{"id":"https://openalex.org/W2601355684","doi":"https://doi.org/10.1145/3267101","title":"Batched Triangular Dense Linear Algebra Kernels for Very Small Matrix Sizes on GPUs","display_name":"Batched Triangular Dense Linear Algebra Kernels for Very Small Matrix Sizes on GPUs","publication_year":2019,"publication_date":"2019-05-03","ids":{"openalex":"https://openalex.org/W2601355684","doi":"https://doi.org/10.1145/3267101","mag":"2601355684"},"language":"en","primary_location":{"id":"doi:10.1145/3267101","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3267101","pdf_url":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022931436","display_name":"Ali Charara","orcid":"https://orcid.org/0000-0002-9509-7794"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Ali Charara","raw_affiliation_strings":["Extreme Computing Research Center, King Abdullah University of Science and Technology, Thuwal, Kingdom of Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0002-9509-7794","affiliations":[{"raw_affiliation_string":"Extreme Computing Research Center, King Abdullah University of Science and Technology, Thuwal, Kingdom of Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021283893","display_name":"David E. Keyes","orcid":"https://orcid.org/0000-0002-4052-7224"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"David Keyes","raw_affiliation_strings":["Extreme Computing Research Center, King Abdullah University of Science and Technology, Thuwal, Kingdom of Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Extreme Computing Research Center, King Abdullah University of Science and Technology, Thuwal, Kingdom of Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017526753","display_name":"Hatem Ltaief","orcid":"https://orcid.org/0000-0002-6897-1095"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Hatem Ltaief","raw_affiliation_strings":["Extreme Computing Research Center, King Abdullah University of Science and Technology, Thuwal, Kingdom of Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Extreme Computing Research Center, King Abdullah University of Science and Technology, Thuwal, Kingdom of Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I71920554"],"apc_list":null,"apc_paid":null,"fwci":2.3941,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.879013,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"45","issue":"2","first_page":"1","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994000196456909,"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":0.9994000196456909,"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/T12303","display_name":"Tensor decomposition and applications","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9904999732971191,"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":0.7676199674606323},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.704167902469635},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6889173984527588},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5871312022209167},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5124147534370422},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.43641820549964905},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4270186722278595},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4218381345272064},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1667877733707428},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11987176537513733}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7676199674606323},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.704167902469635},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6889173984527588},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5871312022209167},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5124147534370422},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.43641820549964905},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4270186722278595},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4218381345272064},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1667877733707428},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11987176537513733},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3267101","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3267101","pdf_url":null,"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:repository.kaust.edu.sa:10754/622975","is_oa":false,"landing_page_url":"http://hdl.handle.net/10754/622975","pdf_url":null,"source":{"id":"https://openalex.org/S4306401596","display_name":"King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I71920554","host_organization_name":"King Abdullah University of Science and Technology","host_organization_lineage":["https://openalex.org/I71920554"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320322320","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1028753842","https://openalex.org/W1563304459","https://openalex.org/W1569304948","https://openalex.org/W1627560504","https://openalex.org/W1737435842","https://openalex.org/W1839773802","https://openalex.org/W1991324025","https://openalex.org/W1997033059","https://openalex.org/W2000867371","https://openalex.org/W2006682733","https://openalex.org/W2013424510","https://openalex.org/W2018419001","https://openalex.org/W2032052535","https://openalex.org/W2038469228","https://openalex.org/W2049009664","https://openalex.org/W2057897376","https://openalex.org/W2063722389","https://openalex.org/W2079658918","https://openalex.org/W2084379367","https://openalex.org/W2127906479","https://openalex.org/W2131752595","https://openalex.org/W2134775085","https://openalex.org/W2138215414","https://openalex.org/W2166737459","https://openalex.org/W2208494155","https://openalex.org/W2268122618","https://openalex.org/W2340091566","https://openalex.org/W2410272182","https://openalex.org/W2493354458","https://openalex.org/W2499931820","https://openalex.org/W2505064766","https://openalex.org/W2531348778","https://openalex.org/W2542358525","https://openalex.org/W2549815592","https://openalex.org/W2563513434","https://openalex.org/W2565236682","https://openalex.org/W2609029235","https://openalex.org/W2612290557","https://openalex.org/W2622509770","https://openalex.org/W2736056409","https://openalex.org/W2754194450","https://openalex.org/W3031997026","https://openalex.org/W4206802205","https://openalex.org/W4229666556"],"related_works":["https://openalex.org/W3062287","https://openalex.org/W2380390332","https://openalex.org/W2742145873","https://openalex.org/W4245975140","https://openalex.org/W2062253548","https://openalex.org/W4225414539","https://openalex.org/W4289522463","https://openalex.org/W1977763331","https://openalex.org/W4318483369","https://openalex.org/W2076165488"],"abstract_inverted_index":{"Batched":[0],"dense":[1,107],"linear":[2,108],"algebra":[3,109],"kernels":[4,32,110,146],"are":[5,33],"becoming":[6],"ubiquitous":[7],"in":[8,15,21],"scientific":[9],"applications,":[10],"ranging":[11],"from":[12],"tensor":[13],"contractions":[14],"deep":[16],"learning":[17],"to":[18,39,117],"data":[19,114,133],"compression":[20],"hierarchical":[22],"low-rank":[23],"matrix":[24,43],"approximation.":[25],"Within":[26],"a":[27,74,101],"single":[28,120],"API":[29,51],"call,":[30],"these":[31],"capable":[34],"of":[35,41,49,57,76,100,104],"simultaneously":[36],"launching":[37],"up":[38],"thousands":[40],"similar":[42],"computations,":[44],"removing":[45],"the":[46,55,58,66,77,84,96,129,143],"expensive":[47],"overhead":[48],"multiple":[50,122],"calls":[52],"while":[53],"increasing":[54],"occupancy":[56],"underlying":[59],"hardware.":[60],"A":[61],"challenge":[62],"is":[63,81],"that":[64],"for":[65,89],"existing":[67,148],"hardware":[68],"landscape":[69],"(x86,":[70],"GPUs,":[71],"etc.),":[72],"only":[73],"subset":[75],"required":[78],"batched":[79,105,145],"operations":[80],"implemented":[82],"by":[83],"vendors,":[85],"with":[86],"limited":[87],"support":[88],"very":[90,112],"small":[91,113],"problem":[92],"sizes.":[93],"We":[94],"describe":[95],"design":[97],"and":[98,121,138],"performance":[99],"new":[102,144],"class":[103],"triangular":[106],"on":[111],"sizes":[115],"(up":[116],"256)":[118],"using":[119],"GPUs.":[123],"By":[124],"deploying":[125],"recursive":[126],"formulations,":[127],"stressing":[128],"register":[130],"usage,":[131],"maintaining":[132],"locality,":[134],"reducing":[135],"threads":[136],"synchronization,":[137],"fusing":[139],"successive":[140],"kernel":[141],"calls,":[142],"outperform":[147],"state-of-the-art":[149],"implementations.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}