{"id":"https://openalex.org/W4280495398","doi":"https://doi.org/10.1145/3530390.3532733","title":"Systematically extending a high-level code generator with support for tensor cores","display_name":"Systematically extending a high-level code generator with support for tensor cores","publication_year":2022,"publication_date":"2022-04-03","ids":{"openalex":"https://openalex.org/W4280495398","doi":"https://doi.org/10.1145/3530390.3532733"},"language":"en","primary_location":{"id":"doi:10.1145/3530390.3532733","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3530390.3532733","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th Workshop on General Purpose Processing Using GPU","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/A5073189266","display_name":"Lukas Siefke","orcid":null},"institutions":[{"id":"https://openalex.org/I22465464","display_name":"University of M\u00fcnster","ror":"https://ror.org/00pd74e08","country_code":"DE","type":"education","lineage":["https://openalex.org/I22465464"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Lukas Siefke","raw_affiliation_strings":["University of M\u00fcnster, M\u00fcnster, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of M\u00fcnster, M\u00fcnster, Germany","institution_ids":["https://openalex.org/I22465464"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022923674","display_name":"Bastian K\u00f6pcke","orcid":"https://orcid.org/0000-0001-5271-6893"},"institutions":[{"id":"https://openalex.org/I22465464","display_name":"University of M\u00fcnster","ror":"https://ror.org/00pd74e08","country_code":"DE","type":"education","lineage":["https://openalex.org/I22465464"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bastian K\u00f6pcke","raw_affiliation_strings":["University of M\u00fcnster, M\u00fcnster, Germany"],"raw_orcid":"https://orcid.org/0000-0001-5271-6893","affiliations":[{"raw_affiliation_string":"University of M\u00fcnster, M\u00fcnster, Germany","institution_ids":["https://openalex.org/I22465464"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061421539","display_name":"Sergei Gorlatch","orcid":"https://orcid.org/0000-0003-3857-9380"},"institutions":[{"id":"https://openalex.org/I22465464","display_name":"University of M\u00fcnster","ror":"https://ror.org/00pd74e08","country_code":"DE","type":"education","lineage":["https://openalex.org/I22465464"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sergei Gorlatch","raw_affiliation_strings":["University of M\u00fcnster, M\u00fcnster, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of M\u00fcnster, M\u00fcnster, Germany","institution_ids":["https://openalex.org/I22465464"]}]},{"author_position":"last","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":["The University of Edinburgh, Edinburgh, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0001-5048-0741","affiliations":[{"raw_affiliation_string":"The University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5073189266"],"corresponding_institution_ids":["https://openalex.org/I22465464"],"apc_list":null,"apc_paid":null,"fwci":0.4669,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.58263054,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9922999739646912,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9918000102043152,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.7649980783462524},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.6733607649803162},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6465334296226501},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.6412264704704285},{"id":"https://openalex.org/keywords/lift","display_name":"Lift (data mining)","score":0.6093353033065796},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5418520569801331},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4797191023826599},{"id":"https://openalex.org/keywords/proposition","display_name":"Proposition","score":0.4787178039550781},{"id":"https://openalex.org/keywords/domain-specific-language","display_name":"Domain-specific language","score":0.4448367953300476},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4315229058265686},{"id":"https://openalex.org/keywords/unreachable-code","display_name":"Unreachable code","score":0.42640790343284607},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.42615601420402527},{"id":"https://openalex.org/keywords/redundant-code","display_name":"Redundant code","score":0.280089795589447},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.15967035293579102}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7649980783462524},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.6733607649803162},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6465334296226501},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.6412264704704285},{"id":"https://openalex.org/C139002025","wikidata":"https://www.wikidata.org/wiki/Q3001212","display_name":"Lift (data mining)","level":2,"score":0.6093353033065796},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5418520569801331},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4797191023826599},{"id":"https://openalex.org/C2777152325","wikidata":"https://www.wikidata.org/wiki/Q108163","display_name":"Proposition","level":2,"score":0.4787178039550781},{"id":"https://openalex.org/C135257023","wikidata":"https://www.wikidata.org/wiki/Q691358","display_name":"Domain-specific language","level":2,"score":0.4448367953300476},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4315229058265686},{"id":"https://openalex.org/C50951305","wikidata":"https://www.wikidata.org/wiki/Q2482534","display_name":"Unreachable code","level":5,"score":0.42640790343284607},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.42615601420402527},{"id":"https://openalex.org/C151578736","wikidata":"https://www.wikidata.org/wiki/Q1251793","display_name":"Redundant code","level":4,"score":0.280089795589447},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15967035293579102},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"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/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","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":1,"locations":[{"id":"doi:10.1145/3530390.3532733","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3530390.3532733","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th Workshop on General Purpose Processing Using GPU","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1997978901","https://openalex.org/W2104958979","https://openalex.org/W2780077279","https://openalex.org/W2901549770","https://openalex.org/W3044913359","https://openalex.org/W3048586522","https://openalex.org/W3104528661","https://openalex.org/W3139246295","https://openalex.org/W3195241200","https://openalex.org/W4206336135"],"related_works":["https://openalex.org/W116913286","https://openalex.org/W2127497159","https://openalex.org/W632311702","https://openalex.org/W2123574549","https://openalex.org/W4253804737","https://openalex.org/W2794657471","https://openalex.org/W2563645043","https://openalex.org/W2369241479","https://openalex.org/W1493727516","https://openalex.org/W1777501891"],"abstract_inverted_index":{"High-level":[0],"code":[1,23,63,68],"generators":[2,64],"like":[3],"Halide,":[4],"Lift,":[5],"and":[6,19,42,58],"RISE":[7,59],"make":[8],"a":[9,15,36,49],"compelling":[10],"proposition:":[11],"write":[12],"programs":[13],"in":[14,45],"simple":[16],"high-level":[17,62],"language":[18,34],"get":[20],"high-performing":[21],"GPU":[22],"\"for":[24],"free\".":[25],"They":[26],"achieve":[27],"this":[28],"feat":[29],"by":[30],"restricting":[31],"the":[32,73],"input":[33],"to":[35,48],"specific":[37],"domain":[38],"(such":[39],"as":[40,72],"image":[41],"array":[43],"processing":[44],"Halide)":[46],"or":[47],"fixed":[50],"set":[51],"of":[52],"flexible":[53],"parallel":[54],"patterns":[55],"(as":[56],"Lift":[57],"do).":[60],"Implementing":[61],"that":[65],"produce":[66],"high-performance":[67],"is":[69],"challenging,":[70],"specifically":[71],"target":[74],"hardware":[75],"constantly":[76],"evolves.":[77]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
