{"id":"https://openalex.org/W3145384893","doi":"https://doi.org/10.1145/3431921","title":"A Set of Batched Basic Linear Algebra Subprograms and LAPACK Routines","display_name":"A Set of Batched Basic Linear Algebra Subprograms and LAPACK Routines","publication_year":2021,"publication_date":"2021-06-26","ids":{"openalex":"https://openalex.org/W3145384893","doi":"https://doi.org/10.1145/3431921","mag":"3145384893"},"language":"en","primary_location":{"id":"doi:10.1145/3431921","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3431921","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3431921","source":{"id":"https://openalex.org/S163326656","display_name":"ACM Transactions on Mathematical Software","issn_l":"0098-3500","issn":["0098-3500","1557-7295"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Mathematical Software","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3431921","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077268543","display_name":"Ahmad Abdelfattah","orcid":"https://orcid.org/0000-0001-5054-4784"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ahmad Abdelfattah","raw_affiliation_strings":["University of Tennessee, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee, USA","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003872070","display_name":"Timothy Costa","orcid":"https://orcid.org/0000-0003-4485-5900"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Timothy Costa","raw_affiliation_strings":["NVIDIA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075517045","display_name":"Jack Dongarra","orcid":"https://orcid.org/0000-0003-3247-1782"},"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"]},{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jack Dongarra","raw_affiliation_strings":["University of Tennessee, Oak Ridge National Laboratory, and University of Manchester, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee, Oak Ridge National Laboratory, and University of Manchester, USA","institution_ids":["https://openalex.org/I1289243028","https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104910026","display_name":"Mark Gates","orcid":"https://orcid.org/0000-0003-2996-1641"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Gates","raw_affiliation_strings":["University of Tennessee, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee, USA","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101964224","display_name":"Azzam Haidar","orcid":"https://orcid.org/0000-0002-3177-2084"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Azzam Haidar","raw_affiliation_strings":["NVIDIA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025834032","display_name":"Sven Hammarling","orcid":"https://orcid.org/0000-0003-3865-4897"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sven Hammarling","raw_affiliation_strings":["University of Manchester, UK"],"raw_orcid":"https://orcid.org/0000-0003-3865-4897","affiliations":[{"raw_affiliation_string":"University of Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069339254","display_name":"Nicholas J. Higham","orcid":"https://orcid.org/0000-0001-5956-4976"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nicholas J. Higham","raw_affiliation_strings":["University of Manchester, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070456582","display_name":"Jakub Kurzak","orcid":"https://orcid.org/0000-0002-9697-0145"},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jakub Kurzak","raw_affiliation_strings":["AMD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AMD, USA","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073990539","display_name":"Piotr \u0141uszczek","orcid":"https://orcid.org/0000-0002-0089-6965"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Piotr Luszczek","raw_affiliation_strings":["University of Tennessee, USA"],"raw_orcid":"https://orcid.org/0000-0002-0089-6965","affiliations":[{"raw_affiliation_string":"University of Tennessee, USA","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083604741","display_name":"Stanimire Tomov","orcid":"https://orcid.org/0000-0002-5937-7959"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stanimire Tomov","raw_affiliation_strings":["University of Tennessee, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee, USA","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079445612","display_name":"Mawussi Zounon","orcid":"https://orcid.org/0000-0002-6955-1500"},"institutions":[{"id":"https://openalex.org/I86122600","display_name":"Numerical Algorithms Group (United Kingdom)","ror":"https://ror.org/04pcnys31","country_code":"GB","type":"company","lineage":["https://openalex.org/I86122600"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mawussi Zounon","raw_affiliation_strings":["NAG Ltd., UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NAG Ltd., UK","institution_ids":["https://openalex.org/I86122600"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.4313,"has_fulltext":true,"cited_by_count":36,"citation_normalized_percentile":{"value":0.96572303,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"47","issue":"3","first_page":"1","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9987000226974487,"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":0.9987000226974487,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.804811954498291},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.7556778192520142},{"id":"https://openalex.org/keywords/double-precision-floating-point-format","display_name":"Double-precision floating-point format","score":0.6482423543930054},{"id":"https://openalex.org/keywords/coprocessor","display_name":"Coprocessor","score":0.6156262159347534},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6039929389953613},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5470092296600342},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5148674249649048},{"id":"https://openalex.org/keywords/single-precision-floating-point-format","display_name":"Single-precision floating-point format","score":0.48919203877449036},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.46281516551971436},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.4088231325149536},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.40320056676864624},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24653425812721252},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.17066356539726257},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1442030966281891}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.804811954498291},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.7556778192520142},{"id":"https://openalex.org/C35912277","wikidata":"https://www.wikidata.org/wiki/Q1243369","display_name":"Double-precision floating-point format","level":3,"score":0.6482423543930054},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.6156262159347534},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6039929389953613},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5470092296600342},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5148674249649048},{"id":"https://openalex.org/C133095886","wikidata":"https://www.wikidata.org/wiki/Q1307173","display_name":"Single-precision