{"id":"https://openalex.org/W2092712520","doi":"https://doi.org/10.1109/ipdpsw.2010.5470775","title":"Fault tolerant linear algebra: Recovering from fail-stop failures without checkpointing","display_name":"Fault tolerant linear algebra: Recovering from fail-stop failures without checkpointing","publication_year":2010,"publication_date":"2010-04-01","ids":{"openalex":"https://openalex.org/W2092712520","doi":"https://doi.org/10.1109/ipdpsw.2010.5470775","mag":"2092712520"},"language":"en","primary_location":{"id":"doi:10.1109/ipdpsw.2010.5470775","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw.2010.5470775","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Symposium on Parallel &amp; Distributed Processing, Workshops and Phd Forum (IPDPSW)","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/A5020743646","display_name":"Teresa Davies","orcid":null},"institutions":[{"id":"https://openalex.org/I167576493","display_name":"Colorado School of Mines","ror":"https://ror.org/04raf6v53","country_code":"US","type":"education","lineage":["https://openalex.org/I167576493"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Teresa Davies","raw_affiliation_strings":["Colorado Schml of Mines, USA","Colorado School of Mines, , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Colorado Schml of Mines, USA","institution_ids":["https://openalex.org/I167576493"]},{"raw_affiliation_string":"Colorado School of Mines, , USA","institution_ids":["https://openalex.org/I167576493"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061737717","display_name":"Zizhong Chen","orcid":"https://orcid.org/0000-0003-2578-4940"},"institutions":[{"id":"https://openalex.org/I167576493","display_name":"Colorado School of Mines","ror":"https://ror.org/04raf6v53","country_code":"US","type":"education","lineage":["https://openalex.org/I167576493"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zizhong Chen","raw_affiliation_strings":["Colorado Schml of Mines, USA","Colorado School of Mines, , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Colorado Schml of Mines, USA","institution_ids":["https://openalex.org/I167576493"]},{"raw_affiliation_string":"Colorado School of Mines, , USA","institution_ids":["https://openalex.org/I167576493"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I167576493"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":null,"first_page":"1","last_page":"4"},"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":0.9987999796867371,"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":0.9987000226974487,"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":0.8095353245735168},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.7850732803344727},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7747172117233276},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.7401607632637024},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.6203528046607971},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5105577707290649},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.477800190448761},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.46721163392066956},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.41381049156188965},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.15999963879585266},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08896923065185547},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.059547215700149536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8095353245735168},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.7850732803344727},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7747172117233276},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.7401607632637024},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.6203528046607971},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5105577707290649},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.477800190448761},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.46721163392066956},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.41381049156188965},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15999963879585266},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08896923065185547},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.059547215700149536},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipdpsw.2010.5470775","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw.2010.5470775","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Symposium on Parallel &amp; Distributed Processing, Workshops and Phd Forum (IPDPSW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1558516248","https://openalex.org/W1607166357","https://openalex.org/W2083613288","https://openalex.org/W2102844000","https://openalex.org/W2117293168","https://openalex.org/W2128564847","https://openalex.org/W2151984682","https://openalex.org/W2152212524","https://openalex.org/W2158344138","https://openalex.org/W2161551433","https://openalex.org/W2296772319"],"related_works":["https://openalex.org/W2389214306","https://openalex.org/W2064720525","https://openalex.org/W4401278057","https://openalex.org/W2111125783","https://openalex.org/W1862835629","https://openalex.org/W2136799148","https://openalex.org/W2897533804","https://openalex.org/W2890506991","https://openalex.org/W2063186542","https://openalex.org/W3141650078"],"abstract_inverted_index":{"Today's":[0],"long":[1],"running":[2],"high":[3],"performance":[4],"computing":[5],"applications":[6,38],"typically":[7],"tolerate":[8,80],"fail-stop":[9,81],"failures":[10,82],"by":[11],"checkpointing.":[12,84],"While":[13],"checkpointing":[14],"is":[15],"a":[16,25,33,40],"very":[17],"general":[18],"technique":[19],"and":[20,75],"can":[21],"be":[22],"applied":[23],"in":[24],"wide":[26],"range":[27],"of":[28,43,65],"applications,":[29],"it":[30],"often":[31],"introduces":[32],"considerable":[34],"overhead":[35,56],"especially":[36],"when":[37],"modify":[39],"large":[41],"amount":[42],"memory":[44],"between":[45],"checkpoints.":[46],"In":[47],"this":[48],"research,":[49],"we":[50],"will":[51,69,86],"design":[52],"highly":[53],"scalable":[54],"low":[55],"fault":[57],"tolerant":[58],"schemes":[59],"according":[60],"to":[61,79],"the":[62,89,93],"specific":[63],"characteristics":[64],"an":[66],"application.":[67],"We":[68,85],"focus":[70],"on":[71],"linear":[72,97],"algebra":[73,98],"operations":[74],"re-design":[76],"selected":[77],"algorithms":[78],"without":[83],"also":[87],"incorporate":[88],"developed":[90],"techniques":[91],"into":[92],"widely":[94],"used":[95],"numerical":[96],"library":[99],"package":[100],"ScaLAPACK.":[101]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
