{"id":"https://openalex.org/W4412610396","doi":"https://doi.org/10.1109/hpcc64274.2024.00038","title":"Leveraging Resource-Aware Application-Level Checkpointing and RDMA for Fault Tolerance and Data Distribution in Malleable MPI Applications","display_name":"Leveraging Resource-Aware Application-Level Checkpointing and RDMA for Fault Tolerance and Data Distribution in Malleable MPI Applications","publication_year":2024,"publication_date":"2024-12-13","ids":{"openalex":"https://openalex.org/W4412610396","doi":"https://doi.org/10.1109/hpcc64274.2024.00038"},"language":"en","primary_location":{"id":"doi:10.1109/hpcc64274.2024.00038","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcc64274.2024.00038","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on High Performance Computing and Communications (HPCC)","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/A5085442143","display_name":"Jophin John","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jophin John","raw_affiliation_strings":["Technische Universität München,Chair of Computer Architecture and Parallel Systems,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universität München,Chair of Computer Architecture and Parallel Systems,Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011103949","display_name":"Michael Gerndt","orcid":"https://orcid.org/0000-0002-3210-5048"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Gerndt","raw_affiliation_strings":["Technische Universität München,Chair of Computer Architecture and Parallel Systems,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universität München,Chair of Computer Architecture and Parallel Systems,Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.43744739,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"216","last_page":"223"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9983000159263611,"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":0.9983000159263611,"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":0.9894000291824341,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9821000099182129,"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/remote-direct-memory-access","display_name":"Remote direct memory access","score":0.8720712661743164},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.818615734577179},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.717149019241333},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5226611495018005},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.45053574442863464},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.42044180631637573},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4198419153690338},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.24357056617736816}],"concepts":[{"id":"https://openalex.org/C130795937","wikidata":"https://www.wikidata.org/wiki/Q2561570","display_name":"Remote direct memory access","level":2,"score":0.8720712661743164},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.818615734577179},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.717149019241333},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5226611495018005},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.45053574442863464},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.42044180631637573},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4198419153690338},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.24357056617736816}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpcc64274.2024.00038","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcc64274.2024.00038","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on High Performance Computing and Communications (HPCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W63848143","https://openalex.org/W1545469897","https://openalex.org/W1595501741","https://openalex.org/W1596936080","https://openalex.org/W2017060126","https://openalex.org/W2045152180","https://openalex.org/W2085222386","https://openalex.org/W2128577831","https://openalex.org/W2140085532","https://openalex.org/W2140899604","https://openalex.org/W2759320443","https://openalex.org/W2890925057","https://openalex.org/W2914167931","https://openalex.org/W2961595369","https://openalex.org/W2963258975","https://openalex.org/W3021539948","https://openalex.org/W3040973301","https://openalex.org/W3159546114","https://openalex.org/W4245507143","https://openalex.org/W4247768107","https://openalex.org/W4252909492","https://openalex.org/W4281255289","https://openalex.org/W4360995047","https://openalex.org/W6765255463","https://openalex.org/W6962406901"],"related_works":["https://openalex.org/W3090586438","https://openalex.org/W2782433361","https://openalex.org/W2416075414","https://openalex.org/W2475302168","https://openalex.org/W4392747727","https://openalex.org/W4366999533","https://openalex.org/W2134569538","https://openalex.org/W3135214639","https://openalex.org/W2594055038","https://openalex.org/W2754465584"],"abstract_inverted_index":{"Dynamic":[0,38],"resource":[1,53,70,168,188,191],"management":[2,89],"and":[3,17,28,52,106,110,158],"application":[4,18,27],"malleability":[5,23],"present":[6],"numerous":[7],"opportunities":[8],"in":[9,22,36,65],"High-Performance":[10],"Computing":[11],"(HPC),":[12],"enhancing":[13],"both":[14,26],"system-level":[15],"services":[16,74],"performance.":[19,141],"Recent":[20],"trends":[21],"research,":[24],"encompassing":[25],"system":[29,90,143],"dynamism,":[30],"are":[31],"building":[32],"a":[33],"new":[34],"era":[35],"HPC.":[37],"applications,":[39,124],"particularly":[40],"those":[41],"leveraging":[42,115],"malleable":[43,78,94,123,183],"resources,":[44],"require":[45],"adaptive":[46,86,171],"checkpointing":[47,60,73,104,109,147],"systems":[48,61],"to":[49,93,121,131],"enhance":[50],"performance":[51,166],"use.":[54],"Applications":[55],"can":[56,144],"significantly":[57],"benefit":[58],"from":[59],"becoming":[62],"dynamic,":[63],"especially":[64],"handling":[66],"data":[67,111,128],"redistribution":[68,112,189],"during":[69,190],"changes.":[71,169,192],"Consequently,":[72],"should":[75],"also":[76],"become":[77],"(or":[79],"adaptive).":[80],"Therefore,":[81],"we":[82],"propose":[83],"iCheck,":[84],"an":[85],"application-level":[87],"checkpoint":[88,156,165],"that":[91],"caters":[92],"MPI":[95],"applications.":[96],"iCheck":[97,125],"aids":[98],"these":[99],"applications":[100,184],"by":[101,185],"dynamically":[102,145],"reconfiguring":[103],"resources":[105],"offering":[107],"robust":[108],"services.":[113],"By":[114],"Remote":[116],"Direct":[117],"Memory":[118],"Access":[119],"(RDMA)":[120],"support":[122],"facilitates":[126],"faster":[127],"transfers":[129],"(up":[130],"40":[132],"times":[133],"improvement":[134],"over":[135],"the":[136,180],"PFS-based":[137],"solution),":[138],"ensuring":[139],"efficient":[140],"The":[142],"adjust":[146],"processes":[148],"based":[149],"on":[150],"metrics":[151],"such":[152],"as":[153,176,178],"available":[154],"memory,":[155],"frequency,":[157],"number":[159],"of":[160,182],"processes,":[161],"maintaining":[162],"or":[163],"improving":[164],"amid":[167],"This":[170],"approach":[172],"supports":[173],"fault":[174],"tolerance":[175],"well":[177],"simplifies":[179],"development":[181],"effectively":[186],"managing":[187]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}