{"id":"https://openalex.org/W4387010580","doi":"https://doi.org/10.1109/tpds.2023.3316011","title":"FT-BLAS: A Fault Tolerant High Performance BLAS Implementation on x86 CPUs","display_name":"FT-BLAS: A Fault Tolerant High Performance BLAS Implementation on x86 CPUs","publication_year":2023,"publication_date":"2023-09-25","ids":{"openalex":"https://openalex.org/W4387010580","doi":"https://doi.org/10.1109/tpds.2023.3316011"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2023.3316011","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2023.3316011","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","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/A5035339023","display_name":"Yujia Zhai","orcid":"https://orcid.org/0000-0002-2688-8058"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yujia Zhai","raw_affiliation_strings":["University of California, Riverside, Riverside, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-2688-8058","affiliations":[{"raw_affiliation_string":"University of California, Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010372747","display_name":"Elisabeth Giem","orcid":"https://orcid.org/0009-0004-3384-6843"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elisabeth Giem","raw_affiliation_strings":["University of California, Riverside, Riverside, CA, USA"],"raw_orcid":"https://orcid.org/0009-0004-3384-6843","affiliations":[{"raw_affiliation_string":"University of California, Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100643410","display_name":"Kai Zhao","orcid":"https://orcid.org/0000-0001-5328-3962"},"institutions":[{"id":"https://openalex.org/I32389192","display_name":"University of Alabama at Birmingham","ror":"https://ror.org/008s83205","country_code":"US","type":"education","lineage":["https://openalex.org/I32389192"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kai Zhao","raw_affiliation_strings":["University of Alabama at Birmingham, Birmingham, AL, USA"],"raw_orcid":"https://orcid.org/0000-0001-5328-3962","affiliations":[{"raw_affiliation_string":"University of Alabama at Birmingham, Birmingham, AL, USA","institution_ids":["https://openalex.org/I32389192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100705519","display_name":"Jinyang Liu","orcid":"https://orcid.org/0000-0003-0177-502X"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinyang Liu","raw_affiliation_strings":["University of California, Riverside, Riverside, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-0177-502X","affiliations":[{"raw_affiliation_string":"University of California, Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100779661","display_name":"Jiajun Huang","orcid":"https://orcid.org/0000-0001-5092-3987"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiajun Huang","raw_affiliation_strings":["University of California, Riverside, Riverside, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-5092-3987","affiliations":[{"raw_affiliation_string":"University of California, Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022569738","display_name":"Bryan M. Wong","orcid":"https://orcid.org/0000-0002-3477-8043"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bryan M. Wong","raw_affiliation_strings":["University of California, Riverside, Riverside, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3477-8043","affiliations":[{"raw_affiliation_string":"University of California, Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091230938","display_name":"Christian R. Shelton","orcid":"https://orcid.org/0000-0001-6698-7838"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christian R. Shelton","raw_affiliation_strings":["University of California, Riverside, Riverside, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-6698-7838","affiliations":[{"raw_affiliation_string":"University of California, Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"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/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zizhong Chen","raw_affiliation_strings":["University of California, Riverside, Riverside, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-2578-4940","affiliations":[{"raw_affiliation_string":"University of California, Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2323,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.51674171,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"34","issue":"12","first_page":"3207","last_page":"3223"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11005","display_name":"Radiation Effects in Electronics","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11005","display_name":"Radiation Effects in Electronics","score":1.0,"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"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994000196456909,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9990000128746033,"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/computer-science","display_name":"Computer science","score":0.8994655609130859},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7292302846908569},{"id":"https://openalex.org/keywords/x86","display_name":"x86","score":0.6088341474533081},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.48663434386253357},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.463169664144516},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.26385995745658875},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.1235712468624115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8994655609130859},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7292302846908569},{"id":"https://openalex.org/C170723468","wikidata":"https://www.wikidata.org/wiki/Q182933","display_name":"x86","level":3,"score":0.6088341474533081},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.48663434386253357},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.463169664144516},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.26385995745658875},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