{"id":"https://openalex.org/W4317600314","doi":"https://doi.org/10.1109/aiccsa56895.2022.10017947","title":"Optimization of Matrix-Matrix Multiplication Algorithm for Matrix-Panel Multiplication on Intel KNL","display_name":"Optimization of Matrix-Matrix Multiplication Algorithm for Matrix-Panel Multiplication on Intel KNL","publication_year":2022,"publication_date":"2022-12-01","ids":{"openalex":"https://openalex.org/W4317600314","doi":"https://doi.org/10.1109/aiccsa56895.2022.10017947"},"language":"en","primary_location":{"id":"doi:10.1109/aiccsa56895.2022.10017947","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/aiccsa56895.2022.10017947","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/ACS 19th International Conference on Computer Systems and Applications (AICCSA)","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/A5081057626","display_name":"Muhammad Rizwan","orcid":"https://orcid.org/0000-0003-0343-6160"},"institutions":[{"id":"https://openalex.org/I141371507","display_name":"Soongsil University","ror":"https://ror.org/017xnm587","country_code":"KR","type":"education","lineage":["https://openalex.org/I141371507"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Muhammad Rizwan","raw_affiliation_strings":["School of Computer Science & Eng., Soongsil University,Seoul,South Korea"],"affiliations":[{"raw_affiliation_string":"School of Computer Science & Eng., Soongsil University,Seoul,South Korea","institution_ids":["https://openalex.org/I141371507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080036624","display_name":"Enoch Jung","orcid":null},"institutions":[{"id":"https://openalex.org/I141371507","display_name":"Soongsil University","ror":"https://ror.org/017xnm587","country_code":"KR","type":"education","lineage":["https://openalex.org/I141371507"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Enoch Jung","raw_affiliation_strings":["School of Computer Science & Eng., Soongsil University,Seoul,South Korea"],"affiliations":[{"raw_affiliation_string":"School of Computer Science & Eng., Soongsil University,Seoul,South Korea","institution_ids":["https://openalex.org/I141371507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057913986","display_name":"Yoosang Park","orcid":"https://orcid.org/0000-0002-7606-820X"},"institutions":[{"id":"https://openalex.org/I141371507","display_name":"Soongsil University","ror":"https://ror.org/017xnm587","country_code":"KR","type":"education","lineage":["https://openalex.org/I141371507"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yoosang Park","raw_affiliation_strings":["School of Computer Science & Eng., Soongsil University,Seoul,South Korea"],"affiliations":[{"raw_affiliation_string":"School of Computer Science & Eng., Soongsil University,Seoul,South Korea","institution_ids":["https://openalex.org/I141371507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044068522","display_name":"Jaeyoung Choi","orcid":"https://orcid.org/0000-0002-7321-9682"},"institutions":[{"id":"https://openalex.org/I141371507","display_name":"Soongsil University","ror":"https://ror.org/017xnm587","country_code":"KR","type":"education","lineage":["https://openalex.org/I141371507"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaeyoung Choi","raw_affiliation_strings":["School of Computer Science & Eng., Soongsil University,Seoul,South Korea"],"affiliations":[{"raw_affiliation_string":"School of Computer Science & Eng., Soongsil University,Seoul,South Korea","institution_ids":["https://openalex.org/I141371507"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yoonhee Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I31766871","display_name":"Sookmyung Women's University","ror":"https://ror.org/00vvvt117","country_code":"KR","type":"education","lineage":["https://openalex.org/I31766871"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yoonhee Kim","raw_affiliation_strings":["Sookmyung Women's University,Department of Computer Science,Seoul,South Korea"],"affiliations":[{"raw_affiliation_string":"Sookmyung Women's University,Department of Computer Science,Seoul,South Korea","institution_ids":["https://openalex.org/I31766871"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5081057626"],"corresponding_institution_ids":["https://openalex.org/I141371507"],"apc_list":null,"apc_paid":null,"fwci":0.7003,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.69789984,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9973000288009644,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9970999956130981,"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/matrix-multiplication","display_name":"Matrix multiplication","score":0.7059018611907959},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6278585195541382},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.6031840443611145},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5790700912475586},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.5443370938301086},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.5063327550888062},{"id":"https://openalex.org/keywords/square-matrix","display_name":"Square matrix","score":0.4779115617275238},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.43824559450149536},{"id":"https://openalex.org/keywords/lu-decomposition","display_name":"LU decomposition","score":0.42655301094055176},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.42550987005233765},{"id":"https://openalex.org/keywords/multiplication-algorithm","display_name":"Multiplication algorithm","score":0.42088478803634644},{"id":"https://openalex.org/keywords/symmetric-matrix","display_name":"Symmetric