{"id":"https://openalex.org/W4404385775","doi":"https://doi.org/10.1145/3698038.3698510","title":"On-demand and Parallel Checkpoint/Restore for GPU Applications","display_name":"On-demand and Parallel Checkpoint/Restore for GPU Applications","publication_year":2024,"publication_date":"2024-11-14","ids":{"openalex":"https://openalex.org/W4404385775","doi":"https://doi.org/10.1145/3698038.3698510"},"language":"en","primary_location":{"id":"doi:10.1145/3698038.3698510","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3698038.3698510","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3698038.3698510?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Symposium on Cloud Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3698038.3698510?download=true","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108854086","display_name":"Y. Yang","orcid":"https://orcid.org/0009-0001-7910-9644"},"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":true,"raw_author_name":"Yanning Yang","raw_affiliation_strings":["Institute of Parallel and Distributed Systems, SEIEE, Shanghai Jiao Tong University and Engineering Research Center for Domain-specific Operating Systems, Ministry of Education"],"affiliations":[{"raw_affiliation_string":"Institute of Parallel and Distributed Systems, SEIEE, Shanghai Jiao Tong University and Engineering Research Center for Domain-specific Operating Systems, Ministry of Education","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102829139","display_name":"Dong Du","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":"Dong Du","raw_affiliation_strings":["Institute of Parallel and Distributed Systems, SEIEE, Shanghai Jiao Tong University and Engineering Research Center for Domain-specific Operating Systems, Ministry of Education"],"affiliations":[{"raw_affiliation_string":"Institute of Parallel and Distributed Systems, SEIEE, Shanghai Jiao Tong University and Engineering Research Center for Domain-specific Operating Systems, Ministry of Education","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100775399","display_name":"Haitao Song","orcid":"https://orcid.org/0000-0003-2113-2224"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haitao Song","raw_affiliation_strings":["Shanghai Artificial Intelligence Research Institute, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Research Institute, Shanghai, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026023746","display_name":"Yubin Xia","orcid":"https://orcid.org/0000-0001-6558-5298"},"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":"Yubin Xia","raw_affiliation_strings":["Institute of Parallel and Distributed Systems, SEIEE, Shanghai Jiao Tong University and Engineering Research Center for Domain-specific Operating Systems, Ministry of Education"],"affiliations":[{"raw_affiliation_string":"Institute of Parallel and Distributed Systems, SEIEE, Shanghai Jiao Tong University and Engineering Research Center for Domain-specific Operating Systems, Ministry of Education","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5108854086"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":2.9628,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.92858036,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"415","last_page":"433"},"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/T11181","display_name":"Advanced Data Storage Technologies","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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9988999962806702,"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/computer-science","display_name":"Computer science","score":0.670162558555603},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6352348327636719}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.670162558555603},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6352348327636719}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3698038.3698510","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3698038.3698510","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3698038.3698510?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Symposium on Cloud Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3698038.3698510","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3698038.3698510","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3698038.3698510?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Symposium on Cloud Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2080338196","display_name":null,"funder_award_id":"SFYF at SJTU","funder_id":"https://openalex.org/F4320322999","funder_display_name":"Shanghai Jiao Tong University"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2174588366","display_name":null,"funder_award_id":"62302300","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2376276132","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G2802911279","display_name":null,"funder_award_id":"Young","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4009049029","display_name":null,"funder_award_id":"Startup","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322999","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404385775.pdf"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W2087866311","https://openalex.org/W2734941459","https://openalex.org/W2982157693","https://openalex.org/W3003011076","https://openalex.org/W3012028616","https://openalex.org/W3022548332","https://openalex.org/W3097411828","https://openalex.org/W3112094022","https://openalex.org/W3125961627","https://openalex.org/W3130689885","https://openalex.org/W3153413990","https://openalex.org/W3155705005","https://openalex.org/W3204216247","https://openalex.org/W3207498965","https://openalex.org/W3209259988","https://openalex.org/W4214512541","https://openalex.org/W4214610523","https://openalex.org/W4214690606","https://openalex.org/W4214764640","https://openalex.org/W4220796798","https://openalex.org/W4220848902","https://openalex.org/W4237820058","https://openalex.org/W4244652618","https://openalex.org/W4285504009","https://openalex.org/W4372263604","https://openalex.org/W4388040948","https://openalex.org/W4388041447","https://openalex.org/W4394871711"],"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":{"Leveraging":[0],"serverless":[1,31,53,99],"computing":[2],"for":[3,18,91,97],"cloud-based":[4],"machine":[5],"learning":[6],"services":[7],"is":[8,54],"on":[9,22,39],"the":[10,87],"rise,":[11],"promising":[12],"cost-efficiency":[13],"and":[14,25,103,108,116],"flexibility":[15],"are":[16],"crucial":[17],"ML":[19],"applications":[20],"relying":[21],"high-performance":[23],"GPUs":[24,37],"substantial":[26],"memory.":[27],"However,":[28],"despite":[29],"modern":[30],"platforms":[32],"handling":[33],"diverse":[34],"devices":[35],"like":[36,65,101],"seamlessly":[38],"a":[40,43,49],"pay-as-you-go":[41],"basis,":[42],"longstanding":[44],"challenge":[45],"remains:":[46],"startup":[47,77],"latency,":[48],"well-studied":[50],"issue":[51],"when":[52],"CPU-centric.":[55],"For":[56,70],"example,":[57],"initializing":[58],"GPU":[59,63],"apps":[60],"with":[61],"minor":[62],"models,":[64],"MobileNet,":[66],"demands":[67],"several":[68],"seconds.":[69],"more":[71],"intricate":[72],"models":[73],"such":[74],"as":[75],"GPT-2,":[76],"latency":[78],"can":[79],"escalate":[80],"to":[81,112],"around":[82],"10":[83],"seconds,":[84],"vastly":[85],"overshadowing":[86],"short":[88],"computation":[89],"time":[90],"GPU-based":[92],"inference.":[93],"Prior":[94],"solutions":[95],"tailored":[96],"CPU":[98],"setups,":[100],"fork()":[102],"Checkpoint/Restore,":[104],"cannot":[105],"be":[106],"directly":[107],"effectively":[109],"applied":[110],"due":[111],"differences":[113],"between":[114],"CPUs":[115],"GPUs.":[117]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5}],"updated_date":"2026-03-25T14:56:36.534964","created_date":"2025-10-10T00:00:00"}