{"id":"https://openalex.org/W2114665465","doi":"https://doi.org/10.1109/ipdps.2008.4536183","title":"Build to order linear algebra kernels","display_name":"Build to order linear algebra kernels","publication_year":2008,"publication_date":"2008-04-01","ids":{"openalex":"https://openalex.org/W2114665465","doi":"https://doi.org/10.1109/ipdps.2008.4536183","mag":"2114665465"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2008.4536183","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2008.4536183","pdf_url":null,"source":{"id":"https://openalex.org/S4210174069","display_name":"Proceedings - IEEE International Parallel and Distributed Processing Symposium","issn_l":"1530-2075","issn":["1530-2075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Symposium on Parallel and Distributed Processing","raw_type":"proceedings-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/A5033999458","display_name":"Jeremy G. Siek","orcid":"https://orcid.org/0000-0002-9894-4856"},"institutions":[{"id":"https://openalex.org/I921990950","display_name":"University of Colorado Denver","ror":"https://ror.org/02hh7en24","country_code":"US","type":"education","lineage":["https://openalex.org/I921990950"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeremy G. Siek","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Colorado, USA","Dept. of Electr. & Comput. Eng., Univ. of Colorado, Denver, CO"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Colorado, USA","institution_ids":[]},{"raw_affiliation_string":"Dept. of Electr. & Comput. Eng., Univ. of Colorado, Denver, CO","institution_ids":["https://openalex.org/I921990950"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030371924","display_name":"Ian Karlin","orcid":null},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ian Karlin","raw_affiliation_strings":["Department of Computer Science, University of Colorado","Dept. of Computer Science, University of Colorado, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Colorado","institution_ids":[]},{"raw_affiliation_string":"Dept. of Computer Science, University of Colorado, USA","institution_ids":["https://openalex.org/I188538660"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041552096","display_name":"Elizabeth R. Jessup","orcid":"https://orcid.org/0000-0002-7740-9985"},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"E. R. Jessup","raw_affiliation_strings":["Department of Computer Science, University of Colorado","Dept. of Computer Science, University of Colorado, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Colorado","institution_ids":[]},{"raw_affiliation_string":"Dept. of Computer Science, University of Colorado, USA","institution_ids":["https://openalex.org/I188538660"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0719,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.88305507,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9988999962806702,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9975000023841858,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8353321552276611},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.7445573210716248},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6950706839561462},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5855485796928406},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5182499885559082},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.4493544101715088},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.44508007168769836},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.4403846561908722},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.4326082766056061},{"id":"https://openalex.org/keywords/powerpc","display_name":"PowerPC","score":0.42568475008010864},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.351596474647522},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3399326801300049},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.31745827198028564},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3152180314064026},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.15618669986724854},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09535405039787292}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8353321552276611},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.7445573210716248},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6950706839561462},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5855485796928406},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5182499885559082},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.4493544101715088},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.44508007168769836},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.4403846561908722},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.4326082766056061},{"id":"https://openalex.org/C56005371","wikidata":"https://www.wikidata.org/wiki/Q209860","display_name":"PowerPC","level":3,"score":0.42568475008010864},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.351596474647522},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3399326801300049},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.31745827198028564},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3152180314064026},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.15618669986724854},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09535405039787292},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ipdps.2008.4536183","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2008.4536183","pdf_url":null,"source":{"id":"https://openalex.org/S4210174069","display_name":"Proceedings - IEEE International Parallel and Distributed Processing Symposium","issn_l":"1530-2075","issn":["1530-2075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Symposium on Parallel and Distributed Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.138.5032","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.138.5032","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ece.colorado.edu/~siek/pohll08.