{"id":"https://openalex.org/W7168039632","doi":"https://doi.org/10.1145/3806645.3816239","title":"Towards Transparent Checkpointing with AI-driven Code Generation","display_name":"Towards Transparent Checkpointing with AI-driven Code Generation","publication_year":2026,"publication_date":"2026-07-11","ids":{"openalex":"https://openalex.org/W7168039632","doi":"https://doi.org/10.1145/3806645.3816239"},"language":null,"primary_location":{"id":"doi:10.1145/3806645.3816239","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3806645.3816239","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 35th International Symposium on High-Performance Parallel and Distributed Computing","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/A5101994317","display_name":"Hai Thanh Nguyen","orcid":"https://orcid.org/0000-0003-4177-0493"},"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":"Hai Duc Nguyen","raw_affiliation_strings":["Argonne National Laboratory, Lemont, IL, USA"],"raw_orcid":"https://orcid.org/0000-0003-4177-0493","affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Lemont, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038566298","display_name":"Tekin Bi\u00e7er","orcid":"https://orcid.org/0000-0002-8428-5159"},"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":"Tekin Bicer","raw_affiliation_strings":["Argonne National Laboratory, Lemont, IL, USA"],"raw_orcid":"https://orcid.org/0000-0002-8428-5159","affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Lemont, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065464552","display_name":"Kyle Chard","orcid":"https://orcid.org/0000-0002-7370-4805"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyle Chard","raw_affiliation_strings":["University of Chicago, Chicago, IL, USA"],"raw_orcid":"https://orcid.org/0000-0002-7370-4805","affiliations":[{"raw_affiliation_string":"University of Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I39422238","https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032231503","display_name":"Ian Foster","orcid":"https://orcid.org/0000-0003-2129-5269"},"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"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ian Foster","raw_affiliation_strings":["University of Chicago and Argonne National Laboratory, Chicago, IL, USA"],"raw_orcid":"https://orcid.org/0000-0003-2129-5269","affiliations":[{"raw_affiliation_string":"University of Chicago and Argonne National Laboratory, Chicago, IL, USA","institution_ids":["https://openalex.org/I1282105669","https://openalex.org/I40347166"]}]},{"author_position":"last","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, IL, USA"],"raw_orcid":"https://orcid.org/0000-0002-0661-7509","affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Lemont, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.96043866,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"760","last_page":"765"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.8492000102996826,"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":0.8492000102996826,"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":0.06700000166893005,"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/T11005","display_name":"Radiation Effects in Electronics","score":0.028599999845027924,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"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/benchmark","display_name":"Benchmark (surveying)","score":0.5996000170707703},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5964000225067139},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5590000152587891},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5583000183105469},{"id":"https://openalex.org/keywords/resilience","display_name":"Resilience (materials science)","score":0.5461000204086304},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.48890000581741333},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.4544000029563904},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.44699999690055847},{"id":"https://openalex.org/keywords/machine-code","display_name":"Machine code","score":0.3671000003814697}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7907000184059143},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5996000170707703},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5964000225067139},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5590000152587891},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5583000183105469},{"id":"https://openalex.org/C2779585090","wikidata":"https://www.wikidata.org/wiki/Q3457762","display_name":"Resilience (materials science)","level":2,"score":0.5461000204086304},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.48890000581741333},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.4544000029563904},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.44699999690055847},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.415800005197525},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3736000061035156},{"id":"https://openalex.org/C115168132","wikidata":"https://www.wikidata.org/wiki/Q55813","display_name":"Machine code","level":3,"score":0.3671000003814697},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.36039999127388},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.35010001063346863},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3334999978542328},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.33309999108314514},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3330000042915344},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.32330000400543213},{"id":"https://openalex.org/C90329073","wikidata":"https://www.wikidata.org/wiki/Q914232","display_name":"Ask price","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3156999945640564},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C85687889","wikidata":"https://www.wikidata.org/wiki/Q445962","display_name":"Legacy code","level":3,"score":0.2865999937057495},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C51929080","wikidata":"https://www.wikidata.org/wiki/Q2425187","display_name":"Codebase","level":3,"score":0.262800008058548},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2605000138282776},{"id":"https://openalex.org/C98183937","wikidata":"https://www.wikidata.org/wiki/Q2112188","display_name":"Program analysis","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3806645.3816239","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3806645.3816239","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 35th International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G102163711","display_name":null,"funder_award_id":"DE\u2010 AC02\u201006CH11357","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G5884270826","display_name":null,"funder_award_id":"CSSI-2411386","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1133087070","https://openalex.org/W1584278023","https://openalex.org/W1981432246","https://openalex.org/W1984564341","https://openalex.org/W2033656974","https://openalex.org/W2114035455","https://openalex.org/W2116115793","https://openalex.org/W2133046454","https://openalex.org/W2139244298","https://openalex.org/W2961595369","https://openalex.org/W2964624821","https://openalex.org/W2983517508","https://openalex.org/W3025571086","https://openalex.org/W3030255514","https://openalex.org/W3046229946","https://openalex.org/W3201073812","https://openalex.org/W3216052173","https://openalex.org/W4241332380","https://openalex.org/W4385623144","https://openalex.org/W4386707668","https://openalex.org/W4393973206","https://openalex.org/W4399427731","https://openalex.org/W4399757647","https://openalex.org/W4402673683"],"related_works":[],"abstract_inverted_index":{"Adding":[0],"reliable":[1],"checkpoint/restart":[2,81,121],"support":[3],"to":[4,119],"an":[5,56],"MPI":[6,46],"scientific":[7,75],"application":[8,21,62],"is":[9,132],"a":[10,27,42,137],"time-consuming":[11],"expert":[12],"effort":[13],"that":[14,126],"requires":[15],"deep":[16],"knowledge":[17],"of":[18,45,107,140],"both":[19],"the":[20,70,77],"and":[22,51,54,110],"resilience.":[23],"We":[24,40],"ask":[25],"whether":[26],"frontier":[28],"large":[29],"language":[30],"model":[31],"can":[32],"perform":[33],"this":[34],"work":[35],"end-to-end":[36,128],"without":[37],"human":[38],"intervention.":[39],"assemble":[41],"benchmark":[43],"suite":[44],"applications":[47,109],"spanning":[48],"diverse":[49],"domains":[50],"computation":[52],"patterns,":[53],"drive":[55],"iterative":[57],"code-generation":[58],"loop":[59],"for":[60,136],"each":[61],"using":[63],"Anthropic\u2019s":[64],"Claude":[65],"Opus":[66],"4.7":[67],"invoked":[68],"through":[69],"OpenCode":[71],"CLI.":[72],"Across":[73],"six":[74,108],"applications,":[76],"LLM":[78],"generates":[79],"working":[80],"code":[82,97],"in":[83],"50":[84],"minutes":[85],"on":[86,105],"average":[87],"while":[88],"consuming":[89],"3.4":[90],"M":[91],"tokens":[92],"per":[93],"application.":[94],"The":[95],"generated":[96],"adds":[98],"negligible":[99],"overhead":[100],"during":[101],"normal":[102],"failure-free":[103],"execution":[104],"five":[106],"recovers":[111],"from":[112],"injected":[113],"process":[114],"failures":[115],"with":[116],"efficiency":[117],"comparable":[118],"human-engineered":[120],"implementations.":[122],"These":[123],"results":[124],"suggest":[125],"automated":[127],"LLM-driven":[129],"resilience":[130],"engineering":[131],"technically":[133],"viable":[134],"today":[135],"meaningful":[138],"fraction":[139],"HPC":[141],"applications.":[142]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2026-07-12T00:00:00"}
