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nigel Tan","raw_affiliation_strings":["Los Alamos National Laboratory, Los Alamos, USA"],"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory, Los Alamos, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088217764","display_name":"Ian Lumsden","orcid":"https://orcid.org/0000-0003-0009-5487"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]},{"id":"https://openalex.org/I2802706902","display_name":"Knoxville College","ror":"https://ror.org/02bxrp522","country_code":"US","type":"education","lineage":["https://openalex.org/I2802706902"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ian Lumsden","raw_affiliation_strings":["University of Tennessee Knoxville, Knoxville, USA"],"affiliations":[{"raw_affiliation_string":"University of Tennessee Knoxville, Knoxville, USA","institution_ids":["https://openalex.org/I2802706902","https://openalex.org/I75027704"]}]},{"author_position":"middle","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, Rochester, USA"],"affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology, Rochester, USA","institution_ids":["https://openalex.org/I155173764"]}]},{"author_position":"middle","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, Rochester, USA"],"affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology, Rochester, USA","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, Lemont, USA"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Lemont, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078387820","display_name":"Michela Taufer","orcid":"https://orcid.org/0000-0002-0031-6377"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]},{"id":"https://openalex.org/I2802706902","display_name":"Knoxville College","ror":"https://ror.org/02bxrp522","country_code":"US","type":"education","lineage":["https://openalex.org/I2802706902"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michela Michela Taufer","raw_affiliation_strings":["University of Tennessee Knoxville, Knoxville, USA"],"affiliations":[{"raw_affiliation_string":"University of Tennessee Knoxville, Knoxville, USA","institution_ids":["https://openalex.org/I2802706902","https://openalex.org/I75027704"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5119624308"],"corresponding_institution_ids":["https://openalex.org/I2802706902","https://openalex.org/I75027704"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30132825,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":1.0,"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":1.0,"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":0.9987999796867371,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9980999827384949,"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/scalability","display_name":"Scalability","score":0.6873000264167786},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.6456000208854675},{"id":"https://openalex.org/keywords/merkle-tree","display_name":"Merkle tree","score":0.44020000100135803},{"id":"https://openalex.org/keywords/high-availability","display_name":"High availability","score":0.33559998869895935},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.3091999888420105}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7559000253677368},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6873000264167786},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.6456000208854675},{"id":"https://openalex.org/C205383636","wikidata":"https://www.wikidata.org/wiki/Q14746","display_name":"Merkle tree","level":4,"score":0.44020000100135803},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.43619999289512634},{"id":"https://openalex.org/C65813073","wikidata":"https://www.wikidata.org/wiki/Q1622420","display_name":"High availability","level":2,"score":0.33559998869895935},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.32739999890327454},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.3091999888420105},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2957000136375427},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2700999975204468},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.2678000032901764}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731545.3735116","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731545.3735116","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W4386707668"],"related_works":[],"abstract_inverted_index":{"Efficient":[0],"checkpoint":[1,29,74],"restoration":[2,30,67,75],"is":[3],"critical":[4],"in":[5,52],"high-performance":[6],"computing":[7],"(HPC)":[8],"and":[9,20,36,69,87,95],"AI":[10],"applications,":[11],"where":[12],"slow":[13],"recovery":[14,35,98],"times":[15],"disrupt":[16],"workflows,":[17],"waste":[18],"resources,":[19],"hinder":[21],"reproducibility.":[22],"This":[23],"work":[24,84],"introduces":[25],"a":[26],"Merkle":[27],"tree":[28],"method":[31,40],"to":[32,48],"accelerate":[33],"failure":[34,97],"improve":[37],"explainability.":[38],"Our":[39,83],"integrates":[41],"asynchronous":[42],"I/O":[43],"via":[44],"the":[45,57],"Liburing":[46],"library":[47],"optimize":[49],"scattered":[50],"reads":[51],"HPC":[53],"applications.":[54],"Tested":[55],"on":[56],"Polaris":[58],"system":[59],"at":[60],"Argonne":[61],"National":[62],"Laboratory,":[63],"it":[64],"exhibits":[65],"lower":[66],"time":[68],"memory":[70],"consumption":[71],"than":[72],"state-of-the-art":[73],"methods,":[76],"reaching":[77],"near-full":[78],"efficiency":[79],"with":[80],"duplicated":[81],"data.":[82],"advances":[85],"scalable":[86],"efficient":[88],"checkpointing":[89],"solutions":[90],"for":[91,99],"HPC,":[92],"ensuring":[93],"reliable":[94],"fast":[96],"large-scale":[100],"simulations.":[101]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}