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.5699999928474426}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320307102","display_name":"Intel Corporation","ror":"https://ror.org/01ek73717"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1506342804","https://openalex.org/W1518917853","https://openalex.org/W1561114351","https://openalex.org/W1562955084","https://openalex.org/W1573728792","https://openalex.org/W1581501197","https://openalex.org/W1596846800","https://openalex.org/W1851570257","https://openalex.org/W1964477602","https://openalex.org/W1972209410","https://openalex.org/W2000618606","https://openalex.org/W2002257715","https://openalex.org/W2020445514","https://openalex.org/W2029566311","https://openalex.org/W2047656763","https://openalex.org/W2049890071","https://openalex.org/W2050129046","https://openalex.org/W2059696856","https://openalex.org/W2066349733","https://openalex.org/W2072213119","https://openalex.org/W2073061372","https://openalex.org/W2110955718","https://openalex.org/W2115089829","https://openalex.org/W2119691711","https://openalex.org/W2122410182","https://openalex.org/W2124438843","https://openalex.org/W2135144788","https://openalex.org/W2135653967","https://openalex.org/W2136952590","https://openalex.org/W2149190906","https://openalex.org/W2149381887","https://openalex.org/W2159560337","https://openalex.org/W2164326463","https://openalex.org/W2165208458","https://openalex.org/W2168519934","https://openalex.org/W2169336925","https://openalex.org/W2623293810","https://openalex.org/W2654061676","https://openalex.org/W2913602891","https://openalex.org/W3136479147","https://openalex.org/W3141428680","https://openalex.org/W3145241477","https://openalex.org/W4249456511","https://openalex.org/W4285719527","https://openalex.org/W6633417046","https://openalex.org/W6678552091","https://openalex.org/W6680007323"],"related_works":["https://openalex.org/W2144573411","https://openalex.org/W3133921371","https://openalex.org/W205041506","https://openalex.org/W36170654","https://openalex.org/W2122702529","https://openalex.org/W2544527082","https://openalex.org/W2170392063","https://openalex.org/W2955750014","https://openalex.org/W2963673899","https://openalex.org/W1510302770"],"abstract_inverted_index":{"The":[0],"performance":[1],"bottleneck":[2],"for":[3,20,52,76,147,158,165],"many":[4,127],"scientific":[5],"applications":[6,64],"is":[7,23,122],"the":[8,29,38,97,101,112],"cost":[9],"of":[10,31,69,91,103,109,115,150,171,180],"memory":[11,21,77,159],"access":[12],"inside":[13],"linear":[14,152],"algebra":[15,153],"kernels.":[16],"Tuning":[17],"such":[18,36],"kernels":[19,167],"efficiency":[22],"a":[24,49,67,119,140],"complex":[25],"task":[26],"that":[27,106,144],"reduces":[28],"productivity":[30],"computational":[32],"scientists.":[33],"Software":[34],"libraries":[35],"as":[37],"Basic":[39],"Linear":[40],"Algebra":[41],"Subprograms":[42],"(BLAS)":[43],"ameliorate":[44],"this":[45,133],"problem":[46],"by":[47],"providing":[48],"standard":[50],"interface":[51],"which":[53,72],"computer":[54],"scientists":[55],"and":[56,155,168,184,190],"hardware":[57],"vendors":[58],"have":[59],"created":[60],"highly-tuned":[61],"implementations.":[62],"Scientific":[63],"often":[65],"require":[66],"sequence":[68,114],"BLAS":[70,81,102,186],"operations,":[71],"presents":[73],"further":[74],"opportunities":[75],"optimization.":[78],"However,":[79],"because":[80],"are":[82,130],"tuned":[83],"in":[84,118],"isolation":[85],"they":[86],"do":[87],"not":[88],"take":[89],"advantage":[90],"these":[92],"opportunities.":[93],"This":[94],"phenomenon":[95],"motivated":[96],"recent":[98],"addition":[99],"to":[100,174,178,182],"several":[104],"routines":[105,129],"perform":[107],"sequences":[108,149,179],"operations.":[110],"Unfortunately,":[111],"exact":[113],"operations":[116,154],"needed":[117],"given":[120],"situation":[121],"highly":[123],"application":[124],"dependent,":[125],"so":[126],"more":[128],"needed.":[131],"In":[132],"paper":[134],"we":[135],"present":[136],"preliminary":[137],"work":[138],"on":[139,187],"domain-":[141],"specific":[142],"compiler":[143],"generates":[145],"implementations":[146],"arbitrary":[148],"basic":[151],"tunes":[156],"them":[157],"efficiency.":[160],"We":[161],"report":[162],"experimental":[163],"results":[164],"dense":[166],"show":[169],"speedups":[170],"25":[172],"%":[173,176],"120":[175],"relative":[177],"calls":[181],"GotoBLAS":[183],"vendor-tuned":[185],"Intel":[188],"Xeon":[189],"IBM":[191],"PowerPC":[192],"platforms.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
