{"id":"https://openalex.org/W2484342675","doi":"https://doi.org/10.1145/2968455.2968521","title":"Matrix multiplication beyond auto-tuning","display_name":"Matrix multiplication beyond auto-tuning","publication_year":2016,"publication_date":"2016-10-01","ids":{"openalex":"https://openalex.org/W2484342675","doi":"https://doi.org/10.1145/2968455.2968521","mag":"2484342675"},"language":"en","primary_location":{"id":"doi:10.1145/2968455.2968521","doi":"https://doi.org/10.1145/2968455.2968521","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2968455.2968521","pdf_url":null,"source":{"id":"https://openalex.org/S7407087172","display_name":"International Conference on Compilers, Architectures and Synthesis for Embedded Systems (CASES)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Compilers, Architectures and Synthesis for Embedded Systems","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/files/26647284/cases2016.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016319844","display_name":"Michel Steuwer","orcid":"https://orcid.org/0000-0001-5048-0741","observed_orcids":["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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050554632","display_name":"Toomas Remmelg","orcid":null,"observed_orcids":[]},"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":"Toomas Remmelg","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":null,"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","observed_orcids":["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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":2.832,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":{"value":0.91612647,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9984999895095825,"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":0.9984999895095825,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.00039999998989515007,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"matrix multiplication","score":0.9990000128746033},{"id":"https://openalex.org/keywords/gpu-computing","display_name":"GPU computing","score":0.6259999871253967},{"id":"https://openalex.org/keywords/auto-tuning","display_name":"auto-tuning","score":0.8420000076293945},{"id":"https://openalex.org/keywords/mobile-gpus","display_name":"mobile GPUs","score":0.7950000166893005},{"id":"https://openalex.org/keywords/opencl","display_name":"OpenCL","score":0.9679999947547913},{"id":"https://openalex.org/keywords/parallel-speedup","display_name":"parallel speedup","score":0.5720000267028809},{"id":"https://openalex.org/keywords/kernel-optimization","display_name":"kernel optimization","score":0.32499998807907104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8349979519844055},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.6812309622764587},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6434633731842041},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5516213774681091},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.525833010673523},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.49921345710754395},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.4377998113632202},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4356227219104767},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.42542898654937744},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4002689719200134},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.38865792751312256},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3333050608634949},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.20819276571273804},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2968455.2968521","doi":"https://doi.org/10.1145/2968455.2968521","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2968455.2968521","pdf_url":null,"source":{"id":"https://openalex.org/S7407087172","display_name":"International Conference on Compilers, Architectures and Synthesis for Embedded Systems (CASES)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Compilers, Architectures and Synthesis for Embedded Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.gla.ac.uk:146599","doi":null,"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,"listed_in":["doaj"],"host_organization":"https://openalex.org/I4405259220","host_organization_name":"Institut Agama Islam Negeri Langsa","host_organization_lineage":["https://openalex.org/I4405259220"],"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":"Conference Proceedings"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/879942f3-5118-402f-9f2e-df13b8210ded","doi":null,"is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/879942f3-5118-402f-9f2e-df13b8210ded","pdf_url":"https://www.research.ed.ac.uk/files/26647284/cases2016.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Steuwer, M, Remmelg, T & Dubach, C 2016, Matrix Multiplication Beyond Auto-Tuning: Rewrite-based GPU Code Generation. in CASES '16 Proceedings of the International Conference on Compilers, Architectures and Synthesis for Embedded Systems., 15, Proceedings of the International Conference on Compilers, Architectures and Synthesis for Embedded Systems, Pittsburgh, Pennsylvania, United States, 2/10/16. https://doi.org/10.1145/2968455.2968521","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/879942f3-5118-402f-9f2e-df13b8210ded","doi":null,"is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/879942f3-5118-402f-9f2e-df13b8210ded","pdf_url":"https://www.research.ed.ac.uk/files/26647284/cases2016.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Steuwer, M, Remmelg, T & Dubach, C 2016, Matrix Multiplication Beyond Auto-Tuning: Rewrite-based GPU Code Generation. in CASES '16 Proceedings of the International Conference on Compilers, Architectures and Synthesis for Embedded Systems., 15, Proceedings of the International Conference on Compilers, Architectures and Synthesis for Embedded Systems, Pittsburgh, Pennsylvania, United States, 2/10/16. https://doi.org/10.1145/2968455.2968521","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.550000011920929,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2484342675.pdf","grobid_xml":"https://content.openalex.org/works/W2484342675.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W36826159","https://openalex.org/W1894701209","https://openalex.org/W1972209410","https://openalex.org/W1978642402","https://openalex.org/W1997978901","https://openalex.org/W2033485113","https://openalex.org/W2037089143","https://openalex.org/W2055312318","https://openalex.org/W2059745360","https://openalex.org/W2061313045","https://openalex.org/W2062368747","https://openalex.org/W2065887019","https://openalex.org/W2083310717","https://openalex.org/W2093843662","https://openalex.org/W2100218206","https://openalex.org/W2107096626","https://openalex.org/W2115148068","https://openalex.org/W2135653967","https://openalex.org/W2142805836","https://openalex.org/W2147654959","https://openalex.org/W2157089785","https://openalex.org/W2253627208","https://openalex.org/W2258220747","https://openalex.org/W2270866986","https://openalex.org/W2294854295","https://openalex.org/W2482658148","https://openalex.org/W2548341626","https://openalex.org/W3100760381","https://openalex.org/W3103983137","https://openalex.org/W3149591378","https://openalex.org/W4234688306","https://openalex.org/W4243796884","https://openalex.org/W4246447814","https://openalex.org/W4300937065"],"related_works":["https://openalex.org/W3099313426","https://openalex.org/W4287593139","https://openalex.org/W2151046618","https://openalex.org/W1972148443","https://openalex.org/W752783541","https://openalex.org/W1506547947","https://openalex.org/W1969233021","https://openalex.org/W2167646277","https://openalex.org/W2027443981","https://openalex.org/W2388314963"],"abstract_inverted_index":{"Graphics":[0],"Processing":[1],"Units":[2],"(GPUs)":[3],"are":[4,18,27],"used":[5],"as":[6,37],"general":[7],"purpose":[8],"parallel":[9],"accelerators":[10],"in":[11,20],"a":[12],"wide":[13],"range":[14],"of":[15,33,48],"applications.":[16],"They":[17],"found":[19],"most":[21],"computing":[22],"systems,":[23],"and":[24],"mobile":[25,40],"devices":[26],"no":[28],"exception.":[29],"The":[30],"recent":[31],"availability":[32],"programming":[34],"APIs":[35],"such":[36],"OpenCL":[38],"for":[39],"GPUs":[41],"promises":[42],"to":[43],"open":[44],"up":[45],"new":[46],"types":[47],"applications":[49],"on":[50],"these":[51],"devices.":[52]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2}],"updated_date":"2026-10-07T09:51:55.459714","created_date":"2025-10-10T00:00:00"}
