{"id":"https://openalex.org/W4414735816","doi":"https://doi.org/10.1145/3731569.3764813","title":"PhoenixOS: Concurrent OS-level GPU Checkpoint and Restore with Validated Speculation","display_name":"PhoenixOS: Concurrent OS-level GPU Checkpoint and Restore with Validated Speculation","publication_year":2025,"publication_date":"2025-10-01","ids":{"openalex":"https://openalex.org/W4414735816","doi":"https://doi.org/10.1145/3731569.3764813"},"language":"en","primary_location":{"id":"doi:10.1145/3731569.3764813","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731569.3764813","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM SIGOPS 31st Symposium on Operating Systems Principles","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/A5002957327","display_name":"Xingda Wei","orcid":"https://orcid.org/0000-0003-4983-6047"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingda Wei","raw_affiliation_strings":["Institute of Parallel and Distributed Systems, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-4983-6047","affiliations":[{"raw_affiliation_string":"Institute of Parallel and Distributed Systems, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027174779","display_name":"Zhuobin Huang","orcid":"https://orcid.org/0009-0005-2251-4146"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhuobin Huang","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0005-2251-4146","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tianle Sun","orcid":"https://orcid.org/0009-0004-0083-6964"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianle Sun","raw_affiliation_strings":["Institute of Parallel and Distributed Systems, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0004-0083-6964","affiliations":[{"raw_affiliation_string":"Institute of Parallel and Distributed Systems, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104310168","display_name":"Yingyi Hao","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingyi Hao","raw_affiliation_strings":["Institute of Parallel and Distributed Systems, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0007-8042-0863","affiliations":[{"raw_affiliation_string":"Institute of Parallel and Distributed Systems, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101543146","display_name":"Rong Chen","orcid":"https://orcid.org/0000-0002-6115-8130"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rong Chen","raw_affiliation_strings":["Institute of Parallel and Distributed Systems, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-6115-8130","affiliations":[{"raw_affiliation_string":"Institute of Parallel and Distributed Systems, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030930550","display_name":"Mingcong Han","orcid":"https://orcid.org/0009-0008-1536-7485"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingcong Han","raw_affiliation_strings":["Institute of Parallel and Distributed Systems, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-1536-7485","affiliations":[{"raw_affiliation_string":"Institute of Parallel and Distributed Systems, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102847820","display_name":"Jinyu Gu","orcid":"https://orcid.org/0000-0002-8112-8481"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinyu Gu","raw_affiliation_strings":["Institute of Parallel and Distributed Systems, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8112-8481","affiliations":[{"raw_affiliation_string":"Institute of Parallel and Distributed Systems, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100406215","display_name":"Haibo Chen","orcid":"https://orcid.org/0000-0002-9720-0361"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haibo Chen","raw_affiliation_strings":["Institute of Parallel and Distributed Systems, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-9720-0361","affiliations":[{"raw_affiliation_string":"Institute of Parallel and Distributed Systems, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.5452,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.95210652,"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":"996","last_page":"1013"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9998000264167786,"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/T10933","display_name":"Real-Time Systems Scheduling","score":0.9984999895095825,"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/process","display_name":"Process (computing)","score":0.58160001039505},{"id":"https://openalex.org/keywords/speculation","display_name":"Speculation","score":0.40689998865127563},{"id":"https://openalex.org/keywords/tracing","display_name":"Tracing","score":0.3919999897480011},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.321399986743927},{"id":"https://openalex.org/keywords/service","display_name":"Service (business)","score":0.32109999656677246},{"id":"https://openalex.org/keywords/rollback","display_name":"Rollback","score":0.31520000100135803},{"id":"https://openalex.org/keywords/concurrency-control","display_name":"Concurrency control","score":0.3098999857902527}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8109999895095825},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.58160001039505},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4471000134944916},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4453999996185303},{"id":"https://openalex.org/C47941915","wikidata":"https://www.wikidata.org/wiki/Q107885","display_name":"Speculation","level":2,"score":0.40689998865127563},{"id":"https://openalex.org/C138673069","wikidata":"https://www.wikidata.org/wiki/Q322229","display_name":"Tracing","level":2,"score":0.3919999897480011},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.35530000925064087},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3321000039577484},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.321399986743927},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.32109999656677246},{"id":"https://openalex.org/C174220543","wikidata":"https://www.wikidata.org/wiki/Q395307","display_name":"Rollback","level":3,"score":0.31520000100135803},{"id":"https://openalex.org/C84511453","wikidata":"https://www.wikidata.org/wiki/Q2914952","display_name":"Concurrency control","level":3,"score":0.3098999857902527},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2939999997615814},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.2924000024795532},{"id":"https://openalex.org/C193702766","wikidata":"https://www.wikidata.org/wiki/Q1414548","display_name":"Concurrency","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.28679999709129333},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.2703999876976013},{"id":"https://openalex.org/C150495011","wikidata":"https://www.wikidata.org/wiki/Q128392","display_name":"Concurrent computing","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.25780001282691956}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731569.3764813","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731569.3764813","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM SIGOPS 31st Symposium on Operating Systems Principles","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W2074787299","https://openalex.org/W2100970777","https://openalex.org/W2234512370","https://openalex.org/W2342083136","https://openalex.org/W2990714382","https://openalex.org/W4205983429","https://openalex.org/W4239652717","https://openalex.org/W4244652618","https://openalex.org/W4376272906","https://openalex.org/W4404343279"],"related_works":[],"abstract_inverted_index":{"PhoenixOS":[0],"(PhOS)":[1],"is":[2,33],"the":[3],"first":[4],"OS":[5],"service":[6],"that":[7],"can":[8],"concurrently":[9],"checkpoint":[10],"and":[11,27,56,66],"restore":[12],"(C/R)":[13],"GPU":[14],"processes\u2014a":[15],"fundamental":[16],"capability":[17],"for":[18,50],"critical":[19],"tasks":[20],"such":[21,58],"as":[22,59],"fault":[23],"tolerance,":[24],"process":[25],"migration,":[26],"fast":[28],"startup.":[29],"While":[30],"concurrent":[31,53],"C/R":[32],"well-established":[34],"on":[35,41],"CPUs,":[36],"it":[37],"poses":[38],"unique":[39],"challenges":[40],"GPUs":[42],"due":[43],"to":[44],"their":[45],"lack":[46],"of":[47],"essential":[48],"features":[49],"efficiently":[51],"tracing":[52],"memory":[54],"reads":[55],"writes,":[57],"specific":[60],"hardware":[61],"capabilities":[62],"(e.g.,":[63,70],"dirty":[64],"bits)":[65],"OS-mediated":[67],"data":[68],"paths":[69],"copy-on-write).":[71]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}