{"id":"https://openalex.org/W4408092563","doi":"https://doi.org/10.1109/hipcw63042.2024.00026","title":"Towards Continuous Checkpointing for HPC Systems Using CXL","display_name":"Towards Continuous Checkpointing for HPC Systems Using CXL","publication_year":2024,"publication_date":"2024-12-18","ids":{"openalex":"https://openalex.org/W4408092563","doi":"https://doi.org/10.1109/hipcw63042.2024.00026"},"language":"en","primary_location":{"id":"doi:10.1109/hipcw63042.2024.00026","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipcw63042.2024.00026","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 31st International Conference on High Performance Computing, Data and Analytics Workshop (HiPCW)","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/A5015298045","display_name":"Ellis Giles","orcid":"https://orcid.org/0000-0002-0247-3587"},"institutions":[{"id":"https://openalex.org/I4210105265","display_name":"Altex Technologies Corporation (United States)","ror":"https://ror.org/00tf8zn82","country_code":"US","type":"company","lineage":["https://openalex.org/I4210105265"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ellis Giles","raw_affiliation_strings":["Elex Technologies,Houston,Texas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Elex Technologies,Houston,Texas","institution_ids":["https://openalex.org/I4210105265"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081334414","display_name":"Peter Varman","orcid":"https://orcid.org/0000-0001-6887-1644"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Varman","raw_affiliation_strings":["Rice University,Houston,Texas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rice University,Houston,Texas","institution_ids":["https://openalex.org/I74775410"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":"90","last_page":"97"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9993000030517578,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9993000030517578,"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":0.9987999796867371,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9986000061035156,"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":0.7378950119018555},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4462757706642151},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3762052059173584},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3633159399032593},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.33281317353248596},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.32616788148880005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7378950119018555},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4462757706642151},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3762052059173584},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3633159399032593},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.33281317353248596},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.32616788148880005}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hipcw63042.2024.00026","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipcw63042.2024.00026","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 31st International Conference on High Performance Computing, Data and Analytics Workshop (HiPCW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1939822385","https://openalex.org/W2017060126","https://openalex.org/W2096504919","https://openalex.org/W2108208207","https://openalex.org/W2485382745","https://openalex.org/W2731397968","https://openalex.org/W2798289565","https://openalex.org/W2904341006","https://openalex.org/W2998121608","https://openalex.org/W3015213502","https://openalex.org/W3091118029","https://openalex.org/W3094386879","https://openalex.org/W3141239549","https://openalex.org/W3154960815","https://openalex.org/W3198669718","https://openalex.org/W4254568056","https://openalex.org/W4316660797","https://openalex.org/W4317928111","https://openalex.org/W4318541517","https://openalex.org/W4320060543","https://openalex.org/W4383749486","https://openalex.org/W4388561296","https://openalex.org/W4399677840","https://openalex.org/W4399757647","https://openalex.org/W4399772343","https://openalex.org/W4401353403"],"related_works":["https://openalex.org/W2384867379","https://openalex.org/W4400094300","https://openalex.org/W2329539859","https://openalex.org/W2227905990","https://openalex.org/W2765823764","https://openalex.org/W3214280620","https://openalex.org/W3191490922","https://openalex.org/W2794038527","https://openalex.org/W2327638088","https://openalex.org/W1599154403"],"abstract_inverted_index":{"Throughout":[0],"the":[1,5,18,27,65,80],"modern":[2,72],"computing":[3,9],"era,":[4],"complexity":[6,33],"of":[7,17,20,29,77],"high-performance":[8],"systems":[10,73],"has":[11],"increased":[12],"exponentially,":[13],"both":[14],"in":[15,110,170],"terms":[16],"number":[19,28],"nodes":[21,102,154],"contained":[22],"within":[23],"a":[24,43,49,58,75,88,107,130,135,167],"system":[25,38,81,96,111,171,185],"and":[26,85,128,155,176],"transistors.":[30],"This":[31],"exponential":[32],"increase":[34,169],"introduces":[35],"probabilities":[36],"for":[37,120,161],"failures":[39,53],"that":[40],"may":[41,61],"affect":[42],"single":[44,59],"node":[45],"or":[46,63],"element":[47],"on":[48],"node.":[50],"If":[51],"these":[52,69],"are":[54],"not":[55],"properly":[56],"mitigated,":[57],"failure":[60,89,131],"disrupt":[62],"halt":[64],"entire":[66,95],"system.To":[67],"address":[68],"potential":[70],"failures,":[71],"implement":[74],"form":[76],"checkpointing,":[78,175],"whereby":[79],"state":[82,151],"is":[83],"saved":[84],"restarted":[86],"if":[87,129],"occurs.":[90],"However,":[91],"synchronous":[92],"checkpointing":[93],"an":[94,124,183],"pre-failure":[97],"can":[98],"be":[99],"costly,":[100],"requiring":[101],"to":[103,134,147,152,158,182],"wait,":[104],"often":[105],"causing":[106],"significant":[108,168],"decrease":[109],"application":[112],"performance.In":[113],"this":[114],"work,":[115],"we":[116],"introduce":[117],"Continuous":[118],"Checkpointing":[119],"HPC":[121],"Systems,":[122],"creating":[123],"asynchronous":[125],"continuous":[126],"checkpoint,":[127],"occurs,":[132],"revert":[133],"consistent":[136],"global":[137],"checkpoint.":[138],"We":[139],"utilize":[140],"emerging":[141],"Compute":[142],"eXpress":[143],"Link":[144],"(CXL)":[145],"Memory":[146],"lazily":[148],"post":[149],"computational":[150],"nearby":[153],"allow":[156],"users":[157],"trade":[159],"space":[160],"time":[162],"efficiently.":[163],"Our":[164],"methods":[165],"show":[166],"utilization":[172],"over":[173],"traditional":[174],"our":[177],"lightweight":[178],"method":[179],"performs":[180],"close":[181],"unsafe":[184],"with":[186],"no":[187],"checkpoints.":[188]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
