{"id":"https://openalex.org/W4372272640","doi":"https://doi.org/10.1145/3588195.3595947","title":"FT-GEMM: A Fault Tolerant High Performance GEMM Implementation on x86 CPUs","display_name":"FT-GEMM: A Fault Tolerant High Performance GEMM Implementation on x86 CPUs","publication_year":2023,"publication_date":"2023-08-07","ids":{"openalex":"https://openalex.org/W4372272640","doi":"https://doi.org/10.1145/3588195.3595947"},"language":"en","primary_location":{"id":"doi:10.1145/3588195.3595947","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3588195.3595947","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2305.02444","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075806978","display_name":"Shixun Wu","orcid":"https://orcid.org/0000-0001-8637-3307"},"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":true,"raw_author_name":"Shixun Wu","raw_affiliation_strings":["University of California, Riverside, Riverside, CA, USA"],"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/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"],"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"],"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/A5071045650","display_name":"Zizhe Jian","orcid":"https://orcid.org/0009-0005-2079-8130"},"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":"Zizhe Jian","raw_affiliation_strings":["University of California, Riverside, Riverside, CA, USA"],"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"],"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":5,"corresponding_author_ids":["https://openalex.org/A5075806978"],"corresponding_institution_ids":["https://openalex.org/I103635307"],"apc_list":null,"apc_paid":null,"fwci":0.6578,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.67422639,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"323","last_page":"324"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11005","display_name":"Radiation Effects in Electronics","score":0.9998000264167786,"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":0.9998000264167786,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9995999932289124,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9986000061035156,"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":0.8327531814575195},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7447258234024048},{"id":"https://openalex.org/keywords/x86","display_name":"x86","score":0.7315347194671631},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.49313563108444214},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.4918098747730255},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.414675235748291},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.36159589886665344},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.24540984630584717},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0714024007320404}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8327531814575195},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7447258234024048},{"id":"https://openalex.org/C170723468","wikidata":"https://www.wikidata.org/wiki/Q182933","display_name":"x86","level":3,"score":0.7315347194671631},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.49313563108444214},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.4918098747730255},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.414675235748291},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.36159589886665344},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.24540984630584717},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0714024007320404},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3588195.3595947","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3588195.3595947","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2305.02444","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.02444","pdf_url":"https://arxiv.org/pdf/2305.02444","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2305.02444","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.02444","pdf_url":"https://arxiv.org/pdf/2305.02444","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6078133158","display_name":null,"funder_award_id":"DE-SC0022209","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4372272640.pdf","grobid_xml":"https://content.openalex.org/works/W4372272640.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W2083613288","https://openalex.org/W3140366478","https://openalex.org/W3164390940","https://openalex.org/W4367859812"],"related_works":["https://openalex.org/W3099313426","https://openalex.org/W4287593139","https://openalex.org/W752783541","https://openalex.org/W1506547947","https://openalex.org/W2995605830","https://openalex.org/W4206811032","https://openalex.org/W2086123442","https://openalex.org/W1925544630","https://openalex.org/W2596457687","https://openalex.org/W3212757063"],"abstract_inverted_index":{"General":[0],"matrix/matrix":[1],"multiplication":[2],"(GEMM)":[3],"is":[4],"crucial":[5],"for":[6,67,95],"scientific":[7],"computing":[8,18],"and":[9,24,82,90,98],"machine":[10],"learning.":[11],"However,":[12],"the":[13,17,45,54,58],"increased":[14],"scale":[15],"of":[16,38,104],"platforms":[19],"raises":[20],"concerns":[21],"about":[22],"hardware":[23],"software":[25],"reliability.":[26],"In":[27],"this":[28],"poster,":[29],"we":[30],"present":[31],"FT-GEMM,":[32],"a":[33,64],"high-performance":[34],"GEMM":[35,59],"being":[36],"capable":[37],"tolerating":[39],"soft":[40],"errors":[41,105],"on-the-fly.":[42],"We":[43,62],"incorporate":[44],"fault":[46],"tolerant":[47],"functionality":[48],"at":[49],"algorithmic":[50],"level":[51],"by":[52,92],"fusing":[53],"memory-intensive":[55],"operations":[56],"into":[57],"assembly":[60],"kernels.":[61],"design":[63],"cache-friendly":[65],"scheme":[66],"parallel":[68,99],"FT-GEMM.":[69],"Experimental":[70],"results":[71],"on":[72],"Intel":[73,87],"Cascade":[74],"Lake":[75],"demonstrate":[76],"that":[77],"FT-GEMM":[78],"offers":[79],"high":[80],"reliability":[81],"performance":[83],"--":[84],"faster":[85],"than":[86],"MKL,":[88],"OpenBLAS,":[89],"BLIS":[91],"3.50%\\sim":[93],"22.14%":[94],"both":[96],"serial":[97],"GEMM,":[100],"even":[101],"under":[102],"hundreds":[103],"injected":[106],"per":[107],"minute.":[108]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2023-05-07T00:00:00"}