.1235712468624115}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2023.3316011","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2023.3316011","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":72,"referenced_works":["https://openalex.org/W1541483005","https://openalex.org/W1898823215","https://openalex.org/W1964031104","https://openalex.org/W1964588245","https://openalex.org/W1986905947","https://openalex.org/W1995746640","https://openalex.org/W1997843200","https://openalex.org/W2004675401","https://openalex.org/W2023856022","https://openalex.org/W2030806070","https://openalex.org/W2034593585","https://openalex.org/W2038238534","https://openalex.org/W2043275593","https://openalex.org/W2046607737","https://openalex.org/W2052455844","https://openalex.org/W2063639637","https://openalex.org/W2064872546","https://openalex.org/W2083613288","https://openalex.org/W2084379367","https://openalex.org/W2095928739","https://openalex.org/W2105524676","https://openalex.org/W2110701642","https://openalex.org/W2118832200","https://openalex.org/W2125768532","https://openalex.org/W2130076536","https://openalex.org/W2130189691","https://openalex.org/W2134320686","https://openalex.org/W2134633067","https://openalex.org/W2138692126","https://openalex.org/W2150981663","https://openalex.org/W2151984682","https://openalex.org/W2156514327","https://openalex.org/W2169596872","https://openalex.org/W2170196949","https://openalex.org/W2170424585","https://openalex.org/W2229245554","https://openalex.org/W2252007067","https://openalex.org/W2292469857","https://openalex.org/W2296204683","https://openalex.org/W2343351966","https://openalex.org/W2411755313","https://openalex.org/W2412349256","https://openalex.org/W2418331349","https://openalex.org/W2419664341","https://openalex.org/W2485331474","https://openalex.org/W2621842477","https://openalex.org/W2647773517","https://openalex.org/W2767260595","https://openalex.org/W2767321582","https://openalex.org/W2767694495","https://openalex.org/W2798289565","https://openalex.org/W2949981335","https://openalex.org/W2986161099","https://openalex.org/W3014034225","https://openalex.org/W3105862567","https://openalex.org/W3120931476","https://openalex.org/W3136479147","https://openalex.org/W3140366478","https://openalex.org/W3164390940","https://openalex.org/W3171842021","https://openalex.org/W3203693205","https://openalex.org/W3212408546","https://openalex.org/W4229666556","https://openalex.org/W4233556486","https://openalex.org/W4248621761","https://openalex.org/W4312129864","https://openalex.org/W4367859812","https://openalex.org/W4372272640","https://openalex.org/W4384705353","https://openalex.org/W4386212580","https://openalex.org/W6675837356","https://openalex.org/W6852157192"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W3215381467","https://openalex.org/W4301207796","https://openalex.org/W2915956107","https://openalex.org/W1862835629","https://openalex.org/W2099111379","https://openalex.org/W2136799148","https://openalex.org/W2897533804","https://openalex.org/W2890506991","https://openalex.org/W2091202943"],"abstract_inverted_index":{"Basic":[0],"Linear":[1],"Algebra":[2],"Subprograms":[3],"(BLAS)":[4],"serve":[5],"as":[6,117,171],"a":[7,21,51,143,156],"foundational":[8],"library":[9],"for":[10,138,205],"scientific":[11],"computing":[12,67],"and":[13,61,69,96,120,177,186,195,202,208],"machine":[14],"learning.":[15],"In":[16],"this":[17],"article,":[18],"we":[19,49,65,86,112,148,217],"present":[20],"new":[22],"BLAS":[23,35,63,110,216],"implementation,":[24],"FT-BLAS,":[25],"that":[26,181],"provides":[27],"performance":[28,188],"comparable":[29],"to":[30,54,76,89,102,127,150,199],"or":[31],"faster":[32,190],"than":[33,191],"state-of-the-art":[34],"libraries,":[36],"while":[37],"being":[38],"capable":[39],"of":[40,145,215,222],"tolerating":[41],"soft":[42],"errors":[43,223],"on-the-fly.":[44],"At":[45],"the":[46,73,82,123,129,152],"algorithmic":[47],"level,":[48],"propose":[50,88],"hybrid":[52],"strategy":[53],"incorporate":[55],"fault-tolerant":[56,140,153],"functionality.":[57],"For":[58,107],"memory-bound":[59],"Level-1":[60],"Level-2":[62],"routines,":[64,111],"duplicate":[66],"instructions":[68],"re-use":[70],"data":[71],"at":[72,155],"register":[74],"level":[75],"avoid":[77],"memory":[78,130],"overhead":[79,154],"when":[80],"validating":[81],"runtime":[83],"correctness.":[84],"Here":[85],"novelly":[87],"utilize":[90],"mask":[91],"registers":[92,98],"on":[93,99,167],"AVX512-enabled":[94],"processors":[95,101,169],"SIMD":[97],"AVX2-enabled":[100],"store":[103],"intermediate":[104],"comparison":[105],"results.":[106],"compute-bound":[108],"Level-3":[109],"fuse":[113],"memory-intensive":[114],"operations":[115],"such":[116,170],"checksum":[118],"encoding":[119],"verification":[121],"into":[122],"GEMM":[124],"assembly":[125],"kernels":[126],"optimize":[128],"footprint.":[131],"We":[132],"also":[133],"design":[134],"cache-friendly":[135],"parallel":[136,209],"algorithms":[137],"our":[139],"library.":[141],"Through":[142],"series":[144],"architectural-aware":[146],"optimizations,":[147],"manage":[149],"maintain":[151],"negligible":[157],"order":[158],"(":[159],"<inline-formula><tex-math":[160],"notation=\"LaTeX\">$&lt;":[161],"$</tex-math></inline-formula>":[162],"3%).":[163],"Experimental":[164],"results":[165],"obtained":[166],"widely-used":[168],"Intel":[172,174,192],"Skylake,":[173],"Cascade":[175],"Lake,":[176],"AMD":[178],"Zen2":[179],"demonstrate":[180],"FT-BLAS":[182],"offers":[183],"high":[184,187],"reliability":[185],"\u2013":[189],"MKL,":[193],"OpenBLAS,":[194],"BLIS":[196],"by":[197],"up":[198],"3.50%,":[200],"22.14%,":[201],"21.70%,":[203],"respectively,":[204],"both":[206],"serial":[207],"routines":[210],"spanning":[211],"all":[212],"three":[213],"levels":[214],"benchmarked,":[218],"even":[219],"under":[220],"hundreds":[221],"injected":[224],"per":[225],"minute.":[226]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}