{"id":"https://openalex.org/W2996604962","doi":"https://doi.org/10.1147/jrd.2019.2958909","title":"Scalable, fault-tolerant job step management for high-performance systems","display_name":"Scalable, fault-tolerant job step management for high-performance systems","publication_year":2019,"publication_date":"2019-12-10","ids":{"openalex":"https://openalex.org/W2996604962","doi":"https://doi.org/10.1147/jrd.2019.2958909","mag":"2996604962"},"language":"en","primary_location":{"id":"doi:10.1147/jrd.2019.2958909","is_oa":false,"landing_page_url":"https://doi.org/10.1147/jrd.2019.2958909","pdf_url":null,"source":{"id":"https://openalex.org/S4210219925","display_name":"IBM Journal of Research and Development","issn_l":"0018-8646","issn":["0018-8646","2151-8556"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320652","host_organization_name":"IBM","host_organization_lineage":["https://openalex.org/P4310320652"],"host_organization_lineage_names":["IBM"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IBM Journal of Research and Development","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/A5006603119","display_name":"David Solt","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"D. Solt","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076123370","display_name":"Joshua Hursey","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"J. Hursey","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040376206","display_name":"A. Lauria","orcid":"https://orcid.org/0000-0002-7978-2687"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"A. Lauria","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111611837","display_name":"D. Guo","orcid":"https://orcid.org/0009-0006-7367-2029"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"D. Guo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5085674806","display_name":"Xin Guo","orcid":"https://orcid.org/0000-0002-3350-4606"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"X. Guo","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5006603119"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5305,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.70513937,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"64","issue":"3/4","first_page":"8:1","last_page":"8:9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":1.0,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":1.0,"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"}},{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.7791123390197754},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.7187783122062683},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6738918423652649},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.6360915303230286},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5618337392807007},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.43513578176498413},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.4210091531276703},{"id":"https://openalex.org/keywords/shared-resource","display_name":"Shared resource","score":0.418448805809021},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2742680609226227},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.16916793584823608}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7791123390197754},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.7187783122062683},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6738918423652649},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6360915303230286},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5618337392807007},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.43513578176498413},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.4210091531276703},{"id":"https://openalex.org/C51332947","wikidata":"https://www.wikidata.org/wiki/Q1172305","display_name":"Shared resource","level":2,"score":0.418448805809021},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2742680609226227},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.16916793584823608},{"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/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"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:10.1147/jrd.2019.2958909","is_oa":false,"landing_page_url":"https://doi.org/10.1147/jrd.2019.2958909","pdf_url":null,"source":{"id":"https://openalex.org/S4210219925","display_name":"IBM Journal of Research and Development","issn_l":"0018-8646","issn":["0018-8646","2151-8556"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320652","host_organization_name":"IBM","host_organization_lineage":["https://openalex.org/P4310320652"],"host_organization_lineage_names":["IBM"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IBM Journal of Research and Development","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.6000000238418579,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1596936080","https://openalex.org/W1916850769","https://openalex.org/W1983500457","https://openalex.org/W2014780580","https://openalex.org/W2089226814","https://openalex.org/W2123859357","https://openalex.org/W2166656891","https://openalex.org/W2475885053","https://openalex.org/W2885156699","https://openalex.org/W2902041647","https://openalex.org/W2969562118","https://openalex.org/W7058249796"],"related_works":["https://openalex.org/W3126131865","https://openalex.org/W4253186488","https://openalex.org/W2044344400","https://openalex.org/W1996938127","https://openalex.org/W2083611981","https://openalex.org/W2072507639","https://openalex.org/W4231814374","https://openalex.org/W2155964760","https://openalex.org/W2064720525","https://openalex.org/W2111125783"],"abstract_inverted_index":{"Scientific":[0],"applications":[1],"on":[2,92,209],"the":[3,87,93,106,115,147,166,169,173,193,210],"CORAL":[4,211],"systems":[5],"demanded":[6],"a":[7,55,60,100,139],"fault-tolerant,":[8,101],"scalable":[9,102],"job":[10,18,112,136],"launch":[11],"infrastructure":[12,204],"for":[13,68,156],"complex":[14],"workflows":[15,110],"with":[16,36],"multiple":[17],"steps":[19,113],"within":[20,180],"an":[21],"allocation.":[22],"The":[23,141],"distinct":[24],"design":[25,194],"of":[26,54,131,168,178,201],"IBM's":[27,202],"Job":[28],"Step":[29],"Manager":[30],"(JSM)":[31],"infrastructure,":[32],"working":[33],"in":[34,58,121,134],"concert":[35],"Load":[37],"Sharing":[38],"Facility":[39],"(LSF)":[40],"and":[41,80,84,127,172,176,198],"Cluster":[42],"System":[43],"Management":[44],"(CSM),":[45],"achieves":[46],"these":[47],"goals.":[48],"JSM":[49,90,107,122,146,203],"demonstrated":[50],"launching":[51],"over":[52,86,165],"three-quarters":[53],"million":[56],"processes":[57,179],"under":[59],"minute":[61],"while":[62],"providing":[63],"efficient":[64],"process":[65,152],"management":[66,88],"interface":[67,79],"exascale-based":[69],"services":[70],"to":[71,98,123,149,154,205],"communication":[72,103],"libraries,":[73],"such":[74],"as":[75],"parallel":[76,94],"active":[77],"messaging":[78],"message":[81],"passing":[82],"interface,":[83],"tools":[85],"network.":[89],"relies":[91],"task":[95],"support":[96,206],"library":[97],"provide":[99],"medium":[104],"between":[105,129],"daemons.":[108],"Application":[109],"using":[111],"harness":[114],"unique":[116],"resource":[117,142,170],"set":[118,143],"abstraction":[119],"concept":[120,144],"manage":[124],"CPUs,":[125],"GPUs,":[126],"memory":[128],"groups":[130],"processes,":[132],"possibly":[133],"discrete":[135],"steps,":[137],"sharing":[138],"node.":[140],"gives":[145],"opportunity":[148],"better":[150],"organize":[151],"placement":[153],"optimize,":[155],"example,":[157],"CPU-to-GPU":[158],"communication.":[159],"Applications":[160],"that":[161],"need":[162],"complete":[163],"control":[164],"shaping":[167],"sets":[171],"placement,":[174],"binding,":[175],"ordering":[177],"them":[181],"can":[182],"leverage":[183],"JSM's":[184],"co-designed":[185],"Explicit":[186],"Resource":[187],"File":[188],"mechanism.":[189],"This":[190],"article":[191],"explores":[192],"decisions,":[195],"implementation":[196],"considerations,":[197],"performance":[199],"optimizations":[200],"scientific":[207],"discovery":[208],"systems.":[212]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
