{"id":"https://openalex.org/W4407216788","doi":"https://doi.org/10.1145/3669940.3707255","title":"PCcheck: Persistent Concurrent Checkpointing for ML","display_name":"PCcheck: Persistent Concurrent Checkpointing for ML","publication_year":2025,"publication_date":"2025-02-06","ids":{"openalex":"https://openalex.org/W4407216788","doi":"https://doi.org/10.1145/3669940.3707255"},"language":"en","primary_location":{"id":"doi:10.1145/3669940.3707255","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3669940.3707255","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 1","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3669940.3707255","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049951876","display_name":"Foteini Strati","orcid":"https://orcid.org/0000-0003-3364-2109"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Foteini Strati","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033895433","display_name":"Michal Friedman","orcid":"https://orcid.org/0009-0003-5588-8617"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Michal Friedman","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000009841","display_name":"Ana Klimovic","orcid":"https://orcid.org/0000-0001-8559-0529"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ana Klimovic","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5049951876"],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":11.3006,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.98076731,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"811","last_page":"827"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9994999766349792,"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/T10772","display_name":"Distributed systems and fault tolerance","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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9959999918937683,"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":0.9926999807357788,"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/computer-science","display_name":"Computer science","score":0.7253255844116211},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3745802044868469},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.35763809084892273},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.33662062883377075}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7253255844116211},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3745802044868469},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.35763809084892273},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.33662062883377075}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3669940.3707255","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3669940.3707255","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 1","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3669940.3707255","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3669940.3707255","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 1","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1970958679","https://openalex.org/W1976573677","https://openalex.org/W1990176279","https://openalex.org/W1993143336","https://openalex.org/W2052915895","https://openalex.org/W2071414195","https://openalex.org/W2100970777","https://openalex.org/W2131053137","https://openalex.org/W2166263713","https://openalex.org/W2194775991","https://openalex.org/W2443378670","https://openalex.org/W2901994046","https://openalex.org/W2919115771","https://openalex.org/W3081168214","https://openalex.org/W3129831491","https://openalex.org/W3209503812","https://openalex.org/W4214590593","https://openalex.org/W4220741164","https://openalex.org/W4287328644","https://openalex.org/W4289646389","https://openalex.org/W4310491421","https://openalex.org/W4310491431","https://openalex.org/W4372267133","https://openalex.org/W4380881139","https://openalex.org/W4387302750","https://openalex.org/W4394923484"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Training":[0],"large-scale":[1],"machine":[2],"learning":[3],"(ML)":[4],"models":[5],"is":[6,64,91],"expensive":[7],"and":[8,24,69],"time-intensive,":[9],"consuming":[10],"many":[11],"hardware":[12,22],"accelerators":[13],"for":[14],"days":[15],"or":[16],"weeks.":[17],"As":[18],"the":[19,30,53],"scale":[20],"of":[21,32,55],"deployments":[23],"training":[25,68],"time":[26],"continue":[27],"to":[28,38,47,60,65,73,93],"grow,":[29],"probability":[31],"failures":[33,63],"also":[34,50],"increases.":[35],"The":[36,57],"desire":[37],"use":[39],"cheaper":[40],"cloud":[41],"resources,":[42],"such":[43],"as":[44],"spot":[45],"VMs,":[46],"lower":[48],"costs":[49],"dramatically":[51],"increases":[52],"frequency":[54],"failures.":[56],"standard":[58],"approach":[59],"deal":[61],"with":[62],"periodically":[66],"pause":[67],"checkpoint":[70],"model":[71],"parameters":[72],"persistent":[74],"storage.":[75],"Unfortunately,":[76],"today's":[77],"checkpointing":[78,90],"mechanisms":[79],"introduce":[80],"high":[81,86],"overhead":[82],"when":[83],"applied":[84],"at":[85],"frequencies,":[87],"yet":[88],"frequent":[89],"necessary":[92],"avoid":[94],"long":[95],"recovery":[96],"times.":[97]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}
