{"id":"https://openalex.org/W2131224891","doi":"https://doi.org/10.1109/date.2011.5763119","title":"Gemma in April: A matrix-like parallel programming architecture on OpenCL","display_name":"Gemma in April: A matrix-like parallel programming architecture on OpenCL","publication_year":2011,"publication_date":"2011-03-01","ids":{"openalex":"https://openalex.org/W2131224891","doi":"https://doi.org/10.1109/date.2011.5763119","mag":"2131224891"},"language":"en","primary_location":{"id":"doi:10.1109/date.2011.5763119","is_oa":false,"landing_page_url":"https://doi.org/10.1109/date.2011.5763119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 Design, Automation &amp; Test in Europe","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/A5056404134","display_name":"Tianji Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tianji Wu","raw_affiliation_strings":["Department of Electrical Engineering, UCLA, USA","Department of Electronic Engineering, TNList, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, UCLA, USA","institution_ids":[]},{"raw_affiliation_string":"Department of Electronic Engineering, TNList, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100735704","display_name":"Di Wu","orcid":"https://orcid.org/0000-0002-9433-7725"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Di Wu","raw_affiliation_strings":["Department of Electronic Engineering, TNList, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, TNList, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100445061","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0001-6108-5157"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Wang","raw_affiliation_strings":["Department of Electronic Engineering, TNList, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, TNList, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100739262","display_name":"Xiaorui Zhang","orcid":"https://orcid.org/0000-0002-7571-2593"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaorui Zhang","raw_affiliation_strings":["Department of Electronic Engineering, TNList, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, TNList, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102971553","display_name":"Hong Luo","orcid":"https://orcid.org/0000-0003-2375-7826"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Luo","raw_affiliation_strings":["Department of Electronic Engineering, TNList, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, TNList, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100833305","display_name":"Ningyi Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ningyi Xu","raw_affiliation_strings":["Hardware Computing Group, Microsoft Research Asia"],"affiliations":[{"raw_affiliation_string":"Hardware Computing Group, Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023755254","display_name":"Huazhong Yang","orcid":"https://orcid.org/0000-0003-2421-353X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huazhong Yang","raw_affiliation_strings":["Department of Electronic Engineering, TNList, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, TNList, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5056404134"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.2519,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58213229,"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":"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":0.9995999932289124,"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":0.9995999932289124,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9987999796867371,"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":0.8932359218597412},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7271026372909546},{"id":"https://openalex.org/keywords/gemma","display_name":"Gemma","score":0.7100975513458252},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6288882493972778},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5077468156814575},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.4993138313293457},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.4813309609889984},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.47717753052711487},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.44983822107315063},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4419270157814026},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.42242181301116943},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.41917121410369873},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.39631161093711853},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.35441237688064575},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.34484732151031494},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3071410357952118}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8932359218597412},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7271026372909546},{"id":"https://openalex.org/C170806853","wikidata":"https://www.wikidata.org/wiki/Q2746099","display_name":"Gemma","level":2,"score":0.7100975513458252},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6288882493972778},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5077468156814575},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.4993138313293457},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.4813309609889984},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.47717753052711487},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.44983822107315063},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4419270157814026},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.42242181301116943},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.41917121410369873},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.39631161093711853},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.35441237688064575},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.34484732151031494},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3071410357952118},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/date.2011.5763119","is_oa":false,"landing_page_url":"https://doi.org/10.1109/date.2011.5763119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 Design, Automation &amp; Test in Europe","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/W1264773896","https://openalex.org/W1522512418","https://openalex.org/W2100830825","https://openalex.org/W2127766448","https://openalex.org/W2129817042","https://openalex.org/W2141389982","https://openalex.org/W2163229756","https://openalex.org/W2173213060","https://openalex.org/W4230094279","https://openalex.org/W6628139786"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825","https://openalex.org/W2893308117"],"abstract_inverted_index":{"Nowadays,":[0],"Graphics":[1],"Processing":[2],"Unit":[3],"(GPU),":[4],"as":[5,126],"a":[6,31,46,54,61,85],"kind":[7],"of":[8,79],"massive":[9],"parallel":[10,48,55,81,108],"processor,":[11],"has":[12],"been":[13,24],"widely":[14],"used":[15],"in":[16,95],"general":[17],"purposed":[18],"computing":[19,49],"tasks.":[20],"Although":[21],"there":[22],"have":[23],"mature":[25],"development":[26],"tools,":[27],"it":[28],"is":[29,67,84],"not":[30],"trivial":[32],"task":[33],"for":[34],"programmers":[35],"to":[36,75],"write":[37],"GPU":[38],"programs.":[39],"Based":[40],"on":[41,69,122],"this":[42],"consideration,":[43],"we":[44],"propose":[45],"novel":[47],"architecture.":[50],"The":[51],"architecture":[52],"includes":[53],"programming":[56,62],"model,":[57],"named":[58,64],"Gemma,":[59],"and":[60,73,91,110,113,129],"framework,":[63],"April.":[65],"Gemma":[66,96,119],"based":[68,121],"generalized":[70],"matrix":[71],"operations,":[72],"helps":[74],"alleviate":[76],"the":[77,106,142],"difficulty":[78],"describing":[80],"algorithms.":[82],"April":[83,101,139],"high-level":[86],"framework":[87],"that":[88,135],"can":[89,102],"compile":[90],"execute":[92],"tasks":[93,120],"described":[94],"with":[97,136,147],"OpenCL.":[98,148],"In":[99],"particular,":[100],"automatically":[103],"1)":[104],"choose":[105],"best":[107],"algorithm":[109],"mapping":[111],"scheme,":[112],"generate":[114],"OpenCL":[115],"kernels,":[116],"2)":[117],"schedule":[118],"execution":[123],"costs":[124],"such":[125],"data":[127],"storing":[128],"transferring.":[130],"Our":[131],"experimental":[132],"results":[133],"show":[134],"competitive":[137],"performance,":[138],"considerably":[140],"reduces":[141],"programs'":[143],"code":[144],"length":[145],"compared":[146]},"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
