{"id":"https://openalex.org/W2397307691","doi":"https://doi.org/10.3233/978-1-61499-041-3-405","title":"Improving Performance of Triangular Matrix-Vector BLAS Routines on GPUs","display_name":"Improving Performance of Triangular Matrix-Vector BLAS Routines on GPUs","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W2397307691","doi":"https://doi.org/10.3233/978-1-61499-041-3-405","mag":"2397307691"},"language":"en","primary_location":{"id":"doi:10.3233/978-1-61499-041-3-405","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-041-3-405","pdf_url":null,"source":{"id":"https://openalex.org/S4210175178","display_name":"Advances in parallel computing","issn_l":"0927-5452","issn":["0927-5452","1879-808X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Parallel Computing","raw_type":"book-chapter"},"type":"book-chapter","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/A5085384704","display_name":"Marek Karwacki","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Karwacki Marek","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5052271359","display_name":"Przemys\u0142aw Stpiczy\u0144ski","orcid":"https://orcid.org/0000-0001-8661-414X"},"institutions":[{"id":"https://openalex.org/I99542240","display_name":"Polish Academy of Sciences","ror":"https://ror.org/01dr6c206","country_code":"PL","type":"funder","lineage":["https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Stpiczyński Przemysław","raw_affiliation_strings":["Polish Academy of Sciences, Warsaw, Poland"],"affiliations":[{"raw_affiliation_string":"Polish Academy of Sciences, Warsaw, Poland","institution_ids":["https://openalex.org/I99542240"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5085384704"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.30687628,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9843999743461609,"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"}},"topics":[{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9843999743461609,"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/T10080","display_name":"Energy Efficient Wireless Sensor Networks","score":0.9394999742507935,"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/parallel-computing","display_name":"Parallel computing","score":0.5686981678009033},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5578060150146484},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4551924467086792},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4475923478603363},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.1345384120941162},{"id":"https://openalex.org/keywords/composite-material","display_name":"Composite material","score":0.04009336233139038}],"concepts":[{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5686981678009033},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5578060150146484},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4551924467086792},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4475923478603363},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.1345384120941162},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.04009336233139038}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/978-1-61499-041-3-405","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-041-3-405","pdf_url":null,"source":{"id":"https://openalex.org/S4210175178","display_name":"Advances in parallel computing","issn_l":"0927-5452","issn":["0927-5452","1879-808X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Parallel Computing","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"CUBLAS":[0,100],"is":[1,24],"a":[2],"widely":[3],"used":[4],"implementation":[5],"of":[6,21,30,64,72],"BLAS":[7,35],"(Basic":[8],"Linear":[9],"Algebra":[10],"Subprograms)":[11],"for":[12,37,50],"NVIDIA":[13],"CUDA":[14],"Graphical":[15],"Processing":[16],"Units":[17],"(GPUs).":[18],"The":[19,70],"aim":[20],"this":[22],"paper":[23],"to":[25,93],"show":[26,86],"that":[27,87],"the":[28,31,65],"performance":[29],"selected":[32],"Level":[33],"2":[34],"routines":[36,66,98],"working":[38],"with":[39],"triangular":[40],"matrices":[41],"can":[42],"be":[43],"improved":[44],"using":[45,53],"some":[46],"optimization":[47],"techniques":[48],"suitable":[49],"GPUs":[51],"like":[52],"shared":[54],"memory":[55,58],"and":[56,68,82],"coalesced":[57],"access.":[59],"We":[60],"present":[61],"new":[62,89],"implementations":[63,90],"xTRMV":[67],"xTRSV.":[69],"results":[71],"experiments":[73],"carried":[74],"out":[75],"on":[76],"two":[77],"GPU":[78],"architectures:":[79],"Tesla":[80],"M2050":[81],"GeForce":[83],"GTX":[84],"260":[85],"these":[88],"are":[91],"up":[92],"500%":[94],"faster":[95],"than":[96],"corresponding":[97],"from":[99],"Library.":[101]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2016-06-24T00:00:00"}