{"id":"https://openalex.org/W2767612671","doi":"https://doi.org/10.1145/3126908.3126941","title":"Designing vector-friendly compact BLAS and LAPACK kernels","display_name":"Designing vector-friendly compact BLAS and LAPACK kernels","publication_year":2017,"publication_date":"2017-11-08","ids":{"openalex":"https://openalex.org/W2767612671","doi":"https://doi.org/10.1145/3126908.3126941","mag":"2767612671"},"language":"en","primary_location":{"id":"doi:10.1145/3126908.3126941","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3126908.3126941","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/biblio/1503430","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076399048","display_name":"Kyungjoo Kim","orcid":"https://orcid.org/0000-0003-1241-1934"},"institutions":[{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kyungjoo Kim","raw_affiliation_strings":["Sandia National Laboratories"],"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories","institution_ids":["https://openalex.org/I4210104735"]}]},{"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/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Timothy B. Costa","raw_affiliation_strings":["Intel Corporation"],"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043682360","display_name":"Mehmet Deveci","orcid":"https://orcid.org/0000-0002-3670-3985"},"institutions":[{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mehmet Deveci","raw_affiliation_strings":["Sandia National Laboratories"],"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories","institution_ids":["https://openalex.org/I4210104735"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028880843","display_name":"Andrew Bradley","orcid":"https://orcid.org/0000-0003-4687-198X"},"institutions":[{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew M. Bradley","raw_affiliation_strings":["Sandia National Laboratories"],"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories","institution_ids":["https://openalex.org/I4210104735"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110468921","display_name":"Simon David Hammond","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Simon D. Hammond","raw_affiliation_strings":["Sandia National Laboratories"],"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories","institution_ids":["https://openalex.org/I4210104735"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069028101","display_name":"Murat Efe Guney","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Murat E. Guney","raw_affiliation_strings":["Intel Corporation"],"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022400916","display_name":"Sarah Knepper","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sarah Knepper","raw_affiliation_strings":["Intel Corporation"],"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024848824","display_name":"Shane Story","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shane Story","raw_affiliation_strings":["Intel Corporation"],"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023482297","display_name":"Sivasankaran Rajamanickam","orcid":"https://orcid.org/0000-0002-5854-409X"},"institutions":[{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sivasankaran Rajamanickam","raw_affiliation_strings":["Sandia National Laboratories"],"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories","institution_ids":["https://openalex.org/I4210104735"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5076399048"],"corresponding_institution_ids":["https://openalex.org/I4210104735"],"apc_list":null,"apc_paid":null,"fwci":3.9361,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.95143155,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"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":0.9983000159263611,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9979000091552734,"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/speedup","display_name":"Speedup","score":0.9297475814819336},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8704853057861328},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8294367790222168},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.699661374092102},{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.6845589876174927},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.6513851881027222},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.6390350461006165},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.5155736804008484},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.45257893204689026},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.4384031593799591},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12020456790924072},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08889660239219666}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.9297475814819336},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8704853057861328},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8294367790222168},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.699661374092102},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.6845589876174927},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.6513851881027222},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.6390350461006165},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5155736804008484},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.45257893204689026},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.4384031593799591},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12020456790924072},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08889660239219666},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3126908.3126941","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3126908.3126941","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:1503430","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1503430","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},{"id":"pmh:oai:osti.gov:1513071","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1513071","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},{"id":"pmh:oai:osti.gov:1513342","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1513342","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:osti.gov:1503430","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1503430","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320338291","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W182691100","https://openalex.org/W1480928214","https://openalex.org/W1972944717","https://openalex.org/W1988425770","https://openalex.org/W1996790573","https://openalex.org/W2002257715","https://openalex.org/W2002555321","https://openalex.org/W2023603353","https://openalex.org/W2026883706","https://openalex.org/W2038128042","https://openalex.org/W2068245876","https://openalex.org/W2073061372","https://openalex.org/W2078794610","https://openalex.org/W2084379367","https://openalex.org/W2134633067","https://openalex.org/W2252007067","https://openalex.org/W2268122618","https://openalex.org/W2297617961","https://openalex.org/W2333459898","https://openalex.org/W2340769696","https://openalex.org/W2499931820","https://openalex.org/W2508318196","https://openalex.org/W2529496125","https://openalex.org/W2540804829","https://openalex.org/W2565236682","https://openalex.org/W2579956341"],"related_works":["https://openalex.org/W32529763","https://openalex.org/W2566637483","https://openalex.org/W2127324789","https://openalex.org/W2778498407","https://openalex.org/W3024308452","https://openalex.org/W2099629705","https://openalex.org/W4244894488","https://openalex.org/W4285390450","https://openalex.org/W2979513934","https://openalex.org/W2366442643"],"abstract_inverted_index":{"Many":[0],"applications,":[1],"such":[2],"as":[3],"PDE":[4],"based":[5],"simulations":[6],"and":[7,93,103,124],"machine":[8],"learning,":[9],"apply":[10],"blas/lapack":[11,75,118],"routines":[12,76],"to":[13,59,74,90],"large":[14],"groups":[15],"of":[16,146],"small":[17],"matrices.":[18],"While":[19],"existing":[20],"batched":[21,117],"blas":[22],"APIs":[23,132],"provide":[24,39],"meaningful":[25],"speedup":[26,95],"for":[27,137],"this":[28,44,66],"problem":[29],"type,":[30],"a":[31,48,71,82,134],"non-canonical":[32],"data":[33,51,68],"layout":[34,52,69,87],"enabling":[35],"cross-matrix":[36],"vectorization":[37],"may":[38],"further":[40],"significant":[41],"speedup.":[42],"In":[43],"paper,":[45],"we":[46,141],"propose":[47],"new":[49,72],"compact":[50,67,116],"that":[53,77],"interleaves":[54],"matrices":[55],"in":[56,120,133],"blocks":[57],"according":[58],"the":[60,108,115,131],"SIMD":[61],"vector":[62],"length.":[63],"We":[64,113,129],"combine":[65],"with":[70],"interface":[73],"can":[78],"be":[79],"used":[80],"within":[81],"hierarchical":[83],"parallel":[84],"application.":[85],"Our":[86],"provides":[88],"up":[89],"14X,":[91],"45X,":[92],"27X":[94],"against":[96],"OpenMP":[97],"loops":[98],"around":[99],"optimized":[100],"dgemm,":[101],"dtrsm":[102],"dgetrf":[104],"kernels,":[105],"respectively,":[106],"on":[107],"Intel":[109],"Knights":[110],"Landing":[111],"architecture.":[112],"discuss":[114],"implementations":[119],"two":[121],"libraries,":[122],"KokkosKernels":[123],"Intel\u00ae":[125],"Math":[126],"Kernel":[127],"Library.":[128],"demonstrate":[130],"line":[135],"solver":[136],"coupled":[138],"PDEs.":[139],"Finally,":[140],"present":[142],"detailed":[143],"performance":[144],"analysis":[145],"our":[147],"kernels.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":5}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
