{"id":"https://openalex.org/W2912427405","doi":"https://doi.org/10.1109/bigdata.2018.8622013","title":"A Flexible-blocking Based Approach for Performance Tuning of Matrix Multiplication Routines for Large Matrices with Edge Cases","display_name":"A Flexible-blocking Based Approach for Performance Tuning of Matrix Multiplication Routines for Large Matrices with Edge Cases","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2912427405","doi":"https://doi.org/10.1109/bigdata.2018.8622013","mag":"2912427405"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2018.8622013","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2018.8622013","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/servlets/purl/1557472","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074646416","display_name":"Md Mosharaf Hossain","orcid":"https://orcid.org/0000-0002-1554-3476"},"institutions":[{"id":"https://openalex.org/I63920570","display_name":"Tennessee Technological University","ror":"https://ror.org/05drmrq39","country_code":"US","type":"education","lineage":["https://openalex.org/I63920570"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Md Mosharaf Hossain","raw_affiliation_strings":["Computer Science, Tennessee Technological University, TN"],"affiliations":[{"raw_affiliation_string":"Computer Science, Tennessee Technological University, TN","institution_ids":["https://openalex.org/I63920570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082236201","display_name":"Thomas M. Hines","orcid":null},"institutions":[{"id":"https://openalex.org/I63920570","display_name":"Tennessee Technological University","ror":"https://ror.org/05drmrq39","country_code":"US","type":"education","lineage":["https://openalex.org/I63920570"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas M. Hines","raw_affiliation_strings":["Computer Science, Tennessee Technological University, TN"],"affiliations":[{"raw_affiliation_string":"Computer Science, Tennessee Technological University, TN","institution_ids":["https://openalex.org/I63920570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041321160","display_name":"Sheikh Ghafoor","orcid":"https://orcid.org/0000-0001-7175-1619"},"institutions":[{"id":"https://openalex.org/I63920570","display_name":"Tennessee Technological University","ror":"https://ror.org/05drmrq39","country_code":"US","type":"education","lineage":["https://openalex.org/I63920570"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sheikh K. Ghafoor","raw_affiliation_strings":["Computer Science, Tennessee Technological University, TN"],"affiliations":[{"raw_affiliation_string":"Computer Science, Tennessee Technological University, TN","institution_ids":["https://openalex.org/I63920570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013969000","display_name":"Sheikh Rabiul Islam","orcid":"https://orcid.org/0000-0001-9610-0230"},"institutions":[{"id":"https://openalex.org/I63920570","display_name":"Tennessee Technological University","ror":"https://ror.org/05drmrq39","country_code":"US","type":"education","lineage":["https://openalex.org/I63920570"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sheikh Rabiul Islam","raw_affiliation_strings":["Computer Science, Tennessee Technological University, TN"],"affiliations":[{"raw_affiliation_string":"Computer Science, Tennessee Technological University, TN","institution_ids":["https://openalex.org/I63920570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014168997","display_name":"Ramakrishnan Kannan","orcid":"https://orcid.org/0000-0002-5852-4806"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ramakrishnan Kannan","raw_affiliation_strings":["Oak Ridge National Laboratory, TN"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, TN","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079418386","display_name":"Sreenivas R. Sukumar","orcid":"https://orcid.org/0000-0003-4031-2888"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sreenivas R. Sukumar","raw_affiliation_strings":["CRAY Inc"],"affiliations":[{"raw_affiliation_string":"CRAY Inc","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5074646416"],"corresponding_institution_ids":["https://openalex.org/I63920570"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19570736,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"3853","last_page":"3862"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9988999962806702,"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":0.9987999796867371,"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":0.7679013609886169},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.7517342567443848},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6708586812019348},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6560086011886597},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.6477094292640686},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.5622406005859375},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.506503701210022},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.47362297773361206},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4545248746871948},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.4543428421020508},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.41111642122268677},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.41045740246772766},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4017380177974701},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1447450816631317}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7679013609886169},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.7517342567443848},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6708586812019348},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6560086011886597},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.6477094292640686},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.5622406005859375},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.506503701210022},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.47362297773361206},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4545248746871948},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.4543428421020508},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.41111642122268677},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.41045740246772766},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4017380177974701},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1447450816631317},{"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