floating-point format","level":3,"score":0.48919203877449036},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.46281516551971436},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.4088231325149536},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.40320056676864624},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24653425812721252},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.17066356539726257},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1442030966281891},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3431921","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3431921","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3431921","source":{"id":"https://openalex.org/S163326656","display_name":"ACM Transactions on Mathematical Software","issn_l":"0098-3500","issn":["0098-3500","1557-7295"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Mathematical Software","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/5f33a552-becc-479b-85c8-c1a638402f83","is_oa":false,"landing_page_url":"https://research.manchester.ac.uk/en/publications/5f33a552-becc-479b-85c8-c1a638402f83","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Abdelfattah, A, Costa, T, Dongarra, J, Gates, M, Haidar, A, Hammarling, S, Higham, N, Kurzak, J, Luszczek, P, Tomov, S & Zounon, M 2020, 'A Set of Batched Basic Linear Algebra Subprograms and LAPACK Routines', ACM Transactions on Mathematical Software.","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.atira.dk:publications/5f33a552-becc-479b-85c8-c1a638402f83","is_oa":false,"landing_page_url":"https://www.research.manchester.ac.uk/portal/en/publications/a-set-of-batched-basic-linear-algebra-subprograms-and-lapack-routines(5f33a552-becc-479b-85c8-c1a638402f83).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Abdelfattah, A, Costa, T, Dongarra, J, Gates, M, Haidar, A, Hammarling, S, Higham, N, Kurzak, J, Luszczek, P, Tomov, S & Zounon, M 2020, 'A Set of Batched Basic Linear Algebra Subprograms and LAPACK Routines', ACM Transactions on Mathematical Software.","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1145/3431921","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3431921","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3431921","source":{"id":"https://openalex.org/S163326656","display_name":"ACM Transactions on Mathematical Software","issn_l":"0098-3500","issn":["0098-3500","1557-7295"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Mathematical Software","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1500703584","display_name":"SI2:SSE: MAtrix, TEnsor, and Deep-Learning Optimized Routines (MATEDOR)","funder_award_id":"1740250","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1776790347","display_name":"Parallel Numerical Linear Algebra for Future Extreme-Scale Systems","funder_award_id":"671633","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G1904859712","display_name":null,"funder_award_id":"OAC 2004850","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5781530723","display_name":null,"funder_award_id":"N14-11-00190","funder_id":"https://openalex.org/F4320324099","funder_display_name":"Russian Science Foundation"},{"id":"https://openalex.org/G7890925933","display_name":"CSR:Medium:Collaborative Research: SparseKaffe: high-performance, auto-tuned, energy-aware algorithms for sparse direct methods on modern heterogeneous architectures","funder_award_id":"1514286","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8084533499","display_name":null,"funder_award_id":"OAC 1740250","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8272958095","display_name":null,"funder_award_id":"CSR 1514286","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8753669605","display_name":null,"funder_award_id":"N14-11-00190","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320324099","display_name":"Russian Science Foundation","ror":"https://ror.org/03y2gwe85"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3145384893.pdf","grobid_xml":"https://content.openalex.org/works/W3145384893.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W133977063","https://openalex.org/W985373623","https://openalex.org/W1737435842","https://openalex.org/W1985691044","https://openalex.org/W1988425770","https://openalex.org/W1991324025","https://openalex.org/W2016279572","https://openalex.org/W2018419001","https://openalex.org/W2028425870","https://openalex.org/W2038469228","https://openalex.org/W2054658678","https://openalex.org/W2057711597","https://openalex.org/W2090593986","https://openalex.org/W2091087653","https://openalex.org/W2099021415","https://openalex.org/W2127906479","https://openalex.org/W2129170915","https://openalex.org/W2130289795","https://openalex.org/W2162322364","https://openalex.org/W2170597842","https://openalex.org/W2183156981","https://openalex.org/W2499931820","https://openalex.org/W2622428623","https://openalex.org/W2887881931","https://openalex.org/W2903589674","https://openalex.org/W2963392252","https://openalex.org/W2983126917","https://openalex.org/W4242726609"],"related_works":["https://openalex.org/W3150370983","https://openalex.org/W2239119680","https://openalex.org/W1564887326","https://openalex.org/W3150959508","https://openalex.org/W2116803521","https://openalex.org/W2773283032","https://openalex.org/W1571090276","https://openalex.org/W3215589575","https://openalex.org/W1973800584","https://openalex.org/W2185760795"],"abstract_inverted_index":{"This":[0],"article":[1],"describes":[2],"a":[3,7,37,41],"standard":[4,104],"API":[5],"for":[6],"set":[8],"of":[9,63,76,106],"Batched":[10,42],"Basic":[11],"Linear":[12],"Algebra":[13],"Subprograms":[14],"(Batched":[15],"BLAS":[16,25,43],"or":[17],"BBLAS).":[18],"The":[19,45,66],"focus":[20],"is":[21,68,125],"on":[22,27,78],"many":[23,128],"independent":[24],"operations":[26],"small":[28],"matrices":[29,46,61],"that":[30],"are":[31,47,62],"grouped":[32,48],"together":[33,49],"and":[34,85,90,92,108,115],"processed":[35],"by":[36],"single":[38,107],"routine,":[39],"called":[40],"routine.":[44],"in":[50,118,127],"uniformly":[51],"sized":[52],"groups,":[53],"with":[54,96,137],"just":[55],"one":[56],"group":[57],"if":[58],"all":[59],"the":[60,103,119],"equal":[64],"size.":[65],"aim":[67],"to":[69],"provide":[70],"more":[71],"efficient,":[72],"but":[73],"portable,":[74],"implementations":[75],"algorithms":[77],"high-performance":[79],"many-core":[80,86],"platforms.":[81],"These":[82],"include":[83,113],"multicore":[84],"CPU":[87],"processors,":[88],"GPUs":[89],"coprocessors,":[91],"other":[93],"hardware":[94],"accelerators":[95],"floating-point":[97],"compute":[98],"facility.":[99],"As":[100],"well":[101],"as":[102,134],"types":[105],"double":[109],"precision,":[110],"we":[111],"also":[112],"half":[114,123],"quadruple":[116],"precision":[117,124],"standard.":[120],"In":[121],"particular,":[122],"used":[126],"very":[129],"large":[130],"scale":[131],"applications,":[132],"such":[133],"those":[135],"associated":[136],"machine":[138],"learning.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-27T08:28:00.272161","created_date":"2025-10-10T00:00:00"}