matrix","score":0.3734078109264374},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.3157065212726593},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25013530254364014},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.24116182327270508},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.09297534823417664},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.07656744122505188},{"id":"https://openalex.org/keywords/eigenvalues-and-eigenvectors","display_name":"Eigenvalues and eigenvectors","score":0.07478231191635132}],"concepts":[{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.7059018611907959},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6278585195541382},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.6031840443611145},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5790700912475586},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.5443370938301086},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.5063327550888062},{"id":"https://openalex.org/C69044650","wikidata":"https://www.wikidata.org/wiki/Q2739329","display_name":"Square matrix","level":4,"score":0.4779115617275238},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.43824559450149536},{"id":"https://openalex.org/C123213974","wikidata":"https://www.wikidata.org/wiki/Q833089","display_name":"LU decomposition","level":4,"score":0.42655301094055176},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.42550987005233765},{"id":"https://openalex.org/C201290732","wikidata":"https://www.wikidata.org/wiki/Q130762","display_name":"Multiplication algorithm","level":3,"score":0.42088478803634644},{"id":"https://openalex.org/C54848796","wikidata":"https://www.wikidata.org/wiki/Q339011","display_name":"Symmetric matrix","level":3,"score":0.3734078109264374},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.3157065212726593},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25013530254364014},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.24116182327270508},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.09297534823417664},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.07656744122505188},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.07478231191635132},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/aiccsa56895.2022.10017947","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/aiccsa56895.2022.10017947","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/ACS 19th International Conference on Computer Systems and Applications (AICCSA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.6200000047683716,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G5299438007","display_name":null,"funder_award_id":"2020M3H6A1084984","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W31923072","https://openalex.org/W1481003809","https://openalex.org/W1947869163","https://openalex.org/W1964031104","https://openalex.org/W1964711958","https://openalex.org/W1988425770","https://openalex.org/W2030167104","https://openalex.org/W2061788314","https://openalex.org/W2073061372","https://openalex.org/W2084379367","https://openalex.org/W2143092196","https://openalex.org/W2148979214","https://openalex.org/W2252007067","https://openalex.org/W2257426362","https://openalex.org/W2499702955","https://openalex.org/W2531559628","https://openalex.org/W2753445897","https://openalex.org/W2788448998","https://openalex.org/W2806900363","https://openalex.org/W2914926228","https://openalex.org/W2954429496","https://openalex.org/W3098012547","https://openalex.org/W3153543698","https://openalex.org/W4230289604"],"related_works":["https://openalex.org/W2026020054","https://openalex.org/W2355201024","https://openalex.org/W2373948857","https://openalex.org/W2381807583","https://openalex.org/W2020771115","https://openalex.org/W2043539212","https://openalex.org/W2124740611","https://openalex.org/W1990921965","https://openalex.org/W2369377693","https://openalex.org/W4238100916"],"abstract_inverted_index":{"The":[0],"most":[1],"scientific":[2],"and":[3,26,78,96,102],"numerical":[4],"problems":[5],"can":[6],"be":[7],"solved":[8],"using":[9],"the":[10,20,33,44,68,80,88,100,123,130],"system":[11],"of":[12,22,36,71,90,137],"equations":[13],"in":[14,59],"linear":[15,23,49],"algebra.":[16],"Matrix-matrix":[17],"multiplication":[18,108,134,142],"is":[19,63],"foundation":[21],"algebra":[24],"equations,":[25],"its":[27],"optimization":[28],"has":[29,40],"an":[30],"impact":[31],"on":[32,75,99],"overall":[34],"performance":[35,127],"a":[37,145],"system.":[38],"ScaLAPACK":[39,124,138],"established":[41],"itself":[42],"as":[43],"industry":[45],"standard":[46],"for":[47,110,116,144],"dense":[48],"algebraic":[50],"computations,":[51],"developed":[52],"30":[53],"years":[54],"ago.":[55],"Owing":[56],"to":[57,65],"advancements":[58],"microprocessor":[60],"architectures,":[61],"it":[62],"difficult":[64],"fully":[66],"utilize":[67],"hardware":[69],"capabilities":[70],"legacy":[72],"software":[73],"systems":[74],"modern":[76],"architectures":[77],"achieve":[79],"maximum":[81],"performance.":[82],"In":[83],"this":[84],"study,":[85],"we":[86],"analyzed":[87],"effects":[89],"matrix":[91],"size,":[92],"register":[93],"blocking":[94],"parameters,":[95],"thread":[97],"distribution":[98],"performance,":[101],"improved":[103],"our":[104,140],"previously":[105],"implemented":[106],"matrix-matrix":[107,133,141],"routine":[109,135,143],"matrix-panel":[111],"multiplication,":[112],"which":[113],"performed":[114],"well":[115],"large-sized":[117],"square":[118],"matrices.":[119],"We":[120],"also":[121],"presented":[122],"QR":[125],"factorization":[126],"by":[128],"replacing":[129],"double-precision":[131],"general":[132],"(DGEMM)":[136],"with":[139],"single":[146],"node":[147],"Intel":[148],"Xeon":[149],"Phi":[150],"Knights":[151],"Landing":[152],"processor.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}