{"id":"https://openalex.org/W7167027240","doi":"https://doi.org/10.1145/3797905.3807872","title":"StreamGuard: Low-Overhead Resilience for Real-time HPC Data Streams","display_name":"StreamGuard: Low-Overhead Resilience for Real-time HPC Data Streams","publication_year":2026,"publication_date":"2026-07-02","ids":{"openalex":"https://openalex.org/W7167027240","doi":"https://doi.org/10.1145/3797905.3807872"},"language":null,"primary_location":{"id":"doi:10.1145/3797905.3807872","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3797905.3807872","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2606.30848","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101994317","display_name":"Hai Thanh Nguyen","orcid":"https://orcid.org/0000-0003-4177-0493"},"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":"Hai Duc Nguyen","raw_affiliation_strings":["Argonne National Laboratory, Lemont, IL, USA and University of Chicago, Chicago, IL, USA"],"raw_orcid":"https://orcid.org/0000-0003-4177-0493","affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Lemont, IL, USA and University of Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085745891","display_name":"Bogdan Nicolae","orcid":"https://orcid.org/0000-0002-0661-7509"},"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":"Bogdan Nicolae","raw_affiliation_strings":["Argonne National Laboratory, Lemont, IL, USA"],"raw_orcid":"https://orcid.org/0000-0002-0661-7509","affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Lemont, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038566298","display_name":"Tekin Bi\u00e7er","orcid":"https://orcid.org/0000-0002-8428-5159"},"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":"Tekin Bicer","raw_affiliation_strings":["Argonne National Laboratory, Lemont, IL, USA"],"raw_orcid":"https://orcid.org/0000-0002-8428-5159","affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Lemont, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102942440","display_name":"Amal Gueroudji","orcid":"https://orcid.org/0009-0004-4830-3139"},"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":"Amal Gueroudji","raw_affiliation_strings":["Argonne National Laboratory, Lemont, IL, USA"],"raw_orcid":"https://orcid.org/0009-0004-4830-3139","affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Lemont, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070907426","display_name":"Matthieu Dorier","orcid":"https://orcid.org/0000-0001-9293-2021"},"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":"Matthieu Dorier","raw_affiliation_strings":["Argonne National Laboratory, Lemont, IL, USA"],"raw_orcid":"https://orcid.org/0000-0001-9293-2021","affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Lemont, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065464552","display_name":"Kyle Chard","orcid":"https://orcid.org/0000-0002-7370-4805"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyle Chard","raw_affiliation_strings":["University of Chicago, Chicago, IL, USA"],"raw_orcid":"https://orcid.org/0000-0002-7370-4805","affiliations":[{"raw_affiliation_string":"University of Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I39422238","https://openalex.org/I40347166"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032231503","display_name":"Ian Foster","orcid":"https://orcid.org/0000-0003-2129-5269"},"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":"Ian Foster","raw_affiliation_strings":["University of Chicago, Chicago, IL, USA and Argonne National Lab, Lemont, IL, USA"],"raw_orcid":"https://orcid.org/0000-0003-2129-5269","affiliations":[{"raw_affiliation_string":"University of Chicago, Chicago, IL, USA and Argonne National Lab, Lemont, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8723993,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1014","last_page":"1026"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.6711999773979187,"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":0.6711999773979187,"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":0.10939999669790268,"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":0.0794999971985817,"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/workflow","display_name":"Workflow","score":0.6244000196456909},{"id":"https://openalex.org/keywords/resilience","display_name":"Resilience (materials science)","score":0.5896999835968018},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.567799985408783},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.4778999984264374},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4772999882698059},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4090000092983246},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.40149998664855957},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.3395000100135803}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7975999712944031},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6244000196456909},{"id":"https://openalex.org/C2779585090","wikidata":"https://www.wikidata.org/wiki/Q3457762","display_name":"Resilience (materials science)","level":2,"score":0.5896999835968018},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.567799985408783},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.546999990940094},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.4778999984264374},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4772999882698059},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4090000092983246},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.40149998664855957},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.3395000100135803},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.3319999873638153},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.3303999900817871},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.3197999894618988},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3151000142097473},{"id":"https://openalex.org/C42090638","wikidata":"https://www.wikidata.org/wiki/Q4048907","display_name":"STREAMS","level":2,"score":0.31279999017715454},{"id":"https://openalex.org/C200749887","wikidata":"https://www.wikidata.org/wiki/Q1165574","display_name":"System