{"id":"https://openalex.org/W2014173661","doi":"https://doi.org/10.1177/1094342010369118","title":"Understanding Checkpointing Overheads on Massive-Scale Systems: Analysis of the IBM Blue Gene/P System","display_name":"Understanding Checkpointing Overheads on Massive-Scale Systems: Analysis of the IBM Blue Gene/P System","publication_year":2010,"publication_date":"2010-06-03","ids":{"openalex":"https://openalex.org/W2014173661","doi":"https://doi.org/10.1177/1094342010369118","mag":"2014173661"},"language":"en","primary_location":{"id":"doi:10.1177/1094342010369118","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342010369118","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"0890-2720","issn":["0890-2720","1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},"type":"article","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/A5050619770","display_name":"Rinku Gupta","orcid":"https://orcid.org/0009-0002-0669-1271"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rinku Gupta","raw_affiliation_strings":["Mathematics and Computer Science Division, Argonne National Laboratory, Argonne, USA,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mathematics and Computer Science Division, Argonne National Laboratory, Argonne, USA,","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026683399","display_name":"Harish Naik","orcid":"https://orcid.org/0000-0002-1420-2688"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Harish Naik","raw_affiliation_strings":["Mathematics and Computer Science Division, Argonne National Laboratory, Argonne, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mathematics and Computer Science Division, Argonne National Laboratory, Argonne, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038177319","display_name":"Pete Beckman","orcid":"https://orcid.org/0000-0002-9428-7801"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pete Beckman","raw_affiliation_strings":["Mathematics and Computer Science Division, Argonne National Laboratory, Argonne, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mathematics and Computer Science Division, Argonne National Laboratory, Argonne, USA","institution_ids":["https://openalex.org/I1282105669"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5050619770"],"corresponding_institution_ids":["https://openalex.org/I1282105669"],"apc_list":null,"apc_paid":null,"fwci":2.0266,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.8808895,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"25","issue":"2","first_page":"180","last_page":"192"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9994999766349792,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9994000196456909,"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/petascale-computing","display_name":"Petascale computing","score":0.8904982209205627},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8673100471496582},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.7731946110725403},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.7213776111602783},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.6122675538063049},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.6046047806739807},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5066435933113098},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4904000759124756},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.4652802348136902},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3690246045589447},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3596065640449524}],"concepts":[{"id":"https://openalex.org/C185410017","wikidata":"https://www.wikidata.org/wiki/Q7171778","display_name":"Petascale computing","level":3,"score":0.8904982209205627},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8673100471496582},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.7731946110725403},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.7213776111602783},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.6122675538063049},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.6046047806739807},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5066435933113098},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4904000759124756},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4652802348136902},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3690246045589447},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3596065640449524},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/1094342010369118","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342010369118","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"0890-2720","issn":["0890-2720","1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8500000238418579,"display_name":"Life below water","id":"https://metadata.un.org/sdg/14"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W39269388","https://openalex.org/W403506996","https://openalex.org/W1494933502","https://openalex.org/W1501145371","https://openalex.org/W1537929875","https://openalex.org/W1582448188","https://openalex.org/W1679126732","https://openalex.org/W1767718504","https://openalex.org/W1997654021","https://openalex.org/W2000935529","https://openalex.org/W2001654321","https://openalex.org/W2028133900","https://openalex.org/W2033656974","https://openalex.org/W2046001409","https://openalex.org/W2048075797","https://openalex.org/W2053572944","https://openalex.org/W2099422474","https://openalex.org/W2100503591","https://openalex.org/W2102576651","https://openalex.org/W2133046454","https://openalex.org/W2152844070","https://openalex.org/W2158272436","https://openalex.org/W2161973644","https://openalex.org/W2169167780","https://openalex.org/W2181301067","https://openalex.org/W2260133378","https://openalex.org/W4213379201","https://openalex.org/W4231414267","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2021702679","https://openalex.org/W3038449658","https://openalex.org/W1582746211","https://openalex.org/W2251285835","https://openalex.org/W3129378740","https://openalex.org/W2266027327","https://openalex.org/W2278366184","https://openalex.org/W1486544172","https://openalex.org/W4206324154","https://openalex.org/W1978931242"],"abstract_inverted_index":{"Providing":[0],"fault":[1,33],"tolerance":[2,34],"in":[3,35,47],"high-end":[4,37],"petascale":[5],"systems,":[6],"consisting":[7],"of":[8,10,147],"millions":[9],"hardware":[11],"components":[12],"and":[13,96,130,140],"complex":[14],"software":[15],"stacks,":[16],"is":[17],"becoming":[18],"an":[19,99],"increasingly":[20],"challenging":[21],"task.":[22],"Checkpointing":[23],"continues":[24],"to":[25,84,92,103],"be":[26],"the":[27,62,74,105,114,119,124,131,148],"most":[28],"prevalent":[29],"technique":[30],"for":[31,55],"providing":[32],"such":[36],"systems.":[38],"Considerable":[39],"research":[40],"has":[41],"focussed":[42],"on":[43,70,144],"optimizing":[44],"checkpointing;":[45],"however,":[46],"practice,":[48],"checkpointing":[49,63,101,107,142],"still":[50],"involves":[51],"a":[52,90],"high-cost":[53],"overhead":[54,64,108],"users.":[56],"In":[57,82,110],"this":[58],"paper,":[59],"we":[60,88,112],"study":[61,113],"seen":[65],"by":[66],"various":[67],"applications":[68],"running":[69],"leadership-class":[71],"machines":[72],"like":[73],"IBM":[75],"Blue":[76,149],"Gene/P":[77,150],"at":[78],"Argonne":[79],"National":[80],"Laboratory.":[81],"addition":[83],"studying":[85],"popular":[86],"applications,":[87],"design":[89],"methodology":[91],"help":[93],"users":[94],"understand":[95],"intelligently":[97],"choose":[98],"optimal":[100],"frequency":[102],"reduce":[104],"overall":[106],"incurred.":[109],"particular,":[111],"Grid-Based":[115],"Projector-Augmented":[116],"Wave":[117],"application,":[118,123],"Carr-Parrinello":[120],"Molecular":[121],"Dynamics":[122],"Nek5000":[125],"computational":[126],"fluid":[127],"dynamics":[128],"application":[129],"Parallel":[132],"Ocean":[133],"Program":[134],"application\u2014and":[135],"analyze":[136],"their":[137],"memory":[138],"usage":[139],"possible":[141],"trends":[143],"65,536":[145],"processors":[146],"system.":[151]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}