},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata.2018.8622013","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2018.8622013","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:1557472","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1557472","pdf_url":"https://www.osti.gov/servlets/purl/1557472","source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:osti.gov:1557472","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1557472","pdf_url":"https://www.osti.gov/servlets/purl/1557472","source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1645119126","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G2042897603","display_name":null,"funder_award_id":"DE-AC05-00OR2272","funder_id":"https://openalex.org/F4320316892","funder_display_name":"UT-Battelle"},{"id":"https://openalex.org/G2296932962","display_name":null,"funder_award_id":"DE-AC05-00OR227","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G3299391273","display_name":null,"funder_award_id":"E-AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G5726405315","display_name":null,"funder_award_id":"DE-AC05","funder_id":"https://openalex.org/F4320306250","funder_display_name":"Battelle"},{"id":"https://openalex.org/G6129992089","display_name":null,"funder_award_id":"DE-AC05-","funder_id":"https://openalex.org/F4320316892","funder_display_name":"UT-Battelle"},{"id":"https://openalex.org/G6864165199","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320306250","funder_display_name":"Battelle"},{"id":"https://openalex.org/G691578896","display_name":null,"funder_award_id":"DE-AC05-00OR2272","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G7995982022","display_name":null,"funder_award_id":"DE-AC05","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8414908677","display_name":null,"funder_award_id":"DE-AC0","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8799952057","display_name":null,"funder_award_id":"DE-AC05-00OR22","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8813984943","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320316892","funder_display_name":"UT-Battelle"},{"id":"https://openalex.org/G8906985441","display_name":null,"funder_award_id":"00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8943143067","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320316892","funder_display_name":"UT-Battelle"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320306250","display_name":"Battelle","ror":"https://ror.org/01h5tnr73"},{"id":"https://openalex.org/F4320316892","display_name":"UT-Battelle","ror":"https://ror.org/04nza6677"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2912427405.pdf","grobid_xml":"https://content.openalex.org/works/W2912427405.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W44492739","https://openalex.org/W1485499095","https://openalex.org/W1514353881","https://openalex.org/W1665412445","https://openalex.org/W1708603942","https://openalex.org/W1851570257","https://openalex.org/W1983157164","https://openalex.org/W1988425770","https://openalex.org/W2002257715","https://openalex.org/W2038469228","https://openalex.org/W2043275593","https://openalex.org/W2064872546","https://openalex.org/W2073061372","https://openalex.org/W2076346710","https://openalex.org/W2084379367","https://openalex.org/W2084391969","https://openalex.org/W2102182691","https://openalex.org/W2135653967","https://openalex.org/W2136952590","https://openalex.org/W2148542244","https://openalex.org/W2252007067","https://openalex.org/W2412152731","https://openalex.org/W2516525699","https://openalex.org/W2963674387","https://openalex.org/W3136479147","https://openalex.org/W6629095914","https://openalex.org/W6680007323"],"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/W2596457687","https://openalex.org/W3212757063","https://openalex.org/W2093666864"],"abstract_inverted_index":{"Efficient":[0],"and":[1,18,41,92,154],"scalable":[2],"matrix":[3,66],"operations":[4,27],"are":[5,36,61,109],"being":[6],"highly":[7,110],"demanding":[8],"in":[9,28,95,132,212],"the":[10,29,53,59,64,87,103,106,116,121,133,141,158,161,179,185,191,194,199,202,207,213,227],"recent":[11],"era":[12],"of":[13,52,58,160,193,201,209],"Machine":[14],"Learning,":[15,17],"Deep":[16],"Big":[19],"Data":[20],"Analytics.":[21],"The":[22,46,83,136],"two":[23],"commonly":[24],"used":[25,211],"matrix-matrix":[26],"Basic":[30],"Linear":[31],"Algebra":[32],"Subprograms":[33],"(BLAS)":[34],"specification":[35],"General":[37],"Matrix-Matrix":[38],"multiplication":[39],"(GEMM)":[40],"Symmetric":[42],"Rank-k":[43],"update":[44],"(SYRK).":[45],"SYRK":[47],"routine":[48],"is":[49,67,139],"a":[50,151,169],"specialization":[51],"GEMM":[54],"routine,":[55],"where":[56],"half":[57],"multiplications":[60],"skipped":[62],"as":[63,204,206],"resultant":[65],"known":[68],"to":[69,177,184],"be":[70],"symmetric.":[71],"Fortunately,":[72],"several":[73],"linear":[74],"algebra":[75],"libraries":[76,84,108,144],"implement":[77],"these":[78],"BLAS":[79],"routines":[80],"quite":[81],"efficiently.":[82],"usually":[85],"partition":[86],"input":[88,162,195],"matrices":[89,122,196,203],"into":[90],"blocks":[91,192],"place":[93],"them":[94],"processor":[96,152],"caches,":[97],"thus":[98],"improving":[99],"performance":[100,117,220],"by":[101],"leveraging":[102],"caches.":[104],"However,":[105],"contemporary":[107,186],"optimized":[111],"for":[112,120,226],"squarish":[113],"matrices,":[114],"but":[115],"degrades":[118],"significantly":[119],"with":[123],"edge":[124,228],"case":[125,229],"(strictly":[126],"thin":[127],"or":[128],"strictly":[129],"fat":[130],"shapes)":[131],"multicore":[134,223],"machine.":[135],"primary":[137],"reason":[138],"that":[140],"current":[142],"state-of-the-art":[143],"make":[145],"fixed":[146],"block":[147],"shapes":[148,200],"based":[149,197],"on":[150,198,222],"architecture,":[153],"do":[155],"not":[156],"consider":[157],"shape":[159],"matrices.":[163,230],"In":[164,182],"this":[165],"paper,":[166],"we":[167,173],"propose":[168],"new":[170],"blocking":[171],"approach,":[172],"name":[174],"it":[175],"Flexible-blocking,":[176],"mitigate":[178],"scalability":[180],"issues.":[181],"contrast":[183],"libraries,":[187],"our":[188],"approach":[189],"formulates":[190],"well":[205],"number":[208],"threads":[210],"implementation.":[214],"Our":[215],"proposed":[216],"technique":[217],"shows":[218],"noticeable":[219],"improvement":[221],"shared-memory":[224],"machines":[225]},"counts_by_year":[],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}