monitoring","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.27880001068115234},{"id":"https://openalex.org/C174998907","wikidata":"https://www.wikidata.org/wiki/Q357662","display_name":"Work in process","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.25619998574256897}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3797905.3807872","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3797905.3807872","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2606.30848","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.30848","pdf_url":"https://arxiv.org/pdf/2606.30848","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2606.30848","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.30848","pdf_url":"https://arxiv.org/pdf/2606.30848","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.6255144476890564,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G102163711","display_name":null,"funder_award_id":"DE\u2010 AC02\u201006CH11357","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G262962599","display_name":null,"funder_award_id":"AC02\u201006CH11357","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G3047219579","display_name":null,"funder_award_id":"CSSI-2514056","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3215254038","display_name":"Collaborative Research: Frameworks: MPI4AI: Enhancing Performance and Productivity of AI Science through Next-generation High Performance Communication Abstractions","funder_award_id":"2514056","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3357838806","display_name":"Collaborative Research: Elements: VLCC-States: Versioned Lineage-Driven Checkpointing of Composable States","funder_award_id":"2411386","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G513797252","display_name":null,"funder_award_id":"DE-AC02\u201306CH11357","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5884270826","display_name":null,"funder_award_id":"CSSI-2411386","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6848031779","display_name":null,"funder_award_id":"06CH11357","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G969889393","display_name":null,"funder_award_id":"DE-AC02-","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320337377","display_name":"Office of Advanced Cyberinfrastructure","ror":"https://ror.org/04nh1dc89"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7167027240.pdf","grobid_xml":"https://content.openalex.org/works/W7167027240.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W1584278023","https://openalex.org/W1971439003","https://openalex.org/W1976821017","https://openalex.org/W1981432246","https://openalex.org/W1982063824","https://openalex.org/W2008503861","https://openalex.org/W2009741028","https://openalex.org/W2022462155","https://openalex.org/W2033656974","https://openalex.org/W2063924830","https://openalex.org/W2070712642","https://openalex.org/W2081409107","https://openalex.org/W2086748522","https://openalex.org/W2129542763","https://openalex.org/W2133046454","https://openalex.org/W2145298408","https://openalex.org/W2173213060","https://openalex.org/W2466095195","https://openalex.org/W2588997145","https://openalex.org/W2623323969","https://openalex.org/W2753910905","https://openalex.org/W2798434712","https://openalex.org/W2902762889","https://openalex.org/W2913854892","https://openalex.org/W2943761765","https://openalex.org/W2961595369","https://openalex.org/W2977600537","https://openalex.org/W2998779578","https://openalex.org/W3122166729","https://openalex.org/W3177121517","https://openalex.org/W4229059674","https://openalex.org/W4321021460","https://openalex.org/W4386943870","https://openalex.org/W4388328602","https://openalex.org/W4388336898","https://openalex.org/W4388581294","https://openalex.org/W4390827958","https://openalex.org/W4393973206","https://openalex.org/W4399427731","https://openalex.org/W4400409828","https://openalex.org/W4402673683","https://openalex.org/W4411107529","https://openalex.org/W4414299303","https://openalex.org/W4416004574"],"related_works":[],"abstract_inverted_index":{"Real-time":[0],"scientific":[1,58],"workflows":[2],"operate":[3],"on":[4,16,44],"continuous":[5],"data":[6],"streams":[7],"and":[8,24,38,79,90,100,119],"must":[9],"produce":[10],"timely,":[11],"high-quality":[12],"results":[13,109],"despite":[14],"executing":[15],"complex,":[17],"failure-prone":[18],"infrastructure.":[19],"Hardware":[20],"faults,":[21],"network":[22],"disruptions,":[23],"performance":[25,37,120],"anomalies":[26,121],"caused":[27],"by":[28,122],"resource":[29],"contention":[30],"or":[31],"system":[32],"heterogeneity":[33],"can":[34],"severely":[35],"degrade":[36],"violate":[39],"real-time":[40],"constraints.":[41],"We":[42,61],"focus":[43],"strengthening":[45],"the":[46,49,115],"resilience":[47],"of":[48,57,117],"producer\u2013consumer":[50],"streaming":[51,59],"pattern,":[52],"a":[53,67,81],"fundamental":[54],"building":[55],"block":[56],"workflows.":[60],"present":[62],"two":[63],"complementary":[64],"techniques:":[65],"(i)":[66],"dynamic,":[68],"asynchronous,":[69],"non-blocking":[70],"checkpointing":[71],"mechanism":[72],"that":[73,86,111],"preserves":[74],"progress":[75,99],"without":[76],"interrupting":[77],"computation,":[78],"(ii)":[80],"progress-aware":[82],"load":[83],"redistribution":[84],"strategy":[85],"detects":[87],"slow":[88],"workers":[89],"proactively":[91],"rebalances":[92],"tasks.":[93],"Together,":[94],"these":[95],"mechanisms":[96],"maintain":[97],"forward":[98],"balanced":[101],"execution":[102],"even":[103],"in":[104,133],"highly":[105],"error-prone":[106],"environments.":[107],"Experimental":[108],"show":[110],"our":[112],"approach":[113],"reduces":[114],"impact":[116],"failures":[118],"up":[123],"to":[124],"6":[125],"\u00d7,":[126],"while":[127],"introducing":[128],"less":[129],"than":[130],"1%":[131],"overhead":[132],"failure-free":[134],"execution.":[135]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2026-07-03T00:00:00"}
