{"id":"https://openalex.org/W4414638839","doi":"https://doi.org/10.1007/978-3-031-97196-9_13","title":"Toward Portable GPU Performance: Julia Recursive Implementation of\u00a0TRMM and\u00a0TRSM","display_name":"Toward Portable GPU Performance: Julia Recursive Implementation of\u00a0TRMM and\u00a0TRSM","publication_year":2025,"publication_date":"2025-09-30","ids":{"openalex":"https://openalex.org/W4414638839","doi":"https://doi.org/10.1007/978-3-031-97196-9_13"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-97196-9_13","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-97196-9_13","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/978-3-031-97196-9_13","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119772411","display_name":"Vicki Carric","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vicki Carric","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119772412","display_name":"Maxwell Onyango","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maxwell Onyango","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013947843","display_name":"Rabab Alomairy","orcid":"https://orcid.org/0000-0001-9911-6094"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rabab Alomairy","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119772413","display_name":"Evelyne Ringoot","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Evelyne Ringoot","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042757147","display_name":"James Schloss","orcid":"https://orcid.org/0000-0002-3243-8918"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Schloss","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029673947","display_name":"Alan Edelman","orcid":"https://orcid.org/0000-0001-7676-3133"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alan Edelman","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5013947843"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24767442,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"154","last_page":"164"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11405","display_name":"Geophysics and Gravity Measurements","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/1910","display_name":"Oceanography"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11405","display_name":"Geophysics and Gravity Measurements","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/1910","display_name":"Oceanography"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11325","display_name":"Inertial Sensor and Navigation","score":0.9811000227928162,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11312","display_name":"Soil Moisture and Remote Sensing","score":0.9679999947547913,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.6930000185966492},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.6417999863624573},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.4738999903202057},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.40880000591278076},{"id":"https://openalex.org/keywords/assembly-language","display_name":"Assembly language","score":0.3837999999523163},{"id":"https://openalex.org/keywords/metaprogramming","display_name":"Metaprogramming","score":0.37619999051094055},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.3546999990940094}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8988999724388123},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6930000185966492},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.6417999863624573},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5527999997138977},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.4738999903202057},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.40880000591278076},{"id":"https://openalex.org/C50831359","wikidata":"https://www.wikidata.org/wiki/Q165436","display_name":"Assembly language","level":3,"score":0.3837999999523163},{"id":"https://openalex.org/C35390924","wikidata":"https://www.wikidata.org/wiki/Q661075","display_name":"Metaprogramming","level":2,"score":0.37619999051094055},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.3546999990940094},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.32670000195503235},{"id":"https://openalex.org/C104528550","wikidata":"https://www.wikidata.org/wiki/Q506265","display_name":"Triangular matrix","level":3,"score":0.32089999318122864},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.3197999894618988},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.30149999260902405},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.27160000801086426},{"id":"https://openalex.org/C128099668","wikidata":"https://www.wikidata.org/wiki/Q573952","display_name":"Lazy evaluation","level":3,"score":0.26899999380111694},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26350000500679016},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C2982832238","wikidata":"https://www.wikidata.org/wiki/Q5531640","display_name":"General purpose","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25780001282691956}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-97196-9_13","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-97196-9_13","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.1007/978-3-031-97196-9_13","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-97196-9_13","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2149381887","https://openalex.org/W2549815592","https://openalex.org/W2622509770","https://openalex.org/W2766943539","https://openalex.org/W2774096293","https://openalex.org/W4285011296","https://openalex.org/W4390657933","https://openalex.org/W4402936386","https://openalex.org/W4409133358","https://openalex.org/W6930982475"],"related_works":[],"abstract_inverted_index":{"This":[0,33],"paper":[1],"presents":[2],"a":[3,98,143],"performant":[4,89],"and":[5,14,44,65,78,85,129],"portable":[6],"recursive":[7,40,113],"implementation":[8,41,71,102,115],"of":[9,27,60,147,152],"triangular":[10,15],"matrix-matrix":[11,53],"multiplication":[12,54],"(TRMM)":[13],"solve":[16],"(TRSM)":[17],"operations":[18,49],"in":[19,72],"Julia":[20,73],"for":[21,42,125,133],"GPUs,":[22],"which":[23,46],"form":[24],"the":[25,48,61,75,82,134,150],"backbone":[26],"many":[28],"other":[29],"linear":[30],"algebra":[31],"algorithms.":[32],"work":[34],"is":[35],"based":[36],"on":[37],"an":[38],"existing":[39,83],"TRMM":[43],"TRSM,":[45],"restructures":[47],"to":[50,105,121,137],"include":[51],"general":[52],"(GEMM)":[55],"calls,":[56],"facilitating":[57],"better":[58],"utilization":[59],"GPU":[62,94,110],"memory":[63],"hierarchy,":[64],"reducing":[66],"latency":[67],"overhead.":[68],"The":[69,112],"unified":[70,153],"harnesses":[74],"language\u2019s":[76],"multiple-dispatch":[77],"metaprogramming":[79],"capabilities":[80],"through":[81],"GPUArrays":[84],"KernelAbstractions":[86],"frameworks,":[87],"enabling":[88],"hardware-agnostic":[90,114],"execution":[91],"across":[92],"different":[93,109],"architectures.":[95],"By":[96],"supporting":[97],"consistent":[99],"API,":[100],"this":[101],"allows":[103],"users":[104],"seamlessly":[106],"switch":[107],"between":[108],"backends.":[111],"we":[116],"present":[117],"achieves":[118],"performance":[119],"comparable":[120],"vendor-optimized":[122],"(cuBLAS/rocBLAS)":[123],"libraries":[124],"larger":[126],"matrix":[127],"sizes":[128],"provides":[130],"such":[131],"methods":[132],"first":[135],"time":[136],"Apple":[138],"Silicion":[139],"hardware":[140],"with":[141],"only":[142],"few":[144],"hundred":[145],"lines":[146],"code,":[148],"demonstrating":[149],"power":[151],"implementations.":[154]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
