{"id":"https://openalex.org/W2258220747","doi":"https://doi.org/10.1145/2884045.2884046","title":"Performance portable GPU code generation for matrix multiplication","display_name":"Performance portable GPU code generation for matrix multiplication","publication_year":2016,"publication_date":"2016-03-04","ids":{"openalex":"https://openalex.org/W2258220747","doi":"https://doi.org/10.1145/2884045.2884046","mag":"2258220747"},"language":"en","primary_location":{"id":"doi:10.1145/2884045.2884046","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2884045.2884046","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th Annual Workshop on General Purpose Processing using Graphics Processing Unit","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/A5050554632","display_name":"Toomas Remmelg","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Toomas Remmelg","raw_affiliation_strings":["University of Edinburgh"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000511414","display_name":"Thibaut Lutz","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Thibaut Lutz","raw_affiliation_strings":["University of Edinburgh"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016319844","display_name":"Michel Steuwer","orcid":"https://orcid.org/0000-0001-5048-0741"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Michel Steuwer","raw_affiliation_strings":["University of Edinburgh"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050229154","display_name":"Christophe Dubach","orcid":"https://orcid.org/0000-0003-4811-2469"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Christophe Dubach","raw_affiliation_strings":["University of Edinburgh"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5050554632"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":4.0994,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.93765281,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"22","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/T10829","display_name":"Interconnection Networks and Systems","score":0.9986000061035156,"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":0.996999979019165,"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/computer-science","display_name":"Computer science","score":0.8778209686279297},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.7872625589370728},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7061710357666016},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6098359823226929},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.6073589324951172},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.585404634475708},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.5739811062812805},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5711341500282288},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4392140805721283},{"id":"https://openalex.org/keywords/double-precision-floating-point-format","display_name":"Double-precision floating-point format","score":0.4141843616962433},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3996517062187195},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.18891483545303345},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.10038197040557861}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8778209686279297},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7872625589370728},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7061710357666016},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6098359823226929},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.6073589324951172},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.585404634475708},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5739811062812805},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5711341500282288},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4392140805721283},{"id":"https://openalex.org/C35912277","wikidata":"https://www.wikidata.org/wiki/Q1243369","display_name":"Double-precision floating-point format","level":3,"score":0.4141843616962433},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3996517062187195},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.18891483545303345},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.10038197040557861},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"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/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"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":3,"locations":[{"id":"doi:10.1145/2884045.2884046","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2884045.2884046","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th Annual Workshop on General Purpose Processing using Graphics Processing Unit","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.gla.ac.uk:146600","is_oa":false,"landing_page_url":"http://eprints.gla.ac.uk/view/author/39312.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":false,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:pure.ed.ac.uk:publications/4b694fde-2787-4517-b304-5311e4046a48","is_oa":false,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/4b694fde-2787-4517-b304-5311e4046a48","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1782174992","https://openalex.org/W1906046253","https://openalex.org/W1978642402","https://openalex.org/W1997978901","https://openalex.org/W2000873501","https://openalex.org/W2004711550","https://openalex.org/W2026188397","https://openalex.org/W2033485113","https://openalex.org/W2059745360","https://openalex.org/W2061313045","https://openalex.org/W2065887019","https://openalex.org/W2077143534","https://openalex.org/W2083310717","https://openalex.org/W2093843662","https://openalex.org/W2107096626","https://openalex.org/W2115148068","https://openalex.org/W2143609451","https://openalex.org/W2145663636","https://openalex.org/W2147654959","https://openalex.org/W2294854295","https://openalex.org/W4252223645","https://openalex.org/W4300937065"],"related_works":["https://openalex.org/W650988184","https://openalex.org/W2162410319","https://openalex.org/W2137356287","https://openalex.org/W4321184925","https://openalex.org/W2255990315","https://openalex.org/W1975364444","https://openalex.org/W60915090","https://openalex.org/W2025840053","https://openalex.org/W2161692994","https://openalex.org/W4302308373"],"abstract_inverted_index":{"Parallel":[0],"accelerators":[1],"such":[2],"as":[3],"GPUs":[4],"are":[5],"notoriously":[6],"hard":[7],"to":[8,33,35,49,59],"program;":[9],"exploiting":[10],"their":[11],"full":[12],"performance":[13,52],"potential":[14],"is":[15],"a":[16],"job":[17],"best":[18],"left":[19],"for":[20,62],"ninja":[21],"programmers.":[22],"High-level":[23],"programming":[24],"languages":[25],"coupled":[26],"with":[27],"optimizing":[28],"compilers":[29],"have":[30],"been":[31],"proposed":[32],"attempt":[34],"address":[36],"this":[37],"issue.":[38],"However,":[39],"they":[40],"rely":[41],"on":[42],"device-specific":[43],"heuristics":[44],"or":[45],"hard-coded":[46],"library":[47],"implementations":[48],"achieve":[50],"good":[51],"resulting":[53],"in":[54],"non-portable":[55],"solutions":[56],"that":[57],"need":[58],"be":[60],"re-optimized":[61],"every":[63],"new":[64],"device.":[65]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
