{"id":"https://openalex.org/W1839773802","doi":"https://doi.org/10.1145/2818311","title":"KBLAS","display_name":"KBLAS","publication_year":2016,"publication_date":"2016-05-10","ids":{"openalex":"https://openalex.org/W1839773802","doi":"https://doi.org/10.1145/2818311","mag":"1839773802"},"language":"en","primary_location":{"id":"doi:10.1145/2818311","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2818311","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/A5077268543","display_name":"Ahmad Abdelfattah","orcid":"https://orcid.org/0000-0001-5054-4784"},"institutions":[{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Ahmad Abdelfattah","raw_affiliation_strings":["Extreme Computing Research Center, KAUST"],"affiliations":[{"raw_affiliation_string":"Extreme Computing Research Center, KAUST","institution_ids":["https://openalex.org/I4210099236"]}]},{"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/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"David Keyes","raw_affiliation_strings":["Extreme Computing Research Center, KAUST"],"affiliations":[{"raw_affiliation_string":"Extreme Computing Research Center, KAUST","institution_ids":["https://openalex.org/I4210099236"]}]},{"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/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hatem Ltaief","raw_affiliation_strings":["Extreme Computing Research Center, KAUST"],"affiliations":[{"raw_affiliation_string":"Extreme Computing Research Center, KAUST","institution_ids":["https://openalex.org/I4210099236"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5077268543"],"corresponding_institution_ids":["https://openalex.org/I4210099236"],"apc_list":null,"apc_paid":null,"fwci":5.0454,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":{"value":0.95514388,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"42","issue":"3","first_page":"1","last_page":"31"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9984999895095825,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9922999739646912,"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":0.8415683507919312},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7706494331359863},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7229764461517334},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6760468482971191},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5051735043525696},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4813138246536255},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.46122390031814575},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.4592689275741577},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4584566652774811},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.42639973759651184},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.22038668394088745},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1024126410484314},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10210981965065002},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09358492493629456}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8415683507919312},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7706494331359863},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7229764461517334},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6760468482971191},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5051735043525696},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4813138246536255},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.46122390031814575},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4592689275741577},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4584566652774811},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.42639973759651184},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.22038668394088745},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1024126410484314},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10210981965065002},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09358492493629456},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2818311","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2818311","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:10754/621727","is_oa":false,"landing_page_url":"http://hdl.handle.net/10754/621727","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/F4320309370","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W187499919","https://openalex.org/W1473251595","https://openalex.org/W1762731526","https://openalex.org/W1957031661","https://openalex.org/W2002555321","https://openalex.org/W2016279572","https://openalex.org/W2032309817","https://openalex.org/W2047614366","https://openalex.org/W2048558763","https://openalex.org/W2063186542","https://openalex.org/W2090593986","https://openalex.org/W2099021415","https://openalex.org/W2125960020","https://openalex.org/W2134775085","https://openalex.org/W2146959317","https://openalex.org/W2506226536","https://openalex.org/W2561675875","https://openalex.org/W4241513866"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825"],"abstract_inverted_index":{"KBLAS":[0,55,94,113,139,179],"is":[1,27,39,114],"an":[2],"open-source,":[3],"high-performance":[4,180],"library":[5],"that":[6],"provides":[7,122],"optimized":[8],"kernels":[9,95,120,181],"for":[10,87,191],"a":[11,35,49,100,123,127],"subset":[12,177],"of":[13,23,32,52,107,130,178],"Level":[14],"2":[15],"BLAS":[16,72,188],"functionalities":[17],"on":[18,58,145,162],"CUDA-enabled":[19],"GPUs.":[20],"Since":[21],"performance":[22,125,140,174],"dense":[24,89],"matrix-vector":[25],"multiplication":[26],"hindered":[28],"by":[29],"the":[30,70,105,138,159],"overhead":[31],"memory":[33,80],"accesses,":[34],"double-buffering":[36],"optimization":[37,75],"technique":[38,76],"employed":[40],"to":[41,99,153],"overlap":[42],"data":[43],"motion":[44],"with":[45,69,84,117],"computation.":[46],"After":[47],"identifying":[48],"proper":[50],"set":[51],"tuning":[53],"parameters,":[54],"efficiently":[56],"runs":[57],"various":[59],"GPU":[60,164],"architectures":[61],"while":[62],"avoiding":[63],"code":[64],"rewriting":[65],"and":[66,121,135,149,155,165],"retaining":[67],"compliance":[68],"standard":[71,187],"API.":[73],"Another":[74],"allows":[77],"ensuring":[78],"coalesced":[79],"access":[81],"when":[82],"dealing":[83],"submatrices,":[85],"especially":[86],"high-level":[88],"linear":[90],"algebra":[91],"algorithms.":[92],"All":[93],"have":[96,182],"been":[97,183],"leveraged":[98],"multi-GPU":[101],"environment,":[102],"which":[103],"requires":[104],"introduction":[106],"new":[108],"APIs.":[109],"Considering":[110,133],"general":[111],"matrices,":[112,137],"very":[115],"competitive":[116],"existing":[118,142],"state-of-the-art":[119,143],"smoother":[124],"across":[126],"wide":[128],"range":[129],"matrix":[131,147],"dimensions.":[132],"symmetric":[134],"Hermitian":[136],"outperforms":[141],"implementations":[144],"all":[146],"sizes":[148],"achieves":[150],"asymptotically":[151],"up":[152],"50%":[154],"60%":[156],"speedup":[157],"against":[158],"best":[160],"competitor":[161],"single":[163],"multi-GPUs":[166],"systems,":[167],"respectively.":[168],"Performance":[169],"results":[170],"also":[171],"validate":[172],"our":[173],"model.":[175],"A":[176],"integrated":[184],"into":[185],"NVIDIA's":[186],"implementation":[189],"(cuBLAS)":[190],"larger":[192],"dissemination,":[193],"starting":[194],"from":[195],"version":[196],"6.0.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}