{"id":"https://openalex.org/W2766249600","doi":"https://doi.org/10.1145/3152041.3152083","title":"Automatic Risk-based Selective Redundancy for Fault-tolerant Task-parallel HPC Applications","display_name":"Automatic Risk-based Selective Redundancy for Fault-tolerant Task-parallel HPC Applications","publication_year":2017,"publication_date":"2017-10-31","ids":{"openalex":"https://openalex.org/W2766249600","doi":"https://doi.org/10.1145/3152041.3152083","mag":"2766249600"},"language":"en","primary_location":{"id":"doi:10.1145/3152041.3152083","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3152041.3152083","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Third International Workshop on Extreme Scale Programming Models and Middleware","raw_type":"proceedings-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/A5034946156","display_name":"Omer Subasi","orcid":"https://orcid.org/0000-0002-5373-7570"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Omer Subasi","raw_affiliation_strings":["Pacific Northwest National Laboratory"],"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075162875","display_name":"Osman \u00dcnsal","orcid":"https://orcid.org/0000-0002-0544-9697"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Osman Unsal","raw_affiliation_strings":["Barcelona Supercomputing Center"],"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006650430","display_name":"Sriram Krishnamoorthy","orcid":"https://orcid.org/0000-0002-4682-1002"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sriram Krishnamoorthy","raw_affiliation_strings":["Pacific Northwest National Laboratory"],"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory","institution_ids":["https://openalex.org/I142606810"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5034946156"],"corresponding_institution_ids":["https://openalex.org/I142606810"],"apc_list":null,"apc_paid":null,"fwci":0.6216,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.73040287,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.9987000226974487,"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/T11005","display_name":"Radiation Effects in Electronics","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8311264514923096},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.7005213499069214},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.699165940284729},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.5965575575828552},{"id":"https://openalex.org/keywords/replicate","display_name":"Replicate","score":0.5905027389526367},{"id":"https://openalex.org/keywords/replication","display_name":"Replication (statistics)","score":0.556914746761322},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5328524708747864},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.49625808000564575},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4743586778640747},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4585655927658081},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.42795369029045105},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.37783700227737427},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.34113049507141113},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.13502496480941772},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1287255585193634}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8311264514923096},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.7005213499069214},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.699165940284729},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5965575575828552},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.5905027389526367},{"id":"https://openalex.org/C12590798","wikidata":"https://www.wikidata.org/wiki/Q3933199","display_name":"Replication (statistics)","level":2,"score":0.556914746761322},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5328524708747864},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.49625808000564575},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4743586778640747},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4585655927658081},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.42795369029045105},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.37783700227737427},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.34113049507141113},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13502496480941772},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1287255585193634},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3152041.3152083","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3152041.3152083","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Third International Workshop on Extreme Scale Programming Models and Middleware","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W47306539","https://openalex.org/W132161408","https://openalex.org/W1779522739","https://openalex.org/W1991421378","https://openalex.org/W1993660990","https://openalex.org/W2005998283","https://openalex.org/W2027476456","https://openalex.org/W2036641664","https://openalex.org/W2070638479","https://openalex.org/W2086779654","https://openalex.org/W2105524676","https://openalex.org/W2142677441","https://openalex.org/W2163950090","https://openalex.org/W2322803542","https://openalex.org/W2397607245","https://openalex.org/W2560662349","https://openalex.org/W2725418265","https://openalex.org/W2821494808","https://openalex.org/W4242361160","https://openalex.org/W4249693612","https://openalex.org/W4256364678"],"related_works":["https://openalex.org/W4254851101","https://openalex.org/W3171007296","https://openalex.org/W22115721","https://openalex.org/W2321234655","https://openalex.org/W2053915529","https://openalex.org/W2111659373","https://openalex.org/W4398395683","https://openalex.org/W4398298289","https://openalex.org/W4398690544","https://openalex.org/W2116314988"],"abstract_inverted_index":{"Silent":[0],"data":[1],"corruption":[2],"(SDC)":[3],"and":[4,26,39,48,70,75,90],"fail-stop":[5,49],"errors":[6,96],"are":[7],"the":[8,53,79,104,108],"most":[9],"hazardous":[10],"error":[11,33],"types":[12],"in":[13],"high-performance":[14],"computing":[15],"(HPC)":[16],"systems.":[17],"In":[18],"this":[19],"study,":[20],"we":[21,59,73],"present":[22],"an":[23],"automatic,":[24],"efficient":[25],"lightweight":[27,62],"redundancy":[28],"mechanism":[29],"to":[30,45],"mitigate":[31,46],"both":[32],"types.":[34],"We":[35],"propose":[36],"partial":[37],"task-replication":[38],"checkpointing":[40],"for":[41],"task-parallel":[42],"HPC":[43],"applications":[44],"silent":[47,95],"errors.":[50],"To":[51],"avoid":[52],"prohibitive":[54],"costs":[55],"of":[56,94,107],"complete":[57],"replication,":[58],"introduce":[60],"a":[61,67,84],"selective":[63],"replication":[64],"mechanism.":[65],"Using":[66],"fully":[68],"automatic":[69],"transparent":[71],"heuristics,":[72],"identify":[74],"selectively":[76],"replicate":[77],"only":[78,98],"reliability-critical":[80],"tasks":[81],"based":[82],"on":[83],"risk":[85],"metric.":[86],"Our":[87],"approach":[88],"detects":[89],"corrects":[91],"around":[92],"70%":[93],"with":[97],"5%":[99],"average":[100],"performance":[101,105],"overhead.":[102],"Additionally,":[103],"overhead":[106],"heuristic":[109],"itself":[110],"is":[111],"negligible.":[112]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2018,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
