{"id":"https://openalex.org/W2799595460","doi":"https://doi.org/10.1145/3204919.3207894","title":"ViennaCL++","display_name":"ViennaCL++","publication_year":2018,"publication_date":"2018-05-02","ids":{"openalex":"https://openalex.org/W2799595460","doi":"https://doi.org/10.1145/3204919.3207894","mag":"2799595460"},"language":"en","primary_location":{"id":"doi:10.1145/3204919.3207894","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3204919.3207894","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Workshop on OpenCL","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/A5102800860","display_name":"Tai-Liang Chen","orcid":"https://orcid.org/0000-0002-3347-8161"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tai-Liang Chen","raw_affiliation_strings":["Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045730926","display_name":"Shih-Huan Chien","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shih-Huan Chien","raw_affiliation_strings":["Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038803698","display_name":"Jenq\u2010Kuen Lee","orcid":"https://orcid.org/0000-0001-9919-6258"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jenq-Kuen Lee","raw_affiliation_strings":["Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1877,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.7876096,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9976000189781189,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9951000213623047,"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/computer-science","display_name":"Computer science","score":0.887742280960083},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.7286257147789001},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6951885223388672},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6213701963424683},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6054803729057312},{"id":"https://openalex.org/keywords/x86","display_name":"x86","score":0.6006713509559631},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4742128849029541},{"id":"https://openalex.org/keywords/control-flow","display_name":"Control flow","score":0.4267944395542145},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.31617194414138794}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.887742280960083},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7286257147789001},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6951885223388672},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6213701963424683},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6054803729057312},{"id":"https://openalex.org/C170723468","wikidata":"https://www.wikidata.org/wiki/Q182933","display_name":"x86","level":3,"score":0.6006713509559631},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4742128849029541},{"id":"https://openalex.org/C160191386","wikidata":"https://www.wikidata.org/wiki/Q868299","display_name":"Control flow","level":2,"score":0.4267944395542145},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.31617194414138794},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3204919.3207894","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3204919.3207894","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Workshop on OpenCL","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":4,"referenced_works":["https://openalex.org/W2524541844","https://openalex.org/W2544527082","https://openalex.org/W2751520368","https://openalex.org/W2767882261"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2027972911","https://openalex.org/W2157978810","https://openalex.org/W2597809628","https://openalex.org/W2778498407"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"the":[3,56,59,62,79,96,143,153,174,191],"ViennaCL++,":[4],"an":[5],"OpenCL":[6,37,70,80,100,102,160,169,176,184],"C++":[7,71,73,103,120,161],"kernel":[8,47,65,104],"library":[9,18,66,88,141],"for":[10,33,49,82,133],"Vienna":[11],"Computing":[12],"Library":[13],"(ViennaCL)":[14],"combined":[15],"with":[16,72,159,181],"TensorFlow/Eigen":[17],"to":[19,45,54,69,77,139,167,189],"enable":[20,36],"acceleration":[21],"and":[22,84,101,122,129,135,162],"optimization":[23],"of":[24,58,99,116,145,155],"linear":[25,63],"algebraic":[26,64],"computing.":[27],"Previously,":[28],"TensorFlow":[29,83],"would":[30],"invoke":[31,41],"Eigen":[32,42,140],"solvers.":[34],"To":[35],"flow,":[38],"one":[39],"can":[40],"via":[43],"ViennaCL":[44],"generate":[46],"programs":[48],"GPU":[50],"computation.":[51],"In":[52],"order":[53],"support":[55,190],"features":[57,74],"latest":[60],"specification,":[61],"is":[67,93,165,179],"migrated":[68],"in":[75],"ViennaCL++":[76,117,156],"construct":[78],"flow":[81,92,124,164],"its":[85],"underlying":[86],"computational":[87],"Eigen.":[89],"The":[90,113],"software":[91],"based":[94],"on":[95,142],"state-of-the-art":[97],"specification":[98],"langauge,":[105],"as":[106,108],"well":[107],"SPIR-V":[109,123,163],"binary":[110],"intermediate":[111],"representation.":[112],"experimental":[114],"results":[115,150],"which":[118],"includes":[119],"class":[121],"are":[125],"achieving":[126],"8":[127],"times":[128,131],"49":[130],"speedup":[132],"BLAS2":[134],"BLAS3":[136],"operations":[137],"compared":[138],"x86_64":[144],"Intel":[146,175],"hardware.":[147],"Overall,":[148],"these":[149],"indicate":[151],"that":[152,173],"performance":[154],"runtime":[157],"execution":[158],"similar":[166],"traditional":[168],"C":[170],"flow.":[171],"Note":[172],"2.1":[177],"compiler":[178],"equipped":[180],"most":[182],"Khronos":[183],"2.2":[185],"(OpenCL":[186],"C++)":[187],"linguistic":[188],"experiment.":[192]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2018-05-17T00:00:00"}