{"id":"https://openalex.org/W4415003933","doi":"https://doi.org/10.1145/3725783.3764394","title":"Indispensable CPU-centric Checkpointing for GPUs","display_name":"Indispensable CPU-centric Checkpointing for GPUs","publication_year":2025,"publication_date":"2025-10-09","ids":{"openalex":"https://openalex.org/W4415003933","doi":"https://doi.org/10.1145/3725783.3764394"},"language":"en","primary_location":{"id":"doi:10.1145/3725783.3764394","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3725783.3764394","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM SIGOPS Asia-Pacific Workshop on Systems","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/A5111120864","display_name":"Junzhe Li","orcid":"https://orcid.org/0009-0000-9026-9617"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Junzhe Li","raw_affiliation_strings":["The University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0009-0000-9026-9617","affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008757709","display_name":"Ran Shu","orcid":"https://orcid.org/0000-0002-2021-4917"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ran Shu","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2021-4917","affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102833929","display_name":"Ziyue Yang","orcid":"https://orcid.org/0009-0008-0491-7082"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyue Yang","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-0491-7082","affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066106377","display_name":"Shuotao Xu","orcid":"https://orcid.org/0009-0000-8593-5443"},"institutions":[{"id":"https://openalex.org/I4210153468","display_name":"Microsoft (Canada)","ror":"https://ror.org/04xhxg104","country_code":"CA","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210153468"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Shuotao Xu","raw_affiliation_strings":["Microsoft Research, Vancouver, Canada"],"raw_orcid":"https://orcid.org/0009-0000-8593-5443","affiliations":[{"raw_affiliation_string":"Microsoft Research, Vancouver, Canada","institution_ids":["https://openalex.org/I4210153468"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071764813","display_name":"Chenxiong Qian","orcid":"https://orcid.org/0000-0002-6201-6011"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chenxiong Qian","raw_affiliation_strings":["The University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-6201-6011","affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633","https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100735357","display_name":"Yongqiang Xiong","orcid":"https://orcid.org/0000-0003-4175-0097"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongqiang Xiong","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4175-0097","affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"115","last_page":"123"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9991000294685364,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9977999925613403,"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/pci-express","display_name":"PCI Express","score":0.7027999758720398},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.6851999759674072},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6717000007629395},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6173999905586243},{"id":"https://openalex.org/keywords/resilience","display_name":"Resilience (materials science)","score":0.48179998993873596},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.38670000433921814},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.30379998683929443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8066999912261963},{"id":"https://openalex.org/C64270927","wikidata":"https://www.wikidata.org/wiki/Q206924","display_name":"PCI Express","level":3,"score":0.7027999758720398},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6851999759674072},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6717000007629395},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6173999905586243},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5394999980926514},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.506600022315979},{"id":"https://openalex.org/C2779585090","wikidata":"https://www.wikidata.org/wiki/Q3457762","display_name":"Resilience (materials science)","level":2,"score":0.48179998993873596},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.38670000433921814},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.30379998683929443},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.30239999294281006},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.296099990606308},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.289900004863739},{"id":"https://openalex.org/C2994168587","wikidata":"https://www.wikidata.org/wiki/Q5295","display_name":"Random access memory","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C2780154230","wikidata":"https://www.wikidata.org/wiki/Q513420","display_name":"Undo","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2517000138759613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3725783.3764394","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3725783.3764394","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM SIGOPS Asia-Pacific Workshop on Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322170","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86"},{"id":"https://openalex.org/F4320333993","display_name":"Microsoft Research Asia","ror":"https://ror.org/0300m5276"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W1493774699","https://openalex.org/W2734941459","https://openalex.org/W2767239597","https://openalex.org/W2975712713","https://openalex.org/W3206357538","https://openalex.org/W4283395684","https://openalex.org/W4318541614","https://openalex.org/W4387302750","https://openalex.org/W4390263770","https://openalex.org/W4394923484","https://openalex.org/W4399757647","https://openalex.org/W4401176820","https://openalex.org/W4407216788","https://openalex.org/W4408847328","https://openalex.org/W4413756980"],"related_works":[],"abstract_inverted_index":{"Checkpointing":[0],"is":[1,67],"a":[2,15],"special":[3],"task":[4],"in":[5,110],"the":[6,40,48,54,62,85,90,96],"modern":[7],"deep":[8],"learning":[9],"training":[10,19,41,56],"process":[11,42],"as":[12,70],"it":[13,45,71],"poses":[14],"hard":[16],"tradeoff":[17],"between":[18,77],"efficiency":[20],"and":[21,79],"reliability.":[22],"Frequent":[23],"checkpoints":[24,37],"of":[25,87],"model":[26],"states":[27],"can":[28],"enhance":[29],"resilience":[30],"to":[31,43,94],"random":[32],"system":[33],"failures,":[34],"yet":[35],"obtaining":[36],"must":[38],"halt":[39],"prevent":[44],"from":[46],"updating":[47],"model,":[49],"which,":[50],"however,":[51],"inevitably":[52],"hurts":[53],"overall":[55],"efficiency.":[57],"To":[58],"mitigate":[59],"this":[60,82],"dilemma,":[61],"GPUDirect":[63],"storage":[64],"(GDS)":[65],"technique":[66,83],"gaining":[68],"attention":[69],"enables":[72],"direct":[73],"PCIe":[74,92],"peer-to-peer":[75],"accesses":[76],"SSDs":[78],"GPUs.":[80],"Conceptually,":[81],"has":[84,105],"potential":[86],"fully":[88],"exploiting":[89],"high":[91],"bandwidth":[93],"accelerate":[95],"checkpointing":[97],"process.":[98],"Nevertheless,":[99],"despite":[100],"its":[101],"promising":[102],"features,":[103],"GDS":[104],"not":[106],"seen":[107],"wide":[108],"deployment":[109],"production.":[111]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}