{"id":"https://openalex.org/W2950588976","doi":"https://doi.org/10.1145/3330345.3330361","title":"GPU snapshot","display_name":"GPU snapshot","publication_year":2019,"publication_date":"2019-06-18","ids":{"openalex":"https://openalex.org/W2950588976","doi":"https://doi.org/10.1145/3330345.3330361","mag":"2950588976"},"language":"en","primary_location":{"id":"doi:10.1145/3330345.3330361","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3330345.3330361","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 International Conference on Supercomputing","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/A5065141395","display_name":"Kyushick Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyushick Lee","raw_affiliation_strings":["University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076752182","display_name":"Michael B. Sullivan","orcid":"https://orcid.org/0000-0001-6537-2065"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael B. Sullivan","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054590774","display_name":"Siva Kumar Sastry Hari","orcid":"https://orcid.org/0000-0001-8346-7981"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siva Kumar Sastry Hari","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027550136","display_name":"Timothy Tsai","orcid":"https://orcid.org/0000-0001-8190-675X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Timothy Tsai","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063354509","display_name":"Stephen W. Keckler","orcid":"https://orcid.org/0000-0001-6701-6099"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stephen W. Keckler","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013680653","display_name":"Mattan Erez","orcid":"https://orcid.org/0000-0002-1567-4097"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mattan Erez","raw_affiliation_strings":["University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"171","last_page":"183"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/snapshot","display_name":"Snapshot (computer storage)","score":0.874294638633728},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8531342148780823},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5055532455444336},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.4890349805355072},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.4742031395435333},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.46098408102989197},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4289153814315796},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.34837013483047485}],"concepts":[{"id":"https://openalex.org/C55282118","wikidata":"https://www.wikidata.org/wiki/Q252683","display_name":"Snapshot (computer storage)","level":2,"score":0.874294638633728},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8531342148780823},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5055532455444336},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.4890349805355072},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4742031395435333},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.46098408102989197},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4289153814315796},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.34837013483047485},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3330345.3330361","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3330345.3330361","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 International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.9100000262260437}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1446278828","https://openalex.org/W1499782454","https://openalex.org/W1537929875","https://openalex.org/W1815088304","https://openalex.org/W1965370830","https://openalex.org/W1974534679","https://openalex.org/W1984564341","https://openalex.org/W1997269120","https://openalex.org/W1999900893","https://openalex.org/W2009164607","https://openalex.org/W2014413779","https://openalex.org/W2023324599","https://openalex.org/W2025024269","https://openalex.org/W2031260715","https://openalex.org/W2036473597","https://openalex.org/W2051114618","https://openalex.org/W2056583598","https://openalex.org/W2058121221","https://openalex.org/W2085396034","https://openalex.org/W2095487435","https://openalex.org/W2100970777","https://openalex.org/W2102922928","https://openalex.org/W2106579652","https://openalex.org/W2113809909","https://openalex.org/W2123646449","https://openalex.org/W2127510911","https://openalex.org/W2133834148","https://openalex.org/W2142950726","https://openalex.org/W2144554431","https://openalex.org/W2148109481","https://openalex.org/W2153985054","https://openalex.org/W2156204788","https://openalex.org/W2162351670","https://openalex.org/W2165022815","https://openalex.org/W2165751385","https://openalex.org/W2169164058","https://openalex.org/W2254416046","https://openalex.org/W2330672121","https://openalex.org/W2528323462","https://openalex.org/W2623640553","https://openalex.org/W2626726782","https://openalex.org/W2735399376","https://openalex.org/W2761412899","https://openalex.org/W2767352027","https://openalex.org/W2886094133","https://openalex.org/W2902041647"],"related_works":["https://openalex.org/W2384867379","https://openalex.org/W3214280620","https://openalex.org/W2329539859","https://openalex.org/W3191490922","https://openalex.org/W2765823764","https://openalex.org/W2227905990","https://openalex.org/W2079244304","https://openalex.org/W2794038527","https://openalex.org/W1588481459","https://openalex.org/W1599154403"],"abstract_inverted_index":{"Future":[0],"High-Performance":[1],"Computing":[2],"(HPC)":[3],"systems":[4],"will":[5],"likely":[6],"be":[7,90],"composed":[8],"of":[9,41,112,139,145,172],"accelerator-dense":[10,30],"heterogeneous":[11],"computers":[12],"because":[13,36],"accelerators":[14,44,52],"are":[15],"able":[16],"to":[17,60,78,89,99,119,168],"deliver":[18],"higher":[19],"performance":[20,171],"at":[21,53,157],"lower":[22],"costs,":[23],"socket":[24],"counts":[25],"and":[26,71,115,123,134],"energy":[27],"consumption.":[28],"Such":[29],"nodes":[31],"pose":[32],"a":[33,38,62,85,129,146,163,173],"reliability":[34],"challenge":[35],"preserving":[37],"large":[39],"amount":[40],"state":[42,95],"within":[43],"for":[45],"checkpointing":[46],"incurs":[47],"significant":[48],"overhead.":[49],"Checkpointing":[50],"multiple":[51],"the":[54,67,110,126,136,143,158,170],"same":[55],"time,":[56],"which":[57,161],"is":[58,96],"necessary":[59],"obtain":[61],"consistent":[63],"coordinated":[64],"checkpoint,":[65],"overwhelms":[66],"host":[68],"interconnect,":[69],"memory":[70],"IO":[72],"band-widths.":[73],"We":[74,151],"propose":[75],"GPU":[76,140,166,177],"Snapshot":[77,141,167],"mitigate":[79],"this":[80],"issue":[81],"by:":[82],"(1)":[83],"enabling":[84],"fast":[86],"logical":[87],"snapshot":[88],"taken,":[91],"while":[92],"actual":[93],"check-pointed":[94],"transferred":[97],"asynchronously":[98],"alleviate":[100],"bandwidth":[101],"hot":[102],"spots;":[103],"(2)":[104],"using":[105],"incremental":[106],"checkpoints":[107],"that":[108],"reduce":[109],"volume":[111],"data":[113],"transferred;":[114],"(3)":[116],"checkpoint":[117,154],"offloading":[118],"limit":[120],"accelerator":[121],"complexity":[122],"effectively":[124],"utilize":[125],"host.":[127],"As":[128],"concrete":[130],"example,":[131],"we":[132],"describe":[133],"evaluate":[135],"design":[137],"tradeoffs":[138],"in":[142],"context":[144],"GPU-dense":[147],"multi-exascale":[148],"HPC":[149],"system.":[150],"demonstrate":[152],"4--40X":[153],"overhead":[155],"reductions":[156],"node":[159],"level,":[160],"enables":[162],"system":[164,174],"with":[165,175],"approach":[169],"idealized":[176],"checkpointing.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2019-06-27T00:00:00"}