{"id":"https://openalex.org/W4310009594","doi":"https://doi.org/10.1109/ictc55196.2022.9952498","title":"Analysis of Sub-Routines in NVIDIA cuBLAS Library for a series of Matrix-Matrix Multiplications in Transformer","display_name":"Analysis of Sub-Routines in NVIDIA cuBLAS Library for a series of Matrix-Matrix Multiplications in Transformer","publication_year":2022,"publication_date":"2022-10-19","ids":{"openalex":"https://openalex.org/W4310009594","doi":"https://doi.org/10.1109/ictc55196.2022.9952498"},"language":"en","primary_location":{"id":"doi:10.1109/ictc55196.2022.9952498","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc55196.2022.9952498","pdf_url":null,"source":{"id":"https://openalex.org/S4363607740","display_name":"2022 13th International Conference on Information and Communication Technology Convergence (ICTC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 13th International Conference on Information and Communication Technology Convergence (ICTC)","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/A5100334088","display_name":"Donghyeon Kim","orcid":"https://orcid.org/0000-0001-5019-8199"},"institutions":[{"id":"https://openalex.org/I67900169","display_name":"Chung-Ang University","ror":"https://ror.org/01r024a98","country_code":"KR","type":"education","lineage":["https://openalex.org/I67900169"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Donghyeon Kim","raw_affiliation_strings":["Chung-Ang University,Department of Food Engineering,Anseong,Republic of Korea","Department of Food Engineering, Chung-Ang University, Anseong, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chung-Ang University,Department of Food Engineering,Anseong,Republic of Korea","institution_ids":["https://openalex.org/I67900169"]},{"raw_affiliation_string":"Department of Food Engineering, Chung-Ang University, Anseong, Republic of Korea","institution_ids":["https://openalex.org/I67900169"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055981217","display_name":"Inseo Kim","orcid":"https://orcid.org/0000-0003-1260-1850"},"institutions":[{"id":"https://openalex.org/I67900169","display_name":"Chung-Ang University","ror":"https://ror.org/01r024a98","country_code":"KR","type":"education","lineage":["https://openalex.org/I67900169"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Inseo Kim","raw_affiliation_strings":["School of Computer Science and Engineering, Chung-Ang University,Seoul,Republic of Korea","School of Computer Science and Engineering, Chung-Ang University, Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Chung-Ang University,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I67900169"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Chung-Ang University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I67900169"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100676208","display_name":"Jinsung Kim","orcid":"https://orcid.org/0000-0003-3751-8869"},"institutions":[{"id":"https://openalex.org/I67900169","display_name":"Chung-Ang University","ror":"https://ror.org/01r024a98","country_code":"KR","type":"education","lineage":["https://openalex.org/I67900169"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jinsung Kim","raw_affiliation_strings":["School of Computer Science and Engineering, Chung-Ang University,Seoul,Republic of Korea","School of Computer Science and Engineering, Chung-Ang University, Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Chung-Ang University,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I67900169"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Chung-Ang University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I67900169"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I67900169"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"618","last_page":"620"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.998199999332428,"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":0.998199999332428,"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":0.9907000064849854,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9832000136375427,"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":0.7313151955604553},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.6322189569473267},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6061282753944397},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5921201705932617},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4747622013092041},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.4468223452568054},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.43816834688186646},{"id":"https://openalex.org/keywords/matrix-algebra","display_name":"Matrix algebra","score":0.42150741815567017},{"id":"https://openalex.org/keywords/numerical-linear-algebra","display_name":"Numerical linear algebra","score":0.4206872284412384},{"id":"https://openalex.org/keywords/linear-system","display_name":"Linear system","score":0.19920668005943298},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14764806628227234}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7313151955604553},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.6322189569473267},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6061282753944397},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5921201705932617},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4747622013092041},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.4468223452568054},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.43816834688186646},{"id":"https://openalex.org/C2988995629","wikidata":"https://www.wikidata.org/wiki/Q2915729","display_name":"Matrix algebra","level":3,"score":0.42150741815567017},{"id":"https://openalex.org/C163834973","wikidata":"https://www.wikidata.org/wiki/Q2004891","display_name":"Numerical linear algebra","level":3,"score":0.4206872284412384},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.19920668005943298},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14764806628227234},{"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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ictc55196.2022.9952498","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc55196.2022.9952498","pdf_url":null,"source":{"id":"https://openalex.org/S4363607740","display_name":"2022 13th International Conference on Information and Communication Technology Convergence (ICTC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 13th International Conference on Information and Communication Technology Convergence (ICTC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3462278898","display_name":null,"funder_award_id":"2022R1G1A1013586","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2963037989","https://openalex.org/W2963323070","https://openalex.org/W3094502228","https://openalex.org/W3129877167","https://openalex.org/W3163652268","https://openalex.org/W3195577433","https://openalex.org/W4287748555","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6780069040","https://openalex.org/W6784333009","https://openalex.org/W6800751262"],"related_works":["https://openalex.org/W4381050447","https://openalex.org/W622366405","https://openalex.org/W2041511182","https://openalex.org/W2050090934","https://openalex.org/W613626279","https://openalex.org/W616292901","https://openalex.org/W1695940191","https://openalex.org/W4207050455","https://openalex.org/W4206336957","https://openalex.org/W2957897535"],"abstract_inverted_index":{"The":[0],"general":[1],"matrix-matrix":[2,39,91],"multiplication":[3],"(GEMM)":[4],"is":[5,66],"a":[6,11,36,88],"key":[7],"operation":[8],"used":[9,93],"in":[10,68,94],"variety":[12],"of":[13,38,90],"areas":[14],"such":[15],"as":[16],"Computational":[17],"Science,":[18,20],"Data":[19],"Machine":[21],"Learning,":[22],"and":[23,82],"so":[24],"on.":[25],"In":[26,77],"transformers":[27],"which":[28],"are":[29],"foundation":[30],"models,":[31],"Multi-Head":[32],"Attention":[33],"(MHA)":[34],"has":[35],"series":[37,89],"multiplications.":[40],"To":[41],"perform":[42],"the":[43,63,95],"MHA":[44],"on":[45,98],"GPUs,":[46,62],"we":[47,80],"need":[48],"to":[49,70,86],"exploit":[50],"highly":[51],"optimized":[52],"sub-routines":[53,85],"for":[54],"GEMM,":[55],"provided":[56,67],"their":[57],"hardware":[58],"vendor.":[59],"On":[60],"NVIDIA":[61,99],"cuBLAS":[64],"library":[65],"order":[69],"support":[71],"basic":[72],"linear":[73],"algebra":[74],"subprograms":[75],"(BLAS).":[76],"this":[78],"paper,":[79],"examine":[81],"analyze":[83],"several":[84],"handle":[87],"multiplications":[92],"transformer":[96],"model":[97],"GPUs.":[100]